diff --git a/.gitignore b/.gitignore
index 640e558..c56f760 100644
--- a/.gitignore
+++ b/.gitignore
@@ -4,6 +4,9 @@
 # Large downloaded data files
 download/
 
+# Temporary files
+job-lib/
+
 # Mac metadata
 .DS_Store
 
diff --git a/2.TCGA-MLexample-covariates.ipynb b/2.TCGA-MLexample-covariates.ipynb
new file mode 100644
index 0000000..24a87b9
--- /dev/null
+++ b/2.TCGA-MLexample-covariates.ipynb
@@ -0,0 +1,1149 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Create a logistic regression model to predict TP53 mutation from gene expression data in TCGA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import urllib\n",
+    "import random\n",
+    "import warnings\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns\n",
+    "import vega\n",
+    "import json\n",
+    "from sklearn import preprocessing\n",
+    "from sklearn.linear_model import SGDClassifier\n",
+    "from sklearn.model_selection import train_test_split, GridSearchCV, ShuffleSplit\n",
+    "from sklearn.metrics import roc_auc_score, roc_curve\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "from sklearn.feature_selection import SelectKBest\n",
+    "from sklearn.decomposition import PCA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "plt.style.use('seaborn-notebook')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Specify model configuration"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# We're going to be building a 'TP53' classifier \n",
+    "GENE = '7157' # TP53"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "*Here is some [documentation](http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDClassifier.html) regarding the classifier and hyperparameters*\n",
+    "\n",
+    "*Here is some [information](https://ghr.nlm.nih.gov/gene/TP53) about TP53*"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Load Data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1min 19s, sys: 6.25 s, total: 1min 26s\n",
+      "Wall time: 1min 28s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "path = os.path.join('download', 'expression-matrix.tsv.bz2')\n",
+    "expression = pd.read_table(path, index_col=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 51.8 s, sys: 1.08 s, total: 52.9 s\n",
+      "Wall time: 53 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "path = os.path.join('download', 'mutation-matrix.tsv.bz2')\n",
+    "Y = pd.read_table(path, index_col=0)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 40 ms, sys: 0 ns, total: 40 ms\n",
+      "Wall time: 44.1 ms\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "path = os.path.join('download', 'covariates.tsv')\n",
+    "covariates = pd.read_table(path, index_col=0)\n",
+    "\n",
+    "# Select acronym_x and n_mutations_log1p covariates only\n",
+    "selected_cols = [col for col in covariates.columns if 'acronym_' in col]\n",
+    "selected_cols.append('n_mutations_log1p')\n",
+    "covariates = covariates[selected_cols]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "y = Y[GENE]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "sample_id\n",
+       "TCGA-02-0047-01    0\n",
+       "TCGA-02-0055-01    1\n",
+       "TCGA-02-2483-01    1\n",
+       "TCGA-02-2485-01    1\n",
+       "TCGA-02-2486-01    0\n",
+       "TCGA-04-1348-01    1\n",
+       "Name: 7157, dtype: int64"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# The Series now holds TP53 Mutation Status for each Sample\n",
+    "y.head(6)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    0.645907\n",
+       "1    0.354093\n",
+       "Name: 7157, dtype: float64"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Here are the percentage of tumors with NF1\n",
+    "y.value_counts(True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Pre-process data set\n",
+    "TODO: currently running PCA on both train and test partitions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# Pre-process expression data for use later\n",
+    "n_components = 100\n",
+    "scaled_expression = StandardScaler().fit_transform(expression)\n",
+    "pca = PCA(n_components).fit(scaled_expression)\n",
+    "explained_variance = pca.explained_variance_\n",
+    "expression_pca = pca.transform(scaled_expression)\n",
+    "expression_pca = pd.DataFrame(expression_pca)\n",
+    "expression_pca = expression_pca.set_index(expression.index.values)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "fraction of variance explained: 0.704812987245\n"
+     ]
+    }
+   ],
+   "source": [
+    "print('fraction of variance explained: ' + str(pca.explained_variance_ratio_.sum()))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Gene expression matrix shape: 7306, 20468\n",
+      "Full feature matrix shape: 7306, 133\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Create full feature matrix (expression + covariates)\n",
+    "X = pd.concat([covariates,expression_pca],axis=1)\n",
+    "print('Gene expression matrix shape: {0[0]}, {0[1]}'.format(expression.shape))\n",
+    "print('Full feature matrix shape: {0[0]}, {0[1]}'.format(X.shape))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Set aside 10% of the data for testing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Size: 133 features, 6,575 training samples, 731 testing samples'"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Typically, this can only be done where the number of mutations is large enough\n",
+    "train_index, test_index = next(ShuffleSplit(n_splits=2, test_size=0.1, random_state=0).split(y))\n",
+    "\n",
+    "X_partitions = {\n",
+    "    'full': {\n",
+    "        'train': X.ix[train_index], \n",
+    "        'test': X.ix[test_index]\n",
+    "        },\n",
+    "    'expressions': {\n",
+    "        'train': expression_pca.ix[train_index], \n",
+    "        'test': expression_pca.ix[test_index]\n",
+    "        },\n",
+    "    'covariates': {\n",
+    "        'train': covariates.ix[train_index], \n",
+    "        'test': covariates.ix[test_index]\n",
+    "        }    \n",
+    "    } \n",
+    "\n",
+    "y_train = y[train_index]\n",
+    "y_test = y[test_index]\n",
+    "\n",
+    "'Size: {:,} features, {:,} training samples, {:,} testing samples'.format(\n",
+    "    len(X_partitions['full']['train'].columns), \n",
+    "    len(X_partitions['full']['train']), \n",
+    "    len(X_partitions['full']['test']))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Define pipeline and Cross validation model fitting"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# Parameter Sweep for Hyperparameters\n",
+    "param_grid = {\n",
+    "    'classify__loss': ['log'],\n",
+    "    'classify__penalty': ['elasticnet'],\n",
+    "    'classify__alpha': [10 ** x for x in range(-3, 1)],\n",
+    "    'classify__l1_ratio': [0, 0.2, 0.8, 1],\n",
+    "}\n",
+    "\n",
+    "pipeline = Pipeline(steps=[\n",
+    "    ('standardize', StandardScaler()),\n",
+    "    ('classify', SGDClassifier(random_state=0, class_weight='balanced'))\n",
+    "])\n",
+    "\n",
+    "models = ['full', 'expressions', 'covariates']\n",
+    "\n",
+    "cv_pipelines = {mod: GridSearchCV(estimator=pipeline, \n",
+    "                             param_grid=param_grid, \n",
+    "                             n_jobs=1, \n",
+    "                             scoring='roc_auc') for mod in models}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Fitting CV for model: full\n",
+      "Fitting CV for model: covariates\n",
+      "Fitting CV for model: expressions\n",
+      "CPU times: user 6.72 s, sys: 14.8 s, total: 21.5 s\n",
+      "Wall time: 5.43 s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "for model, pipeline in cv_pipelines.items():\n",
+    "    print('Fitting CV for model: {0}'.format(model))\n",
+    "    pipeline.fit(X=X_partitions.get(model).get('train'), y=y_train)\n",
+    "# cv_pipeline_full.fit(X=X_train_full, y=y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "full: 92.537%\n",
+      "{'classify__alpha': 0.1, 'classify__penalty': 'elasticnet', 'classify__l1_ratio': 0, 'classify__loss': 'log'}\n",
+      "covariates: 84.259%\n",
+      "{'classify__alpha': 0.1, 'classify__penalty': 'elasticnet', 'classify__l1_ratio': 0, 'classify__loss': 'log'}\n",
+      "expressions: 91.959%\n",
+      "{'classify__alpha': 0.1, 'classify__penalty': 'elasticnet', 'classify__l1_ratio': 0, 'classify__loss': 'log'}\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Best Params\n",
+    "for model, pipeline in cv_pipelines.items():\n",
+    "    print('{0}: {1:.3%}'.format(model, pipeline.best_score_))\n",
+    "\n",
+    "    # Best Params\n",
+    "    print(pipeline.best_params_)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize hyperparameters performance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>mean_fit_time</th>\n",
+       "      <th>mean_score_time</th>\n",
+       "      <th>mean_test_score</th>\n",
+       "      <th>mean_train_score</th>\n",
+       "      <th>param_classify__alpha</th>\n",
+       "      <th>param_classify__l1_ratio</th>\n",
+       "      <th>param_classify__loss</th>\n",
+       "      <th>param_classify__penalty</th>\n",
+       "      <th>params</th>\n",
+       "      <th>rank_test_score</th>\n",
+       "      <th>...</th>\n",
+       "      <th>split2_test_score</th>\n",
+       "      <th>split2_train_score</th>\n",
+       "      <th>std_fit_time</th>\n",
+       "      <th>std_score_time</th>\n",
+       "      <th>std_test_score</th>\n",
+       "      <th>std_train_score</th>\n",
+       "      <th>classify__alpha</th>\n",
+       "      <th>classify__l1_ratio</th>\n",
+       "      <th>classify__loss</th>\n",
+       "      <th>classify__penalty</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>0.032062</td>\n",
+       "      <td>0.003444</td>\n",
+       "      <td>0.886926</td>\n",
+       "      <td>0.903579</td>\n",
+       "      <td>0.001</td>\n",
+       "      <td>0</td>\n",
+       "      <td>log</td>\n",
+       "      <td>elasticnet</td>\n",
+       "      <td>{'classify__alpha': 0.001, 'classify__penalty'...</td>\n",
+       "      <td>11</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.889509</td>\n",
+       "      <td>0.905814</td>\n",
+       "      <td>0.000558</td>\n",
+       "      <td>0.000247</td>\n",
+       "      <td>0.006383</td>\n",
+       "      <td>0.009607</td>\n",
+       "      <td>0.001</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>log</td>\n",
+       "      <td>elasticnet</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>0.043467</td>\n",
+       "      <td>0.003128</td>\n",
+       "      <td>0.901912</td>\n",
+       "      <td>0.916187</td>\n",
+       "      <td>0.001</td>\n",
+       "      <td>0.2</td>\n",
+       "      <td>log</td>\n",
+       "      <td>elasticnet</td>\n",
+       "      <td>{'classify__alpha': 0.001, 'classify__penalty'...</td>\n",
+       "      <td>9</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.904836</td>\n",
+       "      <td>0.920198</td>\n",
+       "      <td>0.004416</td>\n",
+       "      <td>0.000031</td>\n",
+       "      <td>0.002592</td>\n",
+       "      <td>0.005190</td>\n",
+       "      <td>0.001</td>\n",
+       "      <td>0.2</td>\n",
+       "      <td>log</td>\n",
+       "      <td>elasticnet</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>2 rows × 24 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   mean_fit_time  mean_score_time  mean_test_score  mean_train_score  \\\n",
+       "0       0.032062         0.003444         0.886926          0.903579   \n",
+       "1       0.043467         0.003128         0.901912          0.916187   \n",
+       "\n",
+       "  param_classify__alpha param_classify__l1_ratio param_classify__loss  \\\n",
+       "0                 0.001                        0                  log   \n",
+       "1                 0.001                      0.2                  log   \n",
+       "\n",
+       "  param_classify__penalty                                             params  \\\n",
+       "0              elasticnet  {'classify__alpha': 0.001, 'classify__penalty'...   \n",
+       "1              elasticnet  {'classify__alpha': 0.001, 'classify__penalty'...   \n",
+       "\n",
+       "   rank_test_score        ...          split2_test_score  split2_train_score  \\\n",
+       "0               11        ...                   0.889509            0.905814   \n",
+       "1                9        ...                   0.904836            0.920198   \n",
+       "\n",
+       "   std_fit_time  std_score_time  std_test_score  std_train_score  \\\n",
+       "0      0.000558        0.000247        0.006383         0.009607   \n",
+       "1      0.004416        0.000031        0.002592         0.005190   \n",
+       "\n",
+       "   classify__alpha  classify__l1_ratio  classify__loss  classify__penalty  \n",
+       "0            0.001                 0.0             log         elasticnet  \n",
+       "1            0.001                 0.2             log         elasticnet  \n",
+       "\n",
+       "[2 rows x 24 columns]"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "cv_results_df_dict = {model: \n",
+    "    pd.concat([\n",
+    "        pd.DataFrame(pipeline.cv_results_),\n",
+    "        pd.DataFrame.from_records(pipeline.cv_results_['params']),\n",
+    "    ], axis='columns') for model, pipeline in cv_pipelines.items()}\n",
+    "\n",
+    "model = 'full'\n",
+    "\n",
+    "cv_results_df_dict[model].head(2)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAdIAAAFYCAYAAADnS32IAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzs3Xd4FNXXwPHvLqEGkDQSQq+HIiiIIEqRLiCIdBUBERFB\nBQQRpYt06SqiUn5IU3lFkSa9CIICilK89CYtCR0Cqe8fu4QEUpbgJrvZ8+HZJzsze3fOjOuevXfu\n3GuJjY1FKaWUUqljTe8AlFJKKXemiVQppZR6AJpIlVJKqQegiVQppZR6AJpIlVJKqQegiVQppZR6\nAF7pHUBSGj7cRu/LcbIzV8+ldwhK/SeyemVN7xAyvN8Pr7I4670rFK6V6u/7v45vdFpcjnLZRKqU\nUsozWCzpngsfiDbtKqWUUg9Aa6RKKaXSlcXi3nU6945eKaWUSmdaI1VKKZWurLj3NVJNpEoppdKV\nu3c20kSqlFIqXVnd/BqpJlKllFLpyt1rpO79M0AppZRKZ5pIlVJKqQegTbtKKaXSlUV77SqllFKp\np52NlFJKqQfg7p2NNJEqpZRKV1Y3T6TuXZ9WSiml0pkmUqWUUuoBaNOuUkqpdGVx8zqdJlKllFLp\nSjsbKaWUUg/A3TsbaSJVSimVrtx9QAb3bphWSiml0pkmUqWUUuoBaNOuUkqpdKVDBCqllFIPQHvt\nKqWUUg9Ae+0qpZRSD0B77SqllFIeTGukSiml0pUzOxuJyETgCSAW6GmM+T3eth5AeyAa2GGM6SUi\nOYE5gA+QFRhmjPk5uX1ojVQppVSGJCK1gJLGmGrAq8CUeNtyA+8CNYwx1YGyIvIE0AkwxpjaQCtg\nckr70USqlFIqXVksllQ/UlAX+AHAGLMf8LEnUIAI+yOniHgBOYALQCjgZ3+Nj305WZpIlVJKpSur\nxZLqRwqCgJB4yyH2dRhjbgLDgCPAcWC7MeaAMWYhUEhEDgGbgL4p7USvkSqllEpXadhrN25H9prp\nB0Ap4AqwTkQeAcoDJ4wxz9iXZwCVk3tTTaSJyJY9K++OepNcub3JnCUzcz9bxK1bEbzS8wWio6K4\nGX6Lse9/wrUr1+PKNGxRm7pNa8YtlypXnOZVOtC8fSNqPfMke/8wfDV+LgC1m1TH1z8P//e/pWl+\nbK7CYrEwaGQfSkhRIiMiGT5gAuE3whn+cX+8vLyIiori/V4jCAu5cE/ZrFmz8P3q2UyfMocli1by\n0istadi0Dn/u+JsJIz8HoHHzevgH+DLny2/T+tBcSmrOc+UnHuXjz4Zx+MBRAA6ao4weMlnPcxIs\nFgvvf9ST4qUKExkRxahBUzh+5CRtOzan1/tdqVOpBeE3biYoU6lqBUZPHciRg8cBOHTgKB8P+4x2\nnZpTv0ktdu/cx5TRXwLwTLM6+AX4MG/G/6X5sWUAp7HXQO2CgTP252WAI8aYUAAR2Qw8BjwO/Axg\njNktIsEikskYE53UTjSRJqJB86c5dew0syYtwDfAh7EzBhMefpMx703h1LEztHvteRq3rse3M36M\nK/Pz9+v5+fv1AJSvXIaaDZ8EoGbDavRuP4hRXw4ka/asxETH0PD52gzsNjJdjs1V1G5QnZy5vOnQ\nogcFCgXz3tC3uHzxCovmL2XVsvW07dCcDl3aMHHU5/eU7fp2By5fuhq33ODZ2nRo0YPpc8eTPXs2\nomNieL5NY97o2C8tD8klpfY879z+J33eGJJgnZ7nxNWq/yQ5c+Xg1da9yV8oH30GvcGa5Zvw9c9D\nyPmwJMvt+u1v+r85PMG6eo1r8Wrr3nzyv9Fky56NmOhomrVuyNudBzj7MNKVE0c2WoWt+Xa6iFQC\nThtjbn95HAPKiEh2Y0w4tlrncmzXRasC/ycihYFrySVR0ESaqMuXrlK0VGEAcuX25vKlq9y8cZPc\neXIBZ8iZ25tTx04nWf6lbq0Y856tc1hUZBQAl8Iu450zB/Wa1uSnhT8TFZXsf5cMr3CRAuzZvR+A\nUydOE5w/iH49hnHrVgQAF8MuU+bhUveUK1K8EMVKFGHzul/j1kXaz/GFsIvkzOXNsy0asHDO4rhz\n78lSe54To+c5cQWLBLN3twHg3xNnyJc/kI2rt3L92g2eaVbnvt4rMjISgIthl8iZKweNm9fju6+X\nZPhz7KyRjYwxW0Vkp4hsBWKAHiLSCbhsjFksIuOA9SISBWw1xmwWkT+AmSKyEVuO7JbSfpyWSEWk\nNLYeU/nsq04Dq4wxh5y1z//KxhVbafDc08xaPoWcub0Z1H0016/d4ONZQ7l65TrXrlxj5qT5iZYt\n9XBxQs6GcTHsMgAWi5VMXpnwy+tDbEwMZSsKh/45yjvD3+CoOc7iucvT8tBcxkFzhPavtmbujEUU\nKpKfAoXykd07O+HhN7FarbTr0JzpU/53T7m+A7szavAkmrV8Jm6d1WLByysTAYH+xMTGUrFyef7Z\ne5Bh497j4P7DzJ25KC0PzaWk9jwXK1mEKV+NJHeeXHw+6X9s+2WHnuckHDbHeOGVFiyYtZiChYPJ\nXzAfWbNm4fq1G8mWK1qiEOOnDyN3nlx8OWUuv23ZhdX+feEf6EtsTCyPPFYOs+8wg0a/w6F/jrJg\n9uI0OqqMwxjT/65Vu+Ntmw5Mv+v114A297MPp/TaFZGBwBdALmw9oo4C/sB8EentjH3+l+o8W4Pz\nZ0J5pfHbvPfqh/QY0Jke77/CsF4f06VpL/b+YWjarmGiZZ9pUYfVP26IW1767SrGzhzCL6u30/a1\n55k77TtadWrKxMGfU7xMUfwDfdPoqFzLLxu2s2f3fmZ9N4X2nVtz5NBxLBYLVquVkZMG8NvWXWzf\nsitBmaYtGrJ7117+PXk2wfpv5/7IVwsnsWbFRrp0f4lpk2bTsWs7hvYbS+lyJQkMCkjLQ3MpqTnP\nJ46e4vNJs3m7ywcMfGcUw8b2wyuzl57nJGzd+Dt7/zJ8sXA87V55nqOHT6TYVHny2L98NXUufV4f\nwtB3xzFo9Dt4ZfZi0fylfD5vHOtW/kKnN9rx5dS5tO/Sio/en0ipciXIG+SfRkeVtiwP8M8VOKtG\n2gioboyJjb9SREYCG4GJTtrvf6JcRWHnFtuPliPmOH4BPuTNF8C+P2zNN7u2/kWdZ6snWrbC4+X4\nbOTMuOWNK7ayccVWggsF0UaKcGjfUby8MhEbG0vouTDyBgcQeu7eDjWe4JOPZ8Q9X7ZpPhdCL/LR\n+PdtX+ST760l1ajzBAUKBVOrTjUC8wUQERHJuTMhrPxpHSt/WkehIvmRMiXYv+cAXpm9iI2N5dzZ\nEPIVCOTc2ZB73s9T3O95Pn8ulJ+X2q73nzpxmtCQCwQG+et5TsbnE2bHPV+8bjYXwi4l+/qQc2Gs\nXrYRsDUHh4VcIG+gP6uXbmD10g0ULBJMqTLF+GfPQbwy274vzp8NISh/Xs6fTfG2Rrfj7tOoOSt6\nL+406cYXDC7yEyIZp0+cRSqUACBvPn/Cb9zkQuhFChXLD9iab/89fvaecr4BPty8cTPR65/tu7fm\n689sPRu9Mtt+vwQE+RF23jOTaKkyxRk27j0AnqpVhf17DtLoubpERkby2cRZiZbp9+YwXmz2Ou2f\n7873C5cxfcoctm/ZGbe9W69OTLOXzWw/x0H58hJyLuN98TgqNee5cfN6dOzaFgC/AF/8/H04F+/L\nW89zQiVLF2PQ6HcAqFazMv/sPURsbGyyZZ5pVof2XVoB4Ofvg6+/D+fjnb/X3nqZLyZ/DUDmzJkB\nCMznuT+6XZ2zaqQDgNUiEsadm2HzYWvqfcNJ+/zPLPt2NX2Gd2fcrKFk8rIy5cMviYyIpNew14mK\niubq5WtMGDQNgPfH9WT8wM+IuBWJb0AeLl24fM/7PVypNP8eP0PY+YsArF+2hYlzP+Lk0X85969n\n/oI/+M8RrBYL8378nIhbEfTvOZxxnw4la9YszFg4CYAjh44zYuBExkwdzOC+o+M6yCSm0uMVOHH0\nVNyX0fIf1/D14s84cuj4PU3BniQ153nD6i2MmTKY2vWrkzmzFx8NnBDX2UXP870OmaNYrVZmfz+F\nW7ciGfzOaF7p/gJVn6qEX4Avk2eO4O8/9jN1zFeMmPwBH/b7mE1rf+Wjie9Ts141MmfOzOjBU+LO\n8aOVH+bEsX8JOWfr8fvzknXM+G4Sxw6f4PSpjHmO3X0+UktKv5wehIgU5c49PKeNMccdLdvw4TbO\nC0wBcObqufQOQan/RFavrOkdQob3++FVTst2bSp3TvX3/bc7ZqZ7Fnbq7S/GmKPYOhrFEZHnjDE/\nJlFEKaWUh3GVTkOp5dREap+O5naN9Iwx5jqQx5n7VEoppdKSUxKpiFTGNl1NHmwj51uAYBH5F+jh\njH0qpZRyT84akCGtOKtGOgnobIz5J/5K+xBNnwI1Ey2llFJKuRln3f5ivTuJAhhjdgGZnLRPpZRS\nbsiJ85GmCWfVSLeJyBJsE6revr8jCNts4xudtE+llFJuSJt2E2GMeUdEamIba7eqffVpYKgx5tek\nSyqllPI02ms3CcaYTdhmF1dKKaWS5O41Uvce4FAppZRKZ5pIlVJKqQegE3srpZRKV67S+za1NJEq\npZRKV+5+jVQTqVJKqXSlvXaVUkqpB+DuNVLtbKSUUko9AE2kSiml1ANIsWlXRPywjVBUxL7qGLDW\nGBPmvLCUUkp5igzba1dEvIFxwHPAFuC4fVNlYIKI/Aj0s88xqpRSSqWKu18jTa5GuhL4H/C2MSYq\n/gYRyQR0tr+mhvPCU0opldFl2Bop0N4YczyxDcaYaOBLEVnlnLCUUkp5igx7+8vtJCoiZbBNxv04\nEANsA3oYYw4llWiVUkopT+FIr92pwHhs84nmBz4HpjkzKKWUUp7Dakn9wxU4MiCDxRizLN7yYhF5\ny1kBKaWUUu7EkRppFhGpdHtBRB5HR0RSSin1H7FYLKl+uAJHEmJfYL6I5AUswGmgo1OjUkop5TEy\n8u0vABhjtgOlReQhINYYc8X5YSmllPIUrlKzTK3kBmR43xgzSkS+BmLjrQfAGNPB+eEppZRSri25\nGuku+981iWyLTWSdUkopdd+sGfg+0p/tT8sYY/rH3yYiXwFznBmYUkopz5CRm3afB1oA9UQkON6m\nzEBNZwemlFJKuYOUxto9j22Q+rXx1scAQ50Yk1JKKQ+SYXvtGmPCgS0iUtEYczP+NhEZB7zr7OCU\nUkplfG6eRx26j7SGiIwE/OzLWYELaCJVSimlHEqkHwFvAZOAV4G2wGZnBgVwI/Jmyi9SysV5Z/FO\n7xA8wsadX6d3COoBuHvTriNDBF4xxmwDIowxe40xg4F3nByXUkopD2F5gH+uwJEaaWYRqQ5cFJGO\nwD6gqHPDUkop5Sky7O0v8byObQq1d4FPgLzASGcGpZRSSrkLRxJpMWPMCvvzBs4MRimllOfxhGuk\n74iITpumlFLKKSyW1D9cgSMJ8hKwT0R2ARG3V+qg9UoppZRjiXSp/aGUUkr959y9adeR+Uj/l9Q2\nEVlnjKnz34aklFLKk7jKbSyp9aDXPt376JVSSqU7Z9ZIRWQi8AS26T97GmN+j7etB9AeiAZ2GGN6\npVQmMY50NkqOzkuqlFLKJYlILaCkMaYatpH5psTblhvbbZ01jDHVgbIi8kRyZZLyoIlUKaWUeiBO\n7LVbF/gBwBizH/CxJ1CwdZ6NAHLa70zJgW0c+eTKJEoTqVJKqYwqCAiJtxxiX4d9VrNhwBHgOLDd\nGHMguTJJ0WukSiml0lUaDhEYtyN7LfMDoBRwBVgnIo8kVyYpqaqRikg5+9PJqSmvlFJK3Wa1WFL9\nSMFpEtYmg4Ez9udlgCPGmFBjTAS2Wc0eS6FM4vHfx7HGNxXAGPNDKssrpZRSgFOvka4CWgGISCXg\ntDHmqn3bMaCMiGS3L1cGDqZQJlFJNu2KSOdkyuVLMXyllFLKAc66/cUYs1VEdorIViAG6CEinYDL\nxpjFIjIOWC8iUcBWY8xmgLvLpLSf5K6RjgE2ANcS2fbQfR2NUkoplQ6MMf3vWrU73rbpwHQHyiQr\nuUTaAehojHnl7g0isv5+dqKUUkplVEleI7VPnfaZiORMZPN854WklFLKk1ge4J8rSPb2F2PMpiTW\nf+mccJRSSnmaNLz9xSmS62x0ksSHALQAscaYQk6LSimllMewunceTbZGWgMdS1cppZSTZdgaKfAx\n0MUYcymxjSLiA3xpjGnllMiUUkopN5BcIp0G/CYiK4CVwEn7+oLAM/ZHN+eGp5RSSrm2JBOpMWat\niFQEXgN6YkugYEuoK4FKxpjrzg9RKaVURpaRm3axJ8pJ9odSSin1n8vInY2UUkopp8vQNVKllFLK\n2dw8j6Y8+4v9OqlSSimlEuHINGrjnR6FUkopj+XE+UjThCNNuydEZAOwDYi4vdIYM9hZQSmllFLu\nwpFEetT+8BgWi4W+w7pTtGQhoiKj+HjoZ9y8cYuBY3tjzWQlLOQiH707gcjIqATl3ni3ExUeK0sm\nr0zMnb6ITat/pVWHptRpVJ09f+zns7GzAajftBa+/j58M8tz50W3WCwMGtmHElKUyIhIhg+YQPiN\ncIZ/3B8vLy+ioqJ4v9cIwkIuxJWp/MSjfPzZMA4fsH0cD5qjjB4ymZdeaUnDpnX4c8ffTBj5OQCN\nm9fDP8CXOV9+my7H5yosFgv9PnyT4qUKExkZxdjBnxB+4yZDPu6L1Wr7LA97dxyREXc+y01bNeCZ\n5nXilks/XJK6j7akTcfnqNe4Bn/t2scnY2YC0KDZ0/j5+7Bg5uI0PzZX8fvOXfTpP5DixYoCULJE\ncTq//BLvD/mQmJgY/P39GDVsMFmyZElQbsyEyfy1Zw8WLPTv04uHy5Vl7oJvWLl6LRUfqUCfnm8C\nsHTFz4SFhdGx/YtpfmxpxVUGn0+tFBOpMWaYiPgBRY0xO0TEaoyJSYPY0k31ulXxzpWD7i+8R3DB\nIHoOeI1LFy7z/fzlbFi5ha69X6ZJq/r8sGBFXJmKVctTtGQh3mjXj9x5cjFz8SQ2rf6VOo2q0/2F\n95gw80OyZc9KTHQMTVrWo+9rw9LxCNNf7QbVyZnLmw4telCgUDDvDX2LyxevsGj+UlYtW0/bDs3p\n0KUNE0d9nqDczu1/0ueNIQnWNXi2Nh1a9GD63PFkz56N6JgYnm/TmDc69kvLQ3JJNes9Qc5c3nRt\n25f8hYLoPbAbFy9c5v/mLmXdyl/o9k5Hnm3VgMXzl8eV+WnRKn5atAqAilUepm6jmgDUbVSDrm37\nMnn2iLjPctOWDejdRRunKld6lAljRsYtDxz2Ee1at6RhvTpM/vRzFi9ZSttWLeK2/77zD06cPMm8\nmV9y5OgxBg0fwbyZX/LzmnXMnfkFr/XoyY3wcDJZrfywZCnTpkxIj8NKMy7SQptqjnQ2aoetWXe2\nfdVUEenszKDSW8Eiwez/6yAAp0+eJTA4gEerlmfL2u0AbFn/G49VeyRBmd2/72VwzzEAXLtynWzZ\ns2K1WomMjATg4oVLeOfyplXHpnw/bzlRd9VmPU3hIgXYs3s/AKdOnCY4fxAjBk5kzYqNAFwMu8xD\nPrkdeq/bLQMXwi6SM5c3L73SkoVzFnv8OQYoUCQ/+/4yAPx74ixBwXmpVKU8m9dtA+CXddt5/Mmk\n+xN27vEiMz9dAHDnsxx2iZy5vGnT6TkWzVuq5zkRO3b9Qe2a1QGoVeMptv22I8H27b/voE4t2w+U\nYkWLcOXKVa5du07mzJkB8PXx4dq1a8xd+C3tWreMW59Rufs1Ukc6G/UBHgFC7Mt9gddTKiQiz4jI\nS/YxeeOv73LfUaaxwweOUaV6RaxWKwWL5ie4YBDBBQLjvrAvhl3GLyDBYRETE8PN8FsANGlVn22b\ndhITE4PVYiWTVyb88/oSGxND+UplCL8RTv+Rb9O6Y7M0PzZXcdAc4cmaVbBarRQpVpAChfKR3Tu7\n7ZxZrbTr0JwVP665p1yxkkWY8tVIZi+ayhPVKwO2/wm9vDIREOhPTGwsFSuX58b1cIaNe4/2nT17\nKOjD5hhVazyG1Wql0O3PcsGguKbcixcu4X/XZ/m2MuVLcu5sCBdCLwJgtd75LMfExFKhUlnCb4Qz\nYFQv2nZ6Ls2OyRUdPnqMt97pR4cu3di6/TfCw8PjmnL9fH0ICQ1N8PrQsDB8fPLELfv6+BAaFkZM\nTAyRUVGEhIZitVj5c/ff5MiRnUEfjuDr+d+k6TEpxzmSSC8bY27cXjDGhBOv01FiROQroDPwJLBd\nROrG2+zyDf3bN+1i/98H+GTeKNp0bMbxIyeJjIiM257czcPV61bl2Vb1mPjhdAB+WLCCKXNGsPHn\nX2n/eitmfbKQdp2fZ8yAqZQsU4yAQD+nH48r+mXDdvbs3s+s76bQvnNrjhw6jsViwWq1MnLSAH7b\nuovtW3YlKHPi6Ck+nzSbt7t8wMB3RjFsbD+8Mnvx7dwf+WrhJNas2EiX7i8xbdJsOnZtx9B+Yyld\nriSBQQHpdJTpb9umHez76wDT5o+lbafmHDt812c5mWtTzdo0ZNn/3fkx8/38ZXz69Wg2/LyFDt3a\nMGPqfF58tSUjP5hMqTLFCQjyzM9yoYIFeaNLZ6aMH8OIoQMZMnwUUdHRcdtjHZhDK9b+oratnufV\nbm9Sr87TfDV7Dt1e68zsufMZNvB9/jlwgLPnzjvpKNKXxWJJ9cMVONLZKFREOgLZRaQS0JY7tdOk\niDGmBoCI5AOWiMgHxpjV4B5Xlb+aNA+YB8DC1dMJORdGlqxZiLgVQUCgL2HnL9xTpkr1irzcrTV9\nuwzl+jXbb4+1yzezdvlmChTOR4nSLTiw9zBemTMRGxtLyNlQgvLnJeRcWBoemev45OMZcc+XbZrP\nhdCLfDT+fVvCnPy/e15//lwoPy9dD9iag0NDLhAY5M/Kn9ax8qd1FCqSHylTgv17DuCV2YvY2FjO\nnQ0hX4FAzp1N6SObcX0xcU7c8+/WzuD8uVCyZs3CrVsRBAT5EZLIZxmgYpUKjP/wzjXqNcs2sWbZ\nJgoUDqZ96WKYvYfw8rJ9ls+fDSVfcCAhZz3vsxyYN4BnGtQDoGCBAvj7+bJn3zlu3rxFtmxZOXc+\nhLwB/gnK5A3wJzTsznk/HxJKgL8fRQrXp1GD+hw/cZIDBw5SrkxpoqKisVqtBOYN4MzZswQF5k3T\n40sLLpIPU82RGmk34HEgF/AVkB14NYUyXvYEijHmDNAEGCUiL+IGc5wWlyL0H/k2AFVqVOLAviPs\n2Lqbpxs+CUCtBk+yfXPC2pJ3zhx07/cK770+nKuXr93znq+8+QIzp9quNd2+3pE3nz+hSXyJZXSl\nyhRn2Lj3AHiqVhX27zlIo+fqEhkZyWcTZyVapnHzenTs2hYAvwBf/Px9OHf2TpNZt16dmGYvmzmz\n7TdiUL68hJwLvffNPESJ0kUZMKoXAE/UeIwDew/x+5Y/ebrhUwA83fAptm3aeU85/7y+hN8IT/T6\n56tvvciMqbYfmbc/y4H5Agg573lJFGy9amd/PR+A0NAwwi5coHnTJqxeZ/vRt2b9ep6q9kSCMk9W\nrcrqtbbt+/4x5A3wx9vbO277tC9n8EZX21WwyMhIYmNjOXvuPAH+CROycg2O1EifMca8GX+FiHQD\nPk/i9QAfABtE5DFjzDVjzHkRqQ1MAKqlPty0ceTAcawWC9O/+5iIW5EM7zue6OhoBozpTbO2DTl3\nOoQVP6wDYOiEvox8fwp1GtfgIZ9cfDjpTk/Rj96byPkzoVR4rCwnj52OS5qrf9rItIVjOX7kFGdO\nnUuXY0xvB/85gtViYd6PnxNxK4L+PYcz7tOhZM2ahRkLbXMkHDl0nBEDJzJm6mAG9x3NhtVbGDNl\nMLXrVydzZi8+Gjgh7ou+0uMVOHH0FOftSXP5j2v4evFnHDl0nH9Pnk2340xvh80xLFYLMxZN5FZE\nJEPfGUt0dDSDx/WlebtGnD19nuWLbc23H058jxH9J3LrVgR+Ab5cDLt8z/s9UrkcJ4+djmtFWfXT\nBr74djzHD5/02M9y7ZrVeW/gUNZv2kxkZCQD+79LGSnFB0OGs2jxj+QLCqTZs40BePeDQQwfPJBH\nHylP2dJC+85dsVqtDOjXJ+79dv7xJ4ULFSQwr+2SROOGDWj/aleKFSlCgfzB6XKMzuYqTbSpZYlN\nogHfPjRgJWydi8bF25QZGGKMSdV/URHJbr/Omqwa0szla67u7vLNe78o1X/LO4t3yi9SD2zjzq/T\nO4QML0tuP6dlu5kdxqb6+77znH7pnoWTq5HeBAKBPECNeOtjgHcfYJ8NgB8foLxSSinlMpKb2Hs/\nsF9E1hljtqXmzUUkJxBkXzxjn980TzJFlFJKeRh3b9p15BrpTRHZAeQ0xpQWkUHAKmPM9qQKiEhl\nYAq2pBmKradusIj8C/T4D+JWSimVQbh5HnUokU7Fdk/oZPvyN8As4KlkykwCOhtj/om/0n77zKdA\nzfsPVSmlVEbkKiMUpZYjt79EGmP+ur1gjDkApDQmmPXuJGovuwvIdH8hKqWUUq7LkRpplIgUxX7/\np4g0IuVBFbaJyBLgB+4M3hAEtAI2pjJWpZRSGZAnXCPtg62XrYjIZeAY0DG5AsaYd0SkJlAXqGpf\nfRoYaoz5NfXhKqWUUq7FkWnU/gYqiEgAcMsYc8WRNzbGbAI2PWB8SimlMjg3r5CmnEhFpDzwCvAQ\nYBERAIwxGXoqNaWUUmnDE5p2vwMWAHudHItSSikP5OZ51KFEetwYM8zpkSillPJI7n77iyOJdI6I\nDAS2Eu+2F/s1UKWUUsqjOZJI2wMCNIy3LhYdVEEppZRyKJEGGGOKOT0SpZRSHsnNW3YdGtlok4gU\nd3okSimlPJLFYkn1wxU4UiNtALwpIqHYrpFagFhjTCGnRqaUUsojuEg+TDVHEmmTRNb5/NeBKKWU\n8kyuUrNMrRSbdo0xxwFvoLD9UQrbfaVKKaWUx3NkZKPJ2Jp3g4BDQHHgYyfHpZRSSrkFRzobVTHG\nlAH+NMY8DtQHcjg3LKWUUp7CYkn9wxU4kkhv2f9mFRGLMWYnyU/qrZRSSjnMarGk+uEKHOlsZESk\nO7aZXFbo5v+vAAAgAElEQVSLiAHyODcspZRSnsJF8mGqOZJIu2HrpXsJaAcEAqOcGZRSSinP4e69\ndh1JpBONMb3sz+c7MxillFLK3TiSSKNFpA62Qesjbq80xsQ4LSqllFIew80rpA4l0i5AL2wjGt0W\nC2RySkRKKaXUf0REJgJPYMtbPY0xv9vX5wfmxXtpMaC/MWa+iIwFamDLkaOMMd8nt48UE6kx5qFE\nAivp8FEopZRSyXDWNVIRqQWUNMZUE5EywEygGoAx5l/gafvrvIANwBIRqQ08bC/jB/wBPFgiFZFM\n2KZQ87evygoMAIrc91EppZRSd3Fi025d4AcAY8x+EfERkdzGmCt3va4T8H/GmGsisgn4zb7+EuAt\nIpmMMdFJ7cSRpt252HrtPgL8gq2KPOS+DkUppZRKghN77QYBO+Mth9jX3Z1Iu2AbwQ97wrxuX/8q\nsDy5JAqODchQwBjzjO39TWugOvC4A+WUUkopV3JPxhaRasA/d9dSReQ5bIn0zZTe1JFEepuXiGSz\nD2Jf7j7KKaWUUkly4hCBp7HVQG8LBs7c9ZpngTXxV4hIQ2yXMBsZYy6ntBNHEuk6EemHrZ15l4gs\nc7CcUkoplSInTuy9CmgFICKVgNPGmKt3veZxYPftBRF5CBgHPGuMueBI/I702h1y+0KriGzFNrLR\nKkfeXCmllEovxpitIrLTnrtigB4i0gm4bIxZbH9ZPuB8vGJtsXWu/VZEbq/rYIw5kdR+HOm1mxPo\nJCJlsd2H85c9IKWUUuqBOXNABmNM/7tW7b5re/m7lr8AvriffTjSa3chcAHYgu1CbQ2gEdD8fnak\nXE/mTJnTO4QMr3WFaukdglIuz1VmcUktRxKpjzHm2XjLn4vIZmcFpJRSyrO4eR51qNPQURGJ6/Uk\nIoHAQeeFpJRSSrkPR2qkhYHDIrIXW+ItDeyzj/6AMaamE+NTSimVwXnCNGoDnR6FUkopj+XmedSh\n2182pkUgSimllDtypEaqlFJKOY3F6t5VUk2kSiml0lWGb9oVkTqJrI4CDhljTv/3ISmllFLuw5Ea\n6QBsM74YIBoQbNPSFBWRUcaYT50Yn1JKqQzO3XvtOnIf6QmgkjGmgjGmIlAZ2AOUADo4MzillFIZ\nnxNnf0kTjiTSEsaYvbcXjDH7gLLGmJvYaqhKKaVUqjlx9pc04UjT7g0R+RjYgG2w+ieBLPb52q45\nMTallFLK5TmSSF8AegOvY6vB/oNtfjdv4GXnhaaUUsoTuEjFMtUcGZDhAjBIRCzYZn+5vV6nUlNK\nKeXxHLn95V1sPXdz2VdZsM1LmsmJcSmllPIUbl4ldaRptzNQIbnZwZVSSqnUcpVOQ6nlSCI9qElU\nKaWUs7h5HnUokf4tIvOx9dqNur3SGDPTWUEppZTyHJ4w1m4wcAuodtd6TaRKKaU8niO9dl9Ji0CU\nUkopd5RkIhWRb4wxbUXkJLZeugkYYwo5NTKllFIeISNfI33b/rd6WgSilFLKM7l7r90kx9o1xpyz\nP+0BnDbGHDfGHAeuAuPSIjillFIZn7sPWu/QWLvAryLSBSgIjAU+dmpUSimlPIa710gd6Ww0VES+\nA9YDl4Aa8WqrSimllEdLcRo1EXkSmA1MBFYCX4tIMSfHpZRSSrkFR5p2JwOdbs9JKiJPA0uAh50Y\nl1JKKQ/h5i27Dk3sXfWuib03AFWcFpFSSimPkmEn9r59HylwXETi30d6e/YXvY9UKaXUg3OkSufC\n9D5SpZRS6cpVapaplWQijdcz9zxQH3iIeBN7A3OcGJdSSinlFhzpbLQGiABOxVsXSwZOpBaLhb7D\nulO0ZCGiIqP4eOhn3Lxxi4Fje2PNZCUs5CIfvTuByMioBOWKlizEqM8G8O3sJXw/bxkArTo0pU6j\n6uz5Yz+fjZ0NQP2mtfD19+GbWT+k9aG5DIvFwgcf9aJ4qSJERkYxauAkjh05SbuOzen9QTeertic\n8Bs3E5R5rs0zNG5eP265bPlS1CjflBc6PU/9Jk+ze+deJo/+AoBGz9XBz9+XuTMWpelxuZqH6z5K\nmZrl45YDiwezeOQCqr9Ym5joGCJvRrBiyo/cun7nXBcoV5hn+7Qk7GQIAKEnzrN+xs9UbFIFebIs\np81JNs1ZC0DpGg/jnScnO3/alrYH5kJ+37mLPv0HUrxYUQBKlihO55df4v0hHxITE4O/vx+jhg0m\nS5YsCcqNmTCZv/bswYKF/n168XC5ssxd8A0rV6+l4iMV6NPzTQCWrviZsLAwOrZ/Mc2PTTnGkUSK\nMaa2swNxJdXrVsU7Vw66v/AewQWD6DngNS5duMz385ezYeUWuvZ+mSat6vPDghVxZbJlz0qvQV3Z\n+etfCd6rTqPqdH/hPSbM/JBs2bMSEx1Dk5b16PvasLQ+LJfydP0nyZnLm86te1KgUD76Du7B6mUb\n8fX3IeR8WKJlfvx2JT9+uxKASlUqUL9JLQDqNa5F59Y9+XTOGLJlz0ZMdDTNWj/DW698kGbH46r2\nrP2TPWv/BKBA2UKUerIstTrWZ8XkH7h4OowqLZ6iQoNK/L54a4Jyp/adYOnHCX+ElHqyLAsHzKbl\n4JfwypqZ2JgYHq7zKN+PmJ9mx+OqKld6lAljRsYtDxz2Ee1at6RhvTpM/vRzFi9ZSttWLeK2/77z\nD06cPMm8mV9y5OgxBg0fwbyZX/LzmnXMnfkFr/XoyY3wcDJZrfywZCnTpkxIj8NKM27esuvQJd71\nIlJDRNz8crDjChYJZv9fBwE4ffIsgcEBPFq1PFvWbgdgy/rfeKzaIwnKREZE8u5rHxJ6/kLC9ZGR\nAFy8cAnvXN606tiU7+ctJ+qu2qynKVgkP3t3/wPAqRNnyJc/kI1rtvLZ+FnExt4zR8I9Xnu7PV9N\nnQsQdy4vhl0iZy5vXnilBd9+vcTjz/Hdnmhdk22LNnPz6g2y5coOQLac2Qi/csOh8jFR0QDcuHyd\nrDmyUqlJVf5cuYOYqBinxeyuduz6g9o1bd1LatV4im2/7UiwffvvO6hTqyYAxYoW4cqVq1y7dp3M\nmTMD4Ovjw7Vr15i78FvatW4Ztz6jcvdeu44kxwhsoxpFiki0iMSISHRKhUSkioiUsD8vLyKdROSp\nB4w3TRw+cIwq1StitVopWDQ/wQWDCC4QGNeUezHsMn4BPgnKREfHEHEr4p73slqsZPLKhH9eX2Jj\nYihfqQzhN8LpP/JtWndslibH44oOmaNUq1kZq9VK4aIFyF8wiCxZHfuyKFtBOHc6hLDQi4BtUmAv\nr0wE5PUjNiaGRx4rR/j1cAaP6csLr7RI4d08Q2DxfFwNu8KNS9fZMGs1z73Xhk5TupO/TCH2rt99\nz+v9CvjzXP+2tP2oI4Uq2JosLRYL1kxWcvrmIjY2luDSBYm8GUGD7k2p2MSz74g7fPQYb73Tjw5d\nurF1+2+Eh4fHNeX6+foQEhqa4PWhYWH4+OSJW/b18SE0LIyYmBgio6IICQ3FarHy5+6/yZEjO4M+\nHMHX879J02NKS+4+1q4jifQloDiQxf7IbP+bJBGZAAwHZorIOOAzoBQwRERGP1DEaWD7pl3s//sA\nn8wbRZuOzTh+5CSREZFx2+/nV9APC1YwZc4INv78K+1fb8WsTxbSrvPzjBkwlZJlihEQ6OeMQ3B5\nWzf+zp7dhi8XTuDFzi05evgEFhw7r83bNOKn/1sVt7xo3k9Mnz+etSs388obL/DFlK95+bXWDO8/\nntJlS5A3yN9Zh+E2yterGJcwa3dpyJIx3zL77c/4d/9JHn2mcoLXXjpzgV+/3cSPo79h5dQlNOje\nFKuXld0/76T1sJc5uG0/VVo8xa/fbuSxZk+watpP5C0aRE7fXOlxaOmuUMGCvNGlM1PGj2HE0IEM\nGT6KqOg7dQ0HGljiWmHatnqeV7u9Sb06T/PV7Dl0e60zs+fOZ9jA9/nnwAHOnjvvpKNIZ26eSR25\nRvoH8K8xJsVaaDyVjTE1RcQLOAoUNcZEAYjIplTEmea+mjQPmAfAwtXTCTkXRpasWYi4FUFAoC9h\ndzXhJmXt8s2sXb6ZAoXzUaJ0Cw7sPYxX5kzExsYScjaUoPx5CTmX+DXBjG7ahFlxz39cP4cLYZcc\nKvfYE48wdtgnccurlm5g1dINFCySn1JlivPPnoN4eXkRGxvLubMh5MsfyPmzocm8Y8ZXoFwR1s2w\nXV8OKBzIaWPrO3j8ryOUqVE+wWuvXbjKga37ALh87iI3Ll0jp29uzJa9mC17yZPPl8cLB3L+yFky\neWWCWFuZ3AEPce3C1bQ9MBcQmDeAZxrUA6BggQL4+/myZ985bt68RbZsWTl3PoS8AQl/zOUN8Cc0\n7M53yPmQUAL8/ShSuD6NGtTn+ImTHDhwkHJlShMVFY3VaiUwbwBnzp4lKDBvmh6fSpkjNdJYYJ+I\nzBeRObcfKZTxEhEL4A3kAHIBiEhWbDVal1ZcitB/pO022io1KnFg3xF2bN3N0w2fBKBWgyfZvnnX\nfb3nK2++wMypCwDirnfkzed/zzVVT1GydDEGj+kLQLWaj/PP3oMOXRv1z+tH+PXwRK9/dn37ZaZP\n/h8AXpltvxED83nuD5XbvH1yEnkzIu5a5vVL1/AtYPtiDyoezMUzCT+DpWs8zGPNngAgRx5vcuTx\n5tqFK3Hbq7Wuya/f2n4PW70yAZDLLzfXLl5z+rG4oqUrfmb217YOV6GhYYRduEDzpk1YvW49AGvW\nr+epak8kKPNk1aqsXmvbvu8fQ94Af7y9veO2T/tyBm907QLY+lnExsZy9tx5AvwzZuuKxWpJ9cMV\nOFIjXWl/3I95wBHgFvAWsFlEDgNlcIO5TI8cOI7VYmH6dx8TcSuS4X3HEx0dzYAxvWnWtiHnToew\n4od1AAyd0JeR70+hSImCvPleZ4Ly5yUqKpqnGz7JgLdGcfXyNSo8VpaTx07HJc3VP21k2sKxHD9y\nijOnPHMinUPmKFaLhf8t/oSIWxEM7D2Kzt1fpGr1x/AL8GXqrFH8tWsfU8Z8ycjJAxjWbxy3bkXg\nn9c30Zrro48/zIlj/8YlzZU/rWPWoikcPXyC06fOpvXhuRRvn5zcuHw9bnnN9OXUf+NZYqKiuXnt\nJqs+XQJA494tWPXpEg7/foDGvZ+n+ONCJq9MrP1iRVwSzl+mIBfPXIiref6zeQ/tRr7ChVOhXDnv\nWItCRlO7ZnXeGziU9Zs2ExkZycD+71JGSvHBkOEsWvwj+YICafZsYwDe/WAQwwcP5NFHylO2tNC+\nc1esVisD+vWJe7+df/xJ4UIFCcwbAEDjhg1o/2pXihUpQoH8welyjCp5FkdqAakhIrmACGPMLfvz\nMsAxY4xDjfw1pJlzAlNxbkQ61ltTpd5LFWuldwge4c1Z3dM7hAwvS24/p1X//vp0Xqq/7yv0eCnd\nq6UO3UeaGsaYq3c9/w1ARJ4zxvzorP0qpZRyL65yG0tqOS2RAohITiDIvnjGGHMdyJNMEaWUUh7G\nzfOoQxN733O7ioh8lUKZyiKyFVstdCYwC/jL3mP3/nrpKKWUUi4suWnUngdaAPVEJP4V7ixAjRTe\ndxLQ2Rjzz13vWQn4FKiZunCVUkplOG5eJU2uaXcltplfKgNr462PAYak8L7Wu5MogDFml4hkuu8o\nlVJKZViuchtLaiU3jVo4sEVEKmK7H7SoMWaHiFiNMSkNrrlNRJYAPwAh9nVBQCtg438Qt1JKKeUS\nHOls1BzbcH+3gIeBqSKyyxgzI6kCxph3RKQmUBeoal99GhhqjPn1AWNWSimVgTizZVdEJgJPYBtc\nqKcx5vd42woCC7BdstxljOkWb1t2YA8w3BgzO7l9OJJI+wCPAMvsy32BDUCSiRTAGLMJcIvhAJVS\nSqUjJ2VSEakFlDTGVBORMtg6v1aL95LxwHhjzGIR+VREChljTti3DQQcGnrOkSECLxtj4u7ctzf5\n3jvNiVJKKeVa6mK7xIgxZj/gIyK5AexTg9YAlti397idREWkNFCWOxXIZDmSSENFpCOQXUQqicgY\n7lz3VEoppR6IEyd/CSJhvgrhztgGAcBVYKKI/CIio+K9bjzwjqPxO9K02w34CNvA818BvwBdHN2B\nUkoplZw07LVruet5fmAycAxYJiJNAD/gV2PMURFx6E1TTKTGmEvAm/cbrVJKKeUIJw4ReJo7NVCA\nYOCM/XkocNwYcxhARNYC5YDHgGIi8ixQALglIqeMMWuS2kmKiVREXgD6Ab7Ey+bGmEL3dThKKaVU\n2loFDAOm2wcEOn17HHhjTJSIHBGRksaYg9gS6AJjzNjbhUVkKLbJVpJMouBY0+4wbE25x1N3HEop\npVQynFQhNcZsFZGd9iFrY4AeItIJWyfaxUAvYLa949HfwE+p2Y8jifSg/VYWpZRSyq0YY/rftWp3\nvG2HgOrJlB3qyD4cSaRbRWQktntHo+LtYJ0jO1BKKaWS4wnTqNWz/41/E2ssoIlUKaXUA8vwidQY\nUzstAlFKKeWhHBnRwIU5dWJvpZRSKiXuXiN1898BSimlVPpyKJHeHpvQ/jzQeeEopZRS7iXFRCoi\nPYA58VYtFBEd6UgppdR/wmKxpPrhChypkbbHNiH3bQ2Al5wTjlJKKY9jeYCHC3Cks1EmY0xUvOUY\nZwWjlFLK86ThoPVO4UgiXWIfXmkzthpsXeD/nBqVUkopz+EiTbSplWLTrjHmI2yD1p/HNmp+d2PM\nCGcHppRSSrmDJBOpiFS0/60DZAH+AP4EctjXKaWUUh4vuabdDtiS56BEtukQgUoppf4Tbt6ym3Qi\nNcb0tj/90BizPv42EWnu1KiUUkp5DFe5jSW1kkykIlIEKA58LCLvcKejcWZgEvCD06NTSimV8WXg\nXrv5gLZAEWBwvPUxwOdOjEkppZQHybA1UmPMr8CvIrLcGKO1T6WUUioRjoxsdEtE2gOIyDwROSgi\nLZwcl1JKKU/h5iMbOZJIBwMrRaQRkAmoCLzt1KiUUkopN+HIyEY3jDGhItIE+NoYc01Eop0dWKyO\nROh0WTJlSe8QMrxAH+/0DkEpl5dhr5HGk01E3gWeAfqKSEngIeeGpZRSylO4+1i7jjTtdgXyA68Y\nY24CDYH3nBqVUkopz2GxpP7hAlKskRpj9gK94q36ApgHrHVWUEoppTxHhm/aFZGXgQmAr31VDJpE\nlVJKKcCxa6RvA+WBhUATbJN6X3ZmUEoppTyIe1dIHbpGetkYcxbbBN/XjTFfAJ2dHJdSSinlFhyp\nkUaLyLPASREZCuwFCjs1KqWUUh7DE3rtvgycwtbhKBhoD7zlzKCUUkp5kIzaa1dEbifZUPsDoJvT\nI1JKKeVRMnKv3ShsE3jfZrEv3/6byYlxKaWUUm4hudlfHGn2VUoppR5MRr1GKiJ97lquHO/5DGcG\npZRSynNYLJZUP1xBcrXOJnctj433vJgTYlFKKaXcTnLXSO9O9fGXY1FKKaX+C65RsUy15BJpcsnS\nzQ9bKaWUq3CVJtrUup8ORbFJPFdKKaU8VnI10idF5ES85bz2ZQvg79ywlFJKeQw377WbXCKVNItC\nKaWUx3L3pt3k7iM9npaBKKWU8lBunkh10AWllFLqATgy+4tSSinlNO7etKs1UqWUUuoBaI1UKaVU\n+srAvXaVUkopp3P3pl1NpEoppdKXJlKllFIq9Sxu3rSrnY2UUkqpB6A1UqWUUhmWiEwEnsA2RnxP\nY8zv8bYdA04C0fZVLxlj/hWRl4B+QBQw2BizLLl9aCJVSimVvpx0jVREagEljTHVRKQMMBOodtfL\nGhljrsUr4wcMAR4DcgLDAE2kSimlXJcTe+3WBX4AMMbsFxEfEcltjLmSTJl6wBpjzFXgKtA1pZ1o\nIlVKKZW+nJdIg4Cd8ZZD7OviJ9LPRaQI8AvwPlAEyCEiSwAfYKgxZm1yO9FEmgiLxcK7w3pQtGRh\noiKjGDf0U27euMmgsX2wZrISFnKB4e+OJzIyKq5MxSrl+XByf44dtM08d/jAMSZ9NJ3WHZpRp1EN\n/v5jH5+NnQVA/aZP4+fvw8JZi9Pl+FyBxWKh34dvUrxUYSIjoxg7+BPCb9xkyMd9sVqthIVcZNi7\n44iMuHOOs+fIxuBxfciVOydZsmRmxtT5bP9lF206Pke9xjX4a9c+PhkzE4AGzWzneMFMzz3HAMWr\nP0zRamXiln0LB/Ltm58AkK9cYer0bsm8LhMSFrJAlfb1yJPfn5joaH77eg1Xzl5E6lak8ONCyKHT\n/LFoEwBFqpYm20Pe/LNqJ57q95276NN/IMWLFQWgZInidH75Jd4f8iExMTH4+/sxathgsmTJkqDc\nmAmT+WvPHixY6N+nFw+XK8vcBd+wcvVaKj5SgT493wRg6YqfCQsLo2P7F9P82NJKGvbavXtHg4GV\nwAVsNdeW9tf4Ac8DhYH1IlLYGJPkPNyaSBNRo+4TeOfKwRsvvEtwwSB6DujKpQuX+X7+Utav3ELX\n3h1o0qo+PyxYkaDcn7/tYVDPUQnW1W5UnTdeeJeJM4eTLXtWYqJjaNKyPn1fG5KWh+RyatZ7gpy5\nvOnati/5CwXRe2A3Ll64zP/NXcq6lb/Q7Z2OPNuqAYvnL48r06RFPU4c+Zdp42fjn9eXT+aMot0z\nr1O3UQ26tu3L5Nkj4s5x05YN6N1lcDoeoWs4/MseDv+yB4C8pQpQuHIpAKxemSjXuAo3Ll27p0yB\nR0uQJUdWVo1eSM6Ah6jcrjYbpv5A4cdLsWr0Quq805JMWbyIjYmlePWHWT/p+zQ9JldUudKjTBgz\nMm554LCPaNe6JQ3r1WHyp5+zeMlS2rZqEbf9951/cOLkSebN/JIjR48xaPgI5s38kp/XrGPuzC94\nrUdPboSHk8lq5YclS5k2ZUJiu1UpO42tBnpbMHDm9oIxZs7t5yKyHCgPHAO2GmOigMMichUIAM4n\ntRO9/SURBYoEs/+vgwCcPnmWoOC8VKxanl/Wbgdgy/rfqFztUYfeK8pea7144TLeubxp3bEZ389b\nGrfeUxUokp99fxkA/j1hO8eVqpRn87ptAPyybjuPP1kxQZlLF6+QO08uAHLlzsmli7bWmcjISAAu\nhl0iZy5v2nR6jkV6ju9RvukT/L3Udn4fblKVA+v+JCYq+p7X5Q7MQ+jRswBcC7mMt19uLBYL0VEx\nANy8coMs2bNSul4lDqz/k5jomLQ7CDexY9cf1K5ZHYBaNZ5i2287Emzf/vsO6tSqCUCxokW4cuUq\n165dJ3PmzAD4+vhw7do15i78lnatW8atV/dtFdAKQEQqAaft1z4RkYdE5GcRud1UUAvYYy9TR0Ss\n9o5HOYHQ5HbitEQqIqVFpIeIfGR/dBeREs7a33/pyIFjVKleEavVSsGi+QkuGERwgaC4ptyLYZfw\nC/C9p1yREgUZPW0Qn80fQ+UnbYnWYrGQySsT/nl9iY2JoXylsoTfuMn7I3vSumOzND0uV3LYHKNq\njcewWq0Uun2OCwbFNeVevHAJ/wCfBGXWLNtEUHAA3635imnzxzJ1zFcAWK3WuHMcExNLhUplCb8R\nzoBRvWjb6bk0PzZX5FskkOsXrnLzyg1yBeYhTwF/Tuw8mOhrL50KJbhcYSwWC7kCfcgZ8BBZc2XH\nYrFgyWQle56cxMbGElAimMibkTzRqQFSr2Ki7+UpDh89xlvv9KNDl25s3f4b4eHhcU25fr4+hIQm\n/B4ODQvDxydP3LKvjw+hYWHExMQQGRVFSGgoVouVP3f/TY4c2Rn04Qi+nv9Nmh5TmrJYUv9IhjFm\nK7BTRLYCU4AeItJJRJ43xlwGlgPbRGQLtuuni4wx/wKLgG3ACuAtY0yyvxad0rQrIgOBBvYgj2Br\nc84PzBeRBcaYic7Y739l26adlK9Uhk/mjeawOcbxIycpXqpI3PbEepidPHaaWZ8sYN2KzQQXDGLq\nnJG0bdCVHxasYOqckaxZtpmXX2/DrE/m8/o7HenTZQgfjOpFQKAfIefC0vDoXMO2TTuo8FhZps0f\nyyFzlGOHT1JCisRtt9xzKQMaNqvN2dMh9H51MCVKF+WDkb3o3KIn389fxqdfj2bNso106NaGGVPn\n80bfTvTuPIiBo3sTEORHyFnPO8fxlahRniNb9wLwWNun2bFgfZKvPb3nGAElgqn/Xhsungrl8hnb\nuTu4YTf1+rbm+G+Gco2r8PdPv/Joi+qsm/Q91V5pSHafnIRfvLepOKMrVLAgb3TpTMP6dTn17790\n7vYWUdF3avqxSV5ZI95rbC9q2+p5Xu32Js80qMdXs+fQ7bXOTP50Gp9PmcigD0dw9tx5ggLzOutQ\n0o8Thwg0xvS/a9XueNsmA5MTKTMdmO7oPpx1jbQRUP3ui7MiMhLYCLh0IgX4ctLcuOffrP6SkHNh\nZMmahYhbEQQE+hF6/kKC14eeD2Pdis2ArTk4LPQSAYF+rF2+ibXLN1GgcDAlShfF7D2MV2YvYmNj\nCTkbSlD+vB6ZSAG+mBh3eYLv1s7g/LlQsmbNwq1bEbbkd9c5rvBYWbb/f3t3HiZVdeZx/NvduCCy\nd9OyKfKoL0qMGxEUF1AEdRCNRqPGKC7jjBMXYlyBIKMRRVEz6qijweFxQaNGUOOCIKLiCia4Mb6o\ngRZFhAZxidhsPX+c01A0VdVNldVFdf8+z9NP03c7p04d7nvPueeeO/NvAHz84XxKO7SjuLiYaU+/\nzLSnQxmf1qM7/sHHNGtWQnV1NUsWV9KxU3mTD6Tl1oXZE6fTvM32tNqhHX3PORqA5q1bMODSk5h2\n4yMbbf/O5NfW/3vImLP44dvvqZjlVMxyWnZoQ9uuP2N5xRKKSkqgGr7/6ju2b9+qSQbS8g5lHDlw\nAABdu3ShtH073p/7JT/8UMW2227Dl0uW0qGsdKN9OpSVUrlsQ/1esrSSstL2dNvpCI4aeAQVny5k\n3ryP6Ll7D9asWUtxcTHlHcr4YvHiRhlIC33S+lx17TYDOiZZ3olNR01tcXaxnblyzEUA9D54X+bN\n/Vl8D5IAAA4vSURBVITZr82h36ADATh04IG8+crGoxSPOKYfp5z1cwDalbahXfs2GwXIM88/hXtv\nmwhAs63C9UuHjmWbBOSmYpceOzPiumEA9Dl4P+Z98DGzXp1Dv0F9Aeg3qC9vvLxxGX9WsYieexkA\nO3TqwMrvf2Ddug09LmdfcCrjb3sQYP09pfKOZSxd0rSDaPPWLVhdtZp1a9excsV3PDn8XqZc9xBT\nrnuIlV//c5Mg2qZLKX2GDgSgY89uLP90SZgTJtpzyAG8++TrAJQ0C6eQ7dq2TDpwqSn467NTmHB/\n+L9dWbmMZcuXc9wx/8LU6aHVP+3FF+l7QJ+N9jmwd2+mvhDWz/3Q6VBWSosWLdavv/Oe8Zx37jlA\nGANQXV3N4i+XUFa6cUBuNIqLMv/ZAuSqRToCmGpmywj9zhACa0vgvByl+aP5ZN4CioqKuPvRm1lV\ntYqrLxnH2rVrGTn2Yo795VEsXrSEZyeHx4pG33wZY678IzOnv8nocZdy0OF92GqrZowbfcf6wS4/\n3a8nny1YRGU8oU976iXuengcFf9YyBeffZm3z5lPn/gCioqLGP/YLVStWs3oi29g7dq1jLrxEo47\nOZTxM5OmAXD1LZdz7RW3MPnhZxlx3W+548GxlJSUcMOo29cfb69ePVm4YNH6i5fnn5rB3Y/cRMUn\nTbeMazRv04Kqb76vc7u+5x7NG//7PCs+r4SiIgaNOJV1q9fw6j0bRk6X7dqZb7/8ipUxaC5480MG\nXnky33yxnH9WpnvGvfHqf8hBXD5yNC++/AqrV69m5BWXsrvtxvCrruGxSU/QcYdyhgwOPQCXDv89\n14wayd577ckePYzTzjqX4uJiRlz2u/XHe/vvc9hpx66UdygD4OhBAznt7HPp3q0bXTp3ystnlPSK\nquvTgZ8hM9uZDUOPF7l7RX33PcgG5y5jAsDadRptmWvnHzog31loEk68+Yx8Z6HR27pV+5w1/1bM\nnZPx+b7NHnvnvVma0+dI3X0+MD9xmZkd6+5P5DJdERGRhpKPCRl2zkOaIiKypdJgo83WdB+eFBGR\nTRQVFWX8syXI1XOk/5FiVc3zpCIiIsEWMvo2U7nq2r0YmEbCnIYJNNeViIg0GrkKpMcRpmO6yN2r\nEleYWb8cpSkiIgVoS+mizVRO7pG6+/vAYGB1ktW/S7JMRESaqhzNtdtQcjZq192TPgHu7n/LVZoi\nIiINTe8jFRGR/Coq7Dd6KpCKiEheFRX4qN3CvgwQERHJM7VIRUQkv7aQQUOZUiAVEZG8KvTHXxRI\nRUQkvwp8sFFh515ERCTP1CIVEZG80qhdERGRJkwtUhERyS8NNhIREcmcRu2KiIhko8BH7SqQiohI\nfmmwkYiISNOlQCoiIpIFde2KiEheabCRiIhINjTYSEREJHNqkYqIiGSjwFukhZ17ERGRPFMgFRER\nyYK6dkVEJK8K/e0vCqQiIpJfGmwkIiKSuaICH2ykQCoiIvlV4C3Sourq6nznQUREpGAVdntaREQk\nzxRIRUREsqBAKiIikgUFUhERkSwokIqIiGRBgVRERCQLeo60DmZ2C9AHqAYucvdZCesGAGOAtcAz\n7n5Nun3M7ELgJqCtu3/XoB+kQGRY3j8BngBucffbGz7XhauO8t4W+B+gp7v3ylMWC166+pmqTkth\nUYs0DTM7FNjV3Q8AzgZurbXJrcAJQF9goJntkWofMzsdKAcWNVT+C02G5d0CuA14oUEz2wjUo7xv\nBOY0eMYakXrUz03qdEPlTX48CqTpHQ5MBnD3/wPamlkrADPrDix394Xuvg54Jm6fap9J7j6CcOUv\nyWVS3lXA0egCJRMpyzsaDkzKR8YakZT1M02dlgKjQJreDsDShL+XxmXJ1i0BOqbax92/zWE+G4vN\nLm93X+PuKxsof41NuvJGdTZ7ddTPVOcQKTAKpJsn3YSQqdYV9iSS+ZVJeUvmVKb5pfIvUBpslN4i\nEq7QgU7AFynWdY7LVqXZR9LLpLwlc+nKW3JPdbqRUIs0veeBXwCY2b7AopruLndfALQys25m1gwY\nHLdPuY/UKZPylsypruaR6nTjobe/1MHMrgcOAdYBvwH2Ab5290lmdggwNm76F3cfl2wfd3/HzEYA\nRxAeNZgFvO7ulzXsp9nybW55m9l+hEeKugGrgc+B4919eYNnvgDVUd6PAl2BnsDbwN3uPjFvmS1A\nKernk8D8dOcQKSwKpCIiIllQ166IiEgWFEhFRESyoEAqIiKSBQVSERGRLCiQioiIZEETMjRCZtYN\ncOD1hMXNgOHu/vKPnNYCYIC7f1zP7YcCJe4+PoO0TnP3B8xsb+Bsd79gc49Rz3SOBt7I5SM0ZtYJ\n6OHu081sNNDM3UfmML1qYCtga+BId3/czI4E9nP3a9PsNwP4A1BJlmVuZmcAvVIdI9bbme7eJc0x\nRrMZZRXfbvN+JvVNpL4USBuvpe7er+aP+FaJaWbW2d3z9syTu0/IZD8z6wz8O/CAu88BchJEo98C\n5wG5fBa1P7A7MD2HaSSzD3A88Li7Pwc8V5+dsi1zM+sKXAn8NNNjZOhy4F0zm+runzZw2tJEKJA2\nEe4+18yaA6XAUjMbQ3h1U3PgJaBmcojbCZNGLAYWApXuPrKmRePua2KrcoC7n1Zz/Pi6qPuAdkBL\n4FF3H2tm/YDfAz8AjxMe8G9GeCj9hrh7ScxLF8J7Ge+P27QG/svd7wMmAnua2X3AvcAf3P0gM9sN\nuItwm6IZcIW7zzSzCYTp1vYEdgPGu3tNejV57g9cD3wPbAtcCPQCDgYeNLMzCW/k+DPQ3d1PNLOT\nCAGliDDh+DnuvszMvgauBY4kTDx+kru/Z2ZHxTSWA1OA8+PxrwWKzKwmWHcxs8eAHsAMdz+/Vl6H\nxmMXAfsCDxBal/3jsgFAGQktuiStt+bAeMJbXm4A5tZ8j7FnYSLQm1BHhrn7iwnp90so8x2BO4Dt\ngO0JPR3TYplXAQb8yt0/T/gIlwD3uPsqMyuO31kPYBvgTXe/sNbnnQCsBLrH8pzg7jenKqtU9S+m\ndxdwMTAMkRzQPdImwsyGEE78lWZ2ItDZ3Q919/2BXQjTkx0O7B9/TmLzXunUAZjs7v0JQXF4wiu5\negG/Tuxec/e33L1fbDW/AVzn7osI873e7u6HxTzVnDyvAt5z99NrpXsbcGc8znmEk2mN7u5+DDAQ\nGJEkz8OAm2OehxLeJnMn4SLiV+4+N273UQyiXeNxBrj7QcAMwqvGAFrF/B0GPAycY2ZFhBdjnx7T\naB0/+3xgAnB/QnDYBTg5ltUZZtY+SX57AacTZsgaBUx19wMJweuIJNvXtpIQ1KemmFVrmbsfTgg6\nN6U5zp3ATfGzDgH+FKe4A2gRv9fPa+1zJBtav22Bd939EHfvTXgP50+SpNPZ3QcRZl4amVAmycoq\nXf2bGtMXyQm1SBuvsnh/C2BHoAIY7O7VsSV2QML61sDOhBbOK+6+FvinmdWr2y9aAhxsZucRJu7f\nltA6APBU9xvN7BeE7r6j4qJFwGVmdhmhdZosoCTqDfwyJvKembUys9K4bkZcXhGXl8TPVmMiMMbM\n9geecPcnU6TxWvx9AKF1NMXMILSm5idsV9OCqyCc7NsD27v7O3H5Y8CvU6Qx093XAGvMbBnQBlhW\na5vZ7l5lZp8RLoJnxuWfEYN0lqbE368C6V4w3R9oaWZXxb9XEwIZbCir2roSejgAVgBdzex1wkVA\nR0Ir+Lta+zwP4O4rzGwesGtcnqysFpO8/n1D+D66pfk8IllRIG281t8jNbMTCN2WH8V1VYR5Uzea\n1zMGr3UJixKDTqKtkywbRggsfWOwrkxYtyrZQcxsd0JLs198sTGEgS0fufspZrY9UNck6rXv9xYl\nLFuTZN167v5nM5tCaLGOMrO33H04m6rJfxXwlrsPTpGXxPSKCMGuPuVZZ16TbRODSeL2tcti61rp\n16WmhyrZsRJVEeYzTvyOiRcXSb/rWk4GfgYcHG8VzK4jP7XzlKys0tU/kZxS124T4O5/Ab4i3J+D\n0JI5vqY7zsxGmdmuwIdAHzMrMrPtgEEJh/mG0KqA0CKprRyYG09iQwj3z7ZJlSczawk8BAx198SW\nVznwQfz3qcA6M9uGEBC2SnKoN2ryaWb7ELona7fkUuXhPwkjiB8BLiK0OEmT1ixgfzPbIe5/opkd\nmyaJyph/i38fn7AuVRrZ+AZoZ2bbmVkJoUu0tnTpHhZ/HwS8myadmYSuf8ys1Mz+WI+8LWRD/Skn\n9FKsiZO670LyutI/ptE2buNpjp+u/u0ELKhHHkUyokDadPwGuNLMuhMG/bwKvBa718qBfxAG1iwE\nZgMPErrpaq7+rweeN7NnSH5SuhcYambTCd3ED8afdPnpDNxkZjPiz6GEwU5Xm9lUQmv0BUIX7AdA\neVye6ALgX83sRcL90lRdp8l8BEw1sxeA/wZGx+VTgKfM7MDEjeM93IuAv5rZy8DZhECeVGxlDwMm\nx5ZvFRvK8xXgTDO7ZjPym5a7f0W49zobmAT8PclmbwGHmNm9SdZ1MbOngXGE+6SpXAj83MxeIdSZ\n+ow8fo4NF2aPEm4tvAScENO7lXDvNNFXZjaZMBjuKndfkeb46erfAOo5OlkkE3r7i6xnZq2B44D7\n4pX9k8BD7v5QnrNWsGKL9V13n29mxwP/FgfQbFFsM58HzuD4OxIuUPZy9zq7f+Oo3Znu/qcs090a\neIfw7GxFNscSSUUtUkn0LWHE49tm9iphsMuj+c1SwSsBHo+tr4sJj4E0OfEZzrGkHw2cC2OBcQqi\nkktqkYqIiGRBLVIREZEsKJCKiIhkQYFUREQkCwqkIiIiWVAgFRERyYICqYiISBb+H5v3qnic3Goj\nAAAAAElFTkSuQmCC\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f63aa4b0390>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Cross-validated performance heatmap\n",
+    "model = 'full'\n",
+    "\n",
+    "cv_score_mat = pd.pivot_table(cv_results_df_dict[model],\n",
+    "                              values='mean_test_score', \n",
+    "                              index='classify__l1_ratio',\n",
+    "                              columns='classify__alpha')\n",
+    "ax = sns.heatmap(cv_score_mat, annot=True, fmt='.1%')\n",
+    "ax.set_xlabel('Regularization strength multiplier (alpha)')\n",
+    "ax.set_ylabel('Elastic net mixing parameter (l1_ratio)');"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Use Optimal Hyperparameters to Output ROC Curve"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "y_pred_dict = {\n",
+    "    model: {\n",
+    "        'train': pipeline.decision_function(X_partitions[model]['train']),\n",
+    "        'test':  pipeline.decision_function(X_partitions[model]['test'])\n",
+    "    } for model, pipeline in cv_pipelines.items()\n",
+    "}\n",
+    "\n",
+    "def get_threshold_metrics(y_true, y_pred):\n",
+    "    roc_columns = ['fpr', 'tpr', 'threshold']\n",
+    "    roc_items = zip(roc_columns, roc_curve(y_true, y_pred))\n",
+    "    roc_df = pd.DataFrame.from_items(roc_items)\n",
+    "    auroc = roc_auc_score(y_true, y_pred)\n",
+    "    return {'auroc': auroc, 'roc_df': roc_df}\n",
+    "\n",
+    "metrics_dict = {    \n",
+    "    model: {\n",
+    "        'train': get_threshold_metrics(y_train, y_pred_dict[model]['train']),\n",
+    "        'test':  get_threshold_metrics(y_test, y_pred_dict[model]['test'])\n",
+    "    } for model in y_pred_dict.keys()\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div class=\"vega-embed\" id=\"3f00e7a1-5d6c-4c92-9ae6-e57da7073f18\"></div>\n",
+       "\n",
+       "<style>\n",
+       ".vega-embed svg, .vega-embed canvas {\n",
+       "  border: 1px dotted gray;\n",
+       "}\n",
+       "\n",
+       ".vega-embed .vega-actions a {\n",
+       "  margin-right: 6px;\n",
+       "}\n",
+       "</style>\n"
+      ]
+     },
+     "metadata": {
+      "jupyter-vega": "#3f00e7a1-5d6c-4c92-9ae6-e57da7073f18"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/javascript": [
+       "var spec = {\"marks\": [{\"properties\": {\"update\": {\"y\": {\"value\": 0}, \"stroke\": {\"value\": \"red\"}, \"y2\": {\"field\": {\"group\": \"height\"}}, \"x\": {\"signal\": \"index_fpr\", \"scale\": \"xscale\"}}}, \"type\": \"rule\"}, {\"marks\": [{\"properties\": {\"update\": {\"strokeOpacity\": {\"value\": 0.6}, \"stroke\": {\"field\": \"feature_set\", \"scale\": \"colorscale\"}, \"strokeDash\": {\"field\": \"partition\", \"scale\": \"dashscale\"}, \"strokeWidth\": {\"value\": 4}, \"y\": {\"field\": \"true_positive_rate\", \"scale\": \"yscale\"}, \"x\": {\"field\": \"false_positive_rate\", \"scale\": \"xscale\"}}}, \"type\": \"line\"}], \"type\": \"group\", \"from\": {\"data\": \"roc\", \"transform\": [{\"groupby\": \"legend\", \"type\": \"facet\"}]}}, {\"marks\": [{\"marks\": [{\"properties\": {\"update\": {\"fontSize\": {\"value\": 11}, \"y\": {\"value\": 5}, \"x\": {\"value\": 0}, \"fontWeight\": {\"value\": \"bold\"}, \"fill\": {\"value\": \"black\"}, \"text\": {\"template\": \"{{parent.legend}}\"}}}, \"type\": \"text\"}, {\"properties\": {\"update\": {\"y\": {\"value\": 15}, \"fill\": {\"value\": \"black\"}, \"fontSize\": {\"value\": 11}, \"x\": {\"value\": 0}, \"text\": {\"template\": \"TPR: {{parent.agg_true_positive_rate|number: '.3p'}}, FPR: {{index_fpr|number: '.3p'}}, AUC {{parent.lookup.auc|number: '.3p'}}\"}}}, \"type\": \"text\"}], \"properties\": {\"update\": {\"y\": {\"offset\": 5, \"field\": \"lookup.legend_index\", \"scale\": \"legendrow\"}, \"x\": {\"value\": 4}}}, \"type\": \"group\"}], \"properties\": {\"update\": {\"width\": {\"value\": 200}, \"height\": {\"value\": 140}, \"strokeWidth\": {\"value\": 0.5}, \"y\": {\"value\": 100}, \"x\": {\"signal\": \"index_fpr\", \"offset\": 10, \"scale\": \"xscale\"}, \"stroke\": {\"value\": \"black\"}}}, \"type\": \"group\", \"from\": {\"data\": \"roc_index\", \"transform\": [{\"type\": \"lookup\", \"onKey\": \"legend\", \"on\": \"legend_auc\", \"default\": -1, \"keys\": [\"legend\"], \"as\": [\"lookup\"]}, {\"groupby\": \"legend\", \"type\": \"facet\"}]}}], \"scales\": [{\"round\": \"true\", \"type\": \"linear\", \"name\": \"xscale\", \"range\": \"width\", \"domain\": {\"field\": \"false_positive_rate\", \"data\": \"roc\"}, \"zero\": \"true\"}, {\"round\": \"true\", \"type\": \"linear\", \"nice\": \"true\", \"name\": \"yscale\", \"range\": \"height\", \"domain\": {\"field\": \"true_positive_rate\", \"data\": \"roc\"}, \"zero\": \"true\"}, {\"type\": \"ordinal\", \"range\": [\"#FF0000\", \"#5254a3\", \"#fd8d3c\"], \"domain\": {\"field\": \"feature_set\", \"data\": \"roc\"}, \"name\": \"colorscale\"}, {\"type\": \"ordinal\", \"range\": {\"field\": \"strokeDash\", \"data\": \"dash_data\"}, \"domain\": {\"field\": \"partition\", \"data\": \"roc\"}, \"name\": \"dashscale\"}, {\"type\": \"ordinal\", \"range\": {\"field\": \"strokeDash\", \"data\": \"dash_legend\"}, \"domain\": {\"field\": \"partition\", \"data\": \"roc\"}, \"name\": \"dashlegendscale\"}, {\"type\": \"linear\", \"rangeMax\": 110, \"domain\": {\"field\": \"legend_index\", \"data\": \"legend_auc\"}, \"name\": \"legendrow\", \"rangeMin\": 0}], \"data\": [{\"url\": \"jupyter_data/roc_output.csv\", \"name\": \"roc\", \"transform\": [{\"groupby\": [\"partition\", \"feature_set\", \"false_positive_rate\"], \"summarize\": [{\"ops\": [\"min\"], \"field\": \"true_positive_rate\", \"as\": [\"true_positive_rate\"]}], \"type\": \"aggregate\"}, {\"field\": \"legend\", \"expr\": \"datum.partition + ' (' + datum.feature_set + ')'\", \"type\": \"formula\"}], \"format\": {\"type\": \"csv\"}}, {\"source\": \"roc\", \"name\": \"roc_index_lookup\", \"transform\": [{\"test\": \"datum.false_positive_rate >= index_fpr\", \"type\": \"filter\"}, {\"groupby\": [\"legend\"], \"summarize\": [{\"ops\": [\"min\"], \"field\": \"false_positive_rate\", \"as\": [\"min_false_positive_rate\"]}], \"type\": \"aggregate\"}]}, {\"source\": \"roc\", \"name\": \"roc_index\", \"transform\": [{\"type\": \"lookup\", \"onKey\": \"legend\", \"on\": \"roc_index_lookup\", \"default\": -1, \"keys\": [\"legend\"], \"as\": [\"lookup\"]}, {\"test\": \"datum.false_positive_rate == datum.lookup.min_false_positive_rate\", \"type\": \"filter\"}, {\"groupby\": [\"legend\", \"partition\", \"feature_set\"], \"summarize\": [{\"ops\": [\"min\"], \"field\": \"true_positive_rate\", \"as\": [\"agg_true_positive_rate\"]}], \"type\": \"aggregate\"}]}, {\"name\": \"dash_data\", \"values\": [{\"strokeDash\": [0, 0]}, {\"strokeDash\": [5, 7]}]}, {\"name\": \"dash_legend\", \"values\": [{\"strokeDash\": [0, 0]}, {\"strokeDash\": [3, 3]}]}, {\"url\": \"jupyter_data/auc.csv\", \"name\": \"legend_auc\", \"transform\": [{\"field\": \"legend\", \"expr\": \"datum.partition + ' (' + datum.feature_set + ')'\", \"type\": \"formula\"}], \"format\": {\"type\": \"csv\"}}], \"padding\": {\"left\": 70, \"right\": 190, \"top\": 10, \"bottom\": 60}, \"width\": 600, \"legends\": [{\"title\": \"feature set\", \"properties\": {\"legend\": {\"y\": {\"value\": 250}, \"x\": {\"value\": 440}}, \"title\": {\"fontSize\": {\"value\": 16}}, \"symbols\": {\"stroke\": {\"field\": \"data\", \"scale\": \"colorscale\"}, \"shape\": {\"value\": \"M-0.5,-0.0L0.5,0\"}, \"strokeWidth\": {\"value\": 3}, \"size\": {\"value\": 250}}, \"labels\": {\"fontSize\": {\"value\": 15}}}, \"fill\": \"colorscale\"}, {\"stroke\": \"dashlegendscale\", \"title\": \"partition\", \"properties\": {\"legend\": {\"y\": {\"value\": 320}, \"x\": {\"value\": 440}}, \"title\": {\"fontSize\": {\"value\": 16}}, \"symbols\": {\"stroke\": {\"value\": \"black\"}, \"strokeDash\": {\"field\": \"data\", \"scale\": \"dashlegendscale\"}, \"shape\": {\"value\": \"M-0.5,-0.0L0.5,0\"}, \"strokeWidth\": {\"value\": 3}, \"size\": {\"value\": 250}}, \"labels\": {\"fontSize\": {\"value\": 15}, \"text\": {\"field\": \"data\"}}}}], \"signals\": [{\"name\": \"index_fpr\", \"streams\": [{\"expr\": \"clamp(eventX(), 0, eventGroup('root').width)\", \"type\": \"mousemove\", \"scale\": {\"invert\": true, \"name\": \"xscale\"}}], \"init\": 0.4}], \"height\": 400, \"axes\": [{\"title\": \"False positive rate\", \"type\": \"x\", \"scale\": \"xscale\", \"format\": \"%\"}, {\"title\": \"True positive rate\", \"type\": \"y\", \"scale\": \"yscale\", \"format\": \"%\"}]};\n",
+       "var selector = \"#3f00e7a1-5d6c-4c92-9ae6-e57da7073f18\";\n",
+       "var type = \"vega\";\n",
+       "\n",
+       "var output_area = this;\n",
+       "require(['nbextensions/jupyter-vega/index'], function(vega) {\n",
+       "  vega.render(selector, spec, type, output_area);\n",
+       "}, function (err) {\n",
+       "  if (err.requireType !== 'scripterror') {\n",
+       "    throw(err);\n",
+       "  }\n",
+       "});\n"
+      ]
+     },
+     "metadata": {
+      "jupyter-vega": "#3f00e7a1-5d6c-4c92-9ae6-e57da7073f18"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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"
+     },
+     "metadata": {
+      "jupyter-vega": "#3f00e7a1-5d6c-4c92-9ae6-e57da7073f18"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# TODO: do not save intermediate files?\n",
+    "# Assemble the data for ROC curves\n",
+    "model_order = ['full', 'expressions', 'covariates']\n",
+    "\n",
+    "auc_output = pd.DataFrame()\n",
+    "roc_output = pd.DataFrame()\n",
+    "\n",
+    "for model in model_order:\n",
+    "    metrics_partition = metrics_dict[model]\n",
+    "    for partition, metrics in metrics_partition.items():\n",
+    "        auc_output = auc_output.append(pd.DataFrame({\n",
+    "            'partition': [partition],\n",
+    "            'feature_set': [model],\n",
+    "            'auc': metrics['auroc']\n",
+    "        }))\n",
+    "        roc_df = metrics['roc_df']\n",
+    "        roc_output = roc_output.append(pd.DataFrame({\n",
+    "            'false_positive_rate': roc_df.fpr,\n",
+    "            'true_positive_rate': roc_df.tpr,\n",
+    "            'partition': partition,\n",
+    "            'feature_set': model\n",
+    "        }))\n",
+    "auc_output['legend_index'] = range(len(auc_output.index))\n",
+    "\n",
+    "roc_output.to_csv('jupyter_data/roc_output.csv', index = False)\n",
+    "auc_output.to_csv('jupyter_data/auc.csv', index = False)\n",
+    "\n",
+    "with open('jupyter_data/roc_vega_spec.json', 'r') as fp:\n",
+    "    vega_spec = json.load(fp)\n",
+    "    \n",
+    "vega.Vega(vega_spec)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## What are the classifier coefficients?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "final_pipelines = {\n",
+    "    model: pipeline.best_estimator_\n",
+    "    for model, pipeline in cv_pipelines.items()\n",
+    "}\n",
+    "final_classifiers = {\n",
+    "    model: pipeline.named_steps['classify']\n",
+    "    for model, pipeline in final_pipelines.items()\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def get_coefficients(classifier, X_mat):\n",
+    "    coef_df = pd.DataFrame.from_items([\n",
+    "        ('feature', X_mat.columns),\n",
+    "        ('weight', classifier.coef_[0]),\n",
+    "    ])\n",
+    "\n",
+    "    coef_df['abs'] = coef_df['weight'].abs()\n",
+    "    coef_df = coef_df.sort_values('abs', ascending=False)\n",
+    "    \n",
+    "    return coef_df\n",
+    "\n",
+    "coef_df_dict = {\n",
+    "    model: get_coefficients(classifier, X_partitions[model]['train'])\n",
+    "    for model, classifier in final_classifiers.items()\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.0% zero coefficients; 63 negative and 70 positive coefficients\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>feature</th>\n",
+       "      <th>weight</th>\n",
+       "      <th>abs</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>2</td>\n",
+       "      <td>-0.339458</td>\n",
+       "      <td>0.339458</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32</th>\n",
+       "      <td>n_mutations_log1p</td>\n",
+       "      <td>0.324050</td>\n",
+       "      <td>0.324050</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>44</th>\n",
+       "      <td>11</td>\n",
+       "      <td>-0.277003</td>\n",
+       "      <td>0.277003</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>57</th>\n",
+       "      <td>24</td>\n",
+       "      <td>0.257535</td>\n",
+       "      <td>0.257535</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>71</th>\n",
+       "      <td>38</td>\n",
+       "      <td>0.246583</td>\n",
+       "      <td>0.246583</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>62</th>\n",
+       "      <td>29</td>\n",
+       "      <td>0.235441</td>\n",
+       "      <td>0.235441</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>33</th>\n",
+       "      <td>0</td>\n",
+       "      <td>-0.206559</td>\n",
+       "      <td>0.206559</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>67</th>\n",
+       "      <td>34</td>\n",
+       "      <td>-0.206115</td>\n",
+       "      <td>0.206115</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>64</th>\n",
+       "      <td>31</td>\n",
+       "      <td>-0.195329</td>\n",
+       "      <td>0.195329</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>acronym_THCA</td>\n",
+       "      <td>-0.193927</td>\n",
+       "      <td>0.193927</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "              feature    weight       abs\n",
+       "35                  2 -0.339458  0.339458\n",
+       "32  n_mutations_log1p  0.324050  0.324050\n",
+       "44                 11 -0.277003  0.277003\n",
+       "57                 24  0.257535  0.257535\n",
+       "71                 38  0.246583  0.246583\n",
+       "62                 29  0.235441  0.235441\n",
+       "33                  0 -0.206559  0.206559\n",
+       "67                 34 -0.206115  0.206115\n",
+       "64                 31 -0.195329  0.195329\n",
+       "27       acronym_THCA -0.193927  0.193927"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model = 'full'\n",
+    "\n",
+    "print('{:.1%} zero coefficients; {:,} negative and {:,} positive coefficients'.format(\n",
+    "    (coef_df_dict[model].weight == 0).mean(),\n",
+    "    (coef_df_dict[model].weight < 0).sum(),\n",
+    "    (coef_df_dict[model].weight > 0).sum()\n",
+    "))\n",
+    "coef_df_dict[model].head(10)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Investigate the predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {
+    "collapsed": true,
+    "scrolled": false
+   },
+   "outputs": [],
+   "source": [
+    "model = 'full'\n",
+    "\n",
+    "X_all = X_partitions[model]['train'].append(X_partitions[model]['test'])\n",
+    "X_test_index = X_partitions[model]['test'].index\n",
+    "y_all = y_train.append(y_test)\n",
+    "\n",
+    "predict_df = pd.DataFrame.from_items([\n",
+    "    ('sample_id', X_all.index),\n",
+    "    ('testing', X_all.index.isin(X_test_index).astype(int)),\n",
+    "    ('status', y_all),\n",
+    "    ('decision_function', final_pipelines[model].decision_function(X_all)),\n",
+    "    ('probability', final_pipelines[model].predict_proba(X_all)[:, 1])\n",
+    "])\n",
+    "\n",
+    "predict_df['probability_str'] = predict_df['probability'].apply('{:.1%}'.format)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>sample_id</th>\n",
+       "      <th>testing</th>\n",
+       "      <th>status</th>\n",
+       "      <th>decision_function</th>\n",
+       "      <th>probability</th>\n",
+       "      <th>probability_str</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>sample_id</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>TCGA-L5-A4OH-01</th>\n",
+       "      <td>TCGA-L5-A4OH-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3.761191</td>\n",
+       "      <td>0.977273</td>\n",
+       "      <td>97.7%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-EI-6513-01</th>\n",
+       "      <td>TCGA-EI-6513-01</td>\n",
+       "      <td>1</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3.537008</td>\n",
+       "      <td>0.971723</td>\n",
+       "      <td>97.2%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-22-4591-01</th>\n",
+       "      <td>TCGA-22-4591-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3.196160</td>\n",
+       "      <td>0.960690</td>\n",
+       "      <td>96.1%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-L5-A8NR-01</th>\n",
+       "      <td>TCGA-L5-A8NR-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.962345</td>\n",
+       "      <td>0.950844</td>\n",
+       "      <td>95.1%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-RE-A7BO-01</th>\n",
+       "      <td>TCGA-RE-A7BO-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.664928</td>\n",
+       "      <td>0.934925</td>\n",
+       "      <td>93.5%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-46-3765-01</th>\n",
+       "      <td>TCGA-46-3765-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.654768</td>\n",
+       "      <td>0.934304</td>\n",
+       "      <td>93.4%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-BA-5149-01</th>\n",
+       "      <td>TCGA-BA-5149-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.602380</td>\n",
+       "      <td>0.931015</td>\n",
+       "      <td>93.1%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-24-2298-01</th>\n",
+       "      <td>TCGA-24-2298-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.561030</td>\n",
+       "      <td>0.928311</td>\n",
+       "      <td>92.8%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-L5-A4OS-01</th>\n",
+       "      <td>TCGA-L5-A4OS-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.534246</td>\n",
+       "      <td>0.926508</td>\n",
+       "      <td>92.7%</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>TCGA-21-1081-01</th>\n",
+       "      <td>TCGA-21-1081-01</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2.529144</td>\n",
+       "      <td>0.926160</td>\n",
+       "      <td>92.6%</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                       sample_id  testing  status  decision_function  \\\n",
+       "sample_id                                                              \n",
+       "TCGA-L5-A4OH-01  TCGA-L5-A4OH-01        0       0           3.761191   \n",
+       "TCGA-EI-6513-01  TCGA-EI-6513-01        1       0           3.537008   \n",
+       "TCGA-22-4591-01  TCGA-22-4591-01        0       0           3.196160   \n",
+       "TCGA-L5-A8NR-01  TCGA-L5-A8NR-01        0       0           2.962345   \n",
+       "TCGA-RE-A7BO-01  TCGA-RE-A7BO-01        0       0           2.664928   \n",
+       "TCGA-46-3765-01  TCGA-46-3765-01        0       0           2.654768   \n",
+       "TCGA-BA-5149-01  TCGA-BA-5149-01        0       0           2.602380   \n",
+       "TCGA-24-2298-01  TCGA-24-2298-01        0       0           2.561030   \n",
+       "TCGA-L5-A4OS-01  TCGA-L5-A4OS-01        0       0           2.534246   \n",
+       "TCGA-21-1081-01  TCGA-21-1081-01        0       0           2.529144   \n",
+       "\n",
+       "                 probability probability_str  \n",
+       "sample_id                                     \n",
+       "TCGA-L5-A4OH-01     0.977273           97.7%  \n",
+       "TCGA-EI-6513-01     0.971723           97.2%  \n",
+       "TCGA-22-4591-01     0.960690           96.1%  \n",
+       "TCGA-L5-A8NR-01     0.950844           95.1%  \n",
+       "TCGA-RE-A7BO-01     0.934925           93.5%  \n",
+       "TCGA-46-3765-01     0.934304           93.4%  \n",
+       "TCGA-BA-5149-01     0.931015           93.1%  \n",
+       "TCGA-24-2298-01     0.928311           92.8%  \n",
+       "TCGA-L5-A4OS-01     0.926508           92.7%  \n",
+       "TCGA-21-1081-01     0.926160           92.6%  "
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Top predictions amongst negatives (potential hidden responders)\n",
+    "predict_df.sort_values('decision_function', ascending=False).query(\"status == 0\").head(10)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeEAAAFYCAYAAABkj0SzAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQthEkrAQQghhk/8HmL5fDRFc0CUAAAAASUVORK5CYII=\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f6352ca92b0>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Ignore numpy warning caused by seaborn\n",
+    "warnings.filterwarnings('ignore', 'using a non-integer number instead of an integer')\n",
+    "\n",
+    "ax = sns.distplot(predict_df.query(\"status == 0\").decision_function, hist=False, label='Negatives')\n",
+    "ax = sns.distplot(predict_df.query(\"status == 1\").decision_function, hist=False, label='Positives')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAeEAAAFYCAYAAABkj0SzAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAElFTkSuQmCC\n",
+      "text/plain": [
+       "<matplotlib.figure.Figure at 0x7f62feeb5c18>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax = sns.distplot(predict_df.query(\"status == 0\").probability, hist=False, label='Negatives')\n",
+    "ax = sns.distplot(predict_df.query(\"status == 1\").probability, hist=False, label='Positives')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/2.TCGA-MLexample-covariates.py b/2.TCGA-MLexample-covariates.py
new file mode 100644
index 0000000..fdc4ac9
--- /dev/null
+++ b/2.TCGA-MLexample-covariates.py
@@ -0,0 +1,355 @@
+
+# coding: utf-8
+
+# # Create a logistic regression model to predict TP53 mutation from gene expression data in TCGA
+
+# In[1]:
+
+import os
+import urllib
+import random
+import warnings
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+import vega
+import json
+from sklearn import preprocessing
+from sklearn.linear_model import SGDClassifier
+from sklearn.model_selection import train_test_split, GridSearchCV, ShuffleSplit
+from sklearn.metrics import roc_auc_score, roc_curve
+from sklearn.pipeline import Pipeline
+from sklearn.preprocessing import StandardScaler
+from sklearn.feature_selection import SelectKBest
+from sklearn.decomposition import PCA
+
+
+# In[2]:
+
+get_ipython().magic('matplotlib inline')
+plt.style.use('seaborn-notebook')
+
+
+# ## Specify model configuration
+
+# In[3]:
+
+# We're going to be building a 'TP53' classifier 
+GENE = '7157' # TP53
+
+
+# *Here is some [documentation](http://scikit-learn.org/stable/modules/generated/sklearn.linear_model.SGDClassifier.html) regarding the classifier and hyperparameters*
+# 
+# *Here is some [information](https://ghr.nlm.nih.gov/gene/TP53) about TP53*
+
+# ## Load Data
+
+# In[4]:
+
+get_ipython().run_cell_magic('time', '', "path = os.path.join('download', 'expression-matrix.tsv.bz2')\nexpression = pd.read_table(path, index_col=0)")
+
+
+# In[5]:
+
+get_ipython().run_cell_magic('time', '', "path = os.path.join('download', 'mutation-matrix.tsv.bz2')\nY = pd.read_table(path, index_col=0)")
+
+
+# In[6]:
+
+get_ipython().run_cell_magic('time', '', "path = os.path.join('download', 'covariates.tsv')\ncovariates = pd.read_table(path, index_col=0)\n\n# Select acronym_x and n_mutations_log1p covariates only\nselected_cols = [col for col in covariates.columns if 'acronym_' in col]\nselected_cols.append('n_mutations_log1p')\ncovariates = covariates[selected_cols]")
+
+
+# In[7]:
+
+y = Y[GENE]
+
+
+# In[8]:
+
+# The Series now holds TP53 Mutation Status for each Sample
+y.head(6)
+
+
+# In[9]:
+
+# Here are the percentage of tumors with NF1
+y.value_counts(True)
+
+
+# ## Pre-process data set
+# TODO: currently running PCA on both train and test partitions
+
+# In[10]:
+
+# Pre-process expression data for use later
+n_components = 100
+scaled_expression = StandardScaler().fit_transform(expression)
+pca = PCA(n_components).fit(scaled_expression)
+explained_variance = pca.explained_variance_
+expression_pca = pca.transform(scaled_expression)
+expression_pca = pd.DataFrame(expression_pca)
+expression_pca = expression_pca.set_index(expression.index.values)
+
+
+# In[11]:
+
+print('fraction of variance explained: ' + str(pca.explained_variance_ratio_.sum()))
+
+
+# In[12]:
+
+# Create full feature matrix (expression + covariates)
+X = pd.concat([covariates,expression_pca],axis=1)
+print('Gene expression matrix shape: {0[0]}, {0[1]}'.format(expression.shape))
+print('Full feature matrix shape: {0[0]}, {0[1]}'.format(X.shape))
+
+
+# ## Set aside 10% of the data for testing
+
+# In[13]:
+
+# Typically, this can only be done where the number of mutations is large enough
+train_index, test_index = next(ShuffleSplit(n_splits=2, test_size=0.1, random_state=0).split(y))
+
+X_partitions = {
+    'full': {
+        'train': X.ix[train_index], 
+        'test': X.ix[test_index]
+        },
+    'expressions': {
+        'train': expression_pca.ix[train_index], 
+        'test': expression_pca.ix[test_index]
+        },
+    'covariates': {
+        'train': covariates.ix[train_index], 
+        'test': covariates.ix[test_index]
+        }    
+    } 
+
+y_train = y[train_index]
+y_test = y[test_index]
+
+'Size: {:,} features, {:,} training samples, {:,} testing samples'.format(
+    len(X_partitions['full']['train'].columns), 
+    len(X_partitions['full']['train']), 
+    len(X_partitions['full']['test']))
+
+
+# ## Define pipeline and Cross validation model fitting
+
+# In[14]:
+
+# Parameter Sweep for Hyperparameters
+param_grid = {
+    'classify__loss': ['log'],
+    'classify__penalty': ['elasticnet'],
+    'classify__alpha': [10 ** x for x in range(-3, 1)],
+    'classify__l1_ratio': [0, 0.2, 0.8, 1],
+}
+
+pipeline = Pipeline(steps=[
+    ('standardize', StandardScaler()),
+    ('classify', SGDClassifier(random_state=0, class_weight='balanced'))
+])
+
+models = ['full', 'expressions', 'covariates']
+
+cv_pipelines = {mod: GridSearchCV(estimator=pipeline, 
+                             param_grid=param_grid, 
+                             n_jobs=1, 
+                             scoring='roc_auc') for mod in models}
+
+
+# In[15]:
+
+get_ipython().run_cell_magic('time', '', "for model, pipeline in cv_pipelines.items():\n    print('Fitting CV for model: {0}'.format(model))\n    pipeline.fit(X=X_partitions.get(model).get('train'), y=y_train)\n# cv_pipeline_full.fit(X=X_train_full, y=y_train)")
+
+
+# In[16]:
+
+# Best Params
+for model, pipeline in cv_pipelines.items():
+    print('{0}: {1:.3%}'.format(model, pipeline.best_score_))
+
+    # Best Params
+    print(pipeline.best_params_)
+
+
+# ## Visualize hyperparameters performance
+
+# In[17]:
+
+cv_results_df_dict = {model: 
+    pd.concat([
+        pd.DataFrame(pipeline.cv_results_),
+        pd.DataFrame.from_records(pipeline.cv_results_['params']),
+    ], axis='columns') for model, pipeline in cv_pipelines.items()}
+
+model = 'full'
+
+cv_results_df_dict[model].head(2)
+
+
+# In[18]:
+
+# Cross-validated performance heatmap
+model = 'full'
+
+cv_score_mat = pd.pivot_table(cv_results_df_dict[model],
+                              values='mean_test_score', 
+                              index='classify__l1_ratio',
+                              columns='classify__alpha')
+ax = sns.heatmap(cv_score_mat, annot=True, fmt='.1%')
+ax.set_xlabel('Regularization strength multiplier (alpha)')
+ax.set_ylabel('Elastic net mixing parameter (l1_ratio)');
+
+
+# ## Use Optimal Hyperparameters to Output ROC Curve
+
+# In[19]:
+
+y_pred_dict = {
+    model: {
+        'train': pipeline.decision_function(X_partitions[model]['train']),
+        'test':  pipeline.decision_function(X_partitions[model]['test'])
+    } for model, pipeline in cv_pipelines.items()
+}
+
+def get_threshold_metrics(y_true, y_pred):
+    roc_columns = ['fpr', 'tpr', 'threshold']
+    roc_items = zip(roc_columns, roc_curve(y_true, y_pred))
+    roc_df = pd.DataFrame.from_items(roc_items)
+    auroc = roc_auc_score(y_true, y_pred)
+    return {'auroc': auroc, 'roc_df': roc_df}
+
+metrics_dict = {    
+    model: {
+        'train': get_threshold_metrics(y_train, y_pred_dict[model]['train']),
+        'test':  get_threshold_metrics(y_test, y_pred_dict[model]['test'])
+    } for model in y_pred_dict.keys()
+}
+
+
+# In[20]:
+
+# TODO: do not save intermediate files?
+# Assemble the data for ROC curves
+model_order = ['full', 'expressions', 'covariates']
+
+auc_output = pd.DataFrame()
+roc_output = pd.DataFrame()
+
+for model in model_order:
+    metrics_partition = metrics_dict[model]
+    for partition, metrics in metrics_partition.items():
+        auc_output = auc_output.append(pd.DataFrame({
+            'partition': [partition],
+            'feature_set': [model],
+            'auc': metrics['auroc']
+        }))
+        roc_df = metrics['roc_df']
+        roc_output = roc_output.append(pd.DataFrame({
+            'false_positive_rate': roc_df.fpr,
+            'true_positive_rate': roc_df.tpr,
+            'partition': partition,
+            'feature_set': model
+        }))
+auc_output['legend_index'] = range(len(auc_output.index))
+
+roc_output.to_csv('jupyter_data/roc_output.csv', index = False)
+auc_output.to_csv('jupyter_data/auc.csv', index = False)
+
+with open('jupyter_data/roc_vega_spec.json', 'r') as fp:
+    vega_spec = json.load(fp)
+    
+vega.Vega(vega_spec)
+
+
+# ## What are the classifier coefficients?
+
+# In[21]:
+
+final_pipelines = {
+    model: pipeline.best_estimator_
+    for model, pipeline in cv_pipelines.items()
+}
+final_classifiers = {
+    model: pipeline.named_steps['classify']
+    for model, pipeline in final_pipelines.items()
+}
+
+
+# In[22]:
+
+def get_coefficients(classifier, X_mat):
+    coef_df = pd.DataFrame.from_items([
+        ('feature', X_mat.columns),
+        ('weight', classifier.coef_[0]),
+    ])
+
+    coef_df['abs'] = coef_df['weight'].abs()
+    coef_df = coef_df.sort_values('abs', ascending=False)
+    
+    return coef_df
+
+coef_df_dict = {
+    model: get_coefficients(classifier, X_partitions[model]['train'])
+    for model, classifier in final_classifiers.items()
+}
+
+
+# In[23]:
+
+model = 'full'
+
+print('{:.1%} zero coefficients; {:,} negative and {:,} positive coefficients'.format(
+    (coef_df_dict[model].weight == 0).mean(),
+    (coef_df_dict[model].weight < 0).sum(),
+    (coef_df_dict[model].weight > 0).sum()
+))
+coef_df_dict[model].head(10)
+
+
+# ## Investigate the predictions
+
+# In[24]:
+
+model = 'full'
+
+X_all = X_partitions[model]['train'].append(X_partitions[model]['test'])
+X_test_index = X_partitions[model]['test'].index
+y_all = y_train.append(y_test)
+
+predict_df = pd.DataFrame.from_items([
+    ('sample_id', X_all.index),
+    ('testing', X_all.index.isin(X_test_index).astype(int)),
+    ('status', y_all),
+    ('decision_function', final_pipelines[model].decision_function(X_all)),
+    ('probability', final_pipelines[model].predict_proba(X_all)[:, 1])
+])
+
+predict_df['probability_str'] = predict_df['probability'].apply('{:.1%}'.format)
+
+
+# In[25]:
+
+# Top predictions amongst negatives (potential hidden responders)
+predict_df.sort_values('decision_function', ascending=False).query("status == 0").head(10)
+
+
+# In[26]:
+
+# Ignore numpy warning caused by seaborn
+warnings.filterwarnings('ignore', 'using a non-integer number instead of an integer')
+
+ax = sns.distplot(predict_df.query("status == 0").decision_function, hist=False, label='Negatives')
+ax = sns.distplot(predict_df.query("status == 1").decision_function, hist=False, label='Positives')
+
+
+# In[27]:
+
+ax = sns.distplot(predict_df.query("status == 0").probability, hist=False, label='Negatives')
+ax = sns.distplot(predict_df.query("status == 1").probability, hist=False, label='Positives')
+
diff --git a/environment.yml b/environment.yml
index df0a70c..56f3bc6 100644
--- a/environment.yml
+++ b/environment.yml
@@ -11,6 +11,7 @@ dependencies:
 - seaborn=0.7.0
 - setuptools=27.2.0
 - statsmodels=0.6.1
+- vega=0.4.4
 - pip:
   - neo4j-driver==1.0.2
   - altair==1.2.0
diff --git a/jupyter_data/auc.csv b/jupyter_data/auc.csv
new file mode 100644
index 0000000..5d5d9cf
--- /dev/null
+++ b/jupyter_data/auc.csv
@@ -0,0 +1,7 @@
+auc,feature_set,partition,legend_index
+0.9305868803685398,full,test,0
+0.9303816224700439,full,train,1
+0.9243085880640466,expressions,test,2
+0.9250938696062881,expressions,train,3
+0.853991714253723,covariates,test,4
+0.8452932437615834,covariates,train,5
diff --git a/jupyter_data/roc_output.csv b/jupyter_data/roc_output.csv
new file mode 100644
index 0000000..2eaa734
--- /dev/null
+++ b/jupyter_data/roc_output.csv
@@ -0,0 +1,5347 @@
+false_positive_rate,feature_set,partition,true_positive_rate
+0.0,full,test,0.0
+0.002183406113537118,full,test,0.0
+0.002183406113537118,full,test,0.06593406593406594
+0.004366812227074236,full,test,0.06593406593406594
+0.004366812227074236,full,test,0.12454212454212454
+0.006550218340611353,full,test,0.12454212454212454
+0.006550218340611353,full,test,0.14285714285714285
+0.008733624454148471,full,test,0.14285714285714285
+0.008733624454148471,full,test,0.1684981684981685
+0.010917030567685589,full,test,0.1684981684981685
+0.010917030567685589,full,test,0.2490842490842491
+0.013100436681222707,full,test,0.2490842490842491
+0.013100436681222707,full,test,0.27472527472527475
+0.015283842794759825,full,test,0.27472527472527475
+0.015283842794759825,full,test,0.315018315018315
+0.019650655021834062,full,test,0.315018315018315
+0.019650655021834062,full,test,0.336996336996337
+0.021834061135371178,full,test,0.336996336996337
+0.021834061135371178,full,test,0.3443223443223443
+0.024017467248908297,full,test,0.3443223443223443
+0.024017467248908297,full,test,0.4139194139194139
+0.026200873362445413,full,test,0.4139194139194139
+0.026200873362445413,full,test,0.4432234432234432
+0.03056768558951965,full,test,0.4432234432234432
+0.03056768558951965,full,test,0.48717948717948717
+0.03275109170305677,full,test,0.48717948717948717
+0.03275109170305677,full,test,0.4908424908424908
+0.034934497816593885,full,test,0.4908424908424908
+0.034934497816593885,full,test,0.4981684981684982
+0.03711790393013101,full,test,0.4981684981684982
+0.03711790393013101,full,test,0.5128205128205128
+0.039301310043668124,full,test,0.5128205128205128
+0.039301310043668124,full,test,0.5201465201465202
+0.04148471615720524,full,test,0.5201465201465202
+0.04148471615720524,full,test,0.5274725274725275
+0.04585152838427948,full,test,0.5274725274725275
+0.04585152838427948,full,test,0.5311355311355311
+0.048034934497816595,full,test,0.5311355311355311
+0.048034934497816595,full,test,0.5531135531135531
+0.05021834061135371,full,test,0.5531135531135531
+0.05021834061135371,full,test,0.5714285714285714
+0.05240174672489083,full,test,0.5714285714285714
+0.05240174672489083,full,test,0.5824175824175825
+0.05458515283842795,full,test,0.5824175824175825
+0.05458515283842795,full,test,0.608058608058608
+0.056768558951965066,full,test,0.608058608058608
+0.056768558951965066,full,test,0.6153846153846154
+0.05895196506550218,full,test,0.6153846153846154
+0.05895196506550218,full,test,0.6373626373626373
+0.0611353711790393,full,test,0.6373626373626373
+0.0611353711790393,full,test,0.6446886446886447
+0.06331877729257641,full,test,0.6446886446886447
+0.06331877729257641,full,test,0.6483516483516484
+0.06550218340611354,full,test,0.6483516483516484
+0.06550218340611354,full,test,0.652014652014652
+0.06768558951965066,full,test,0.652014652014652
+0.06768558951965066,full,test,0.6703296703296703
+0.06986899563318777,full,test,0.6703296703296703
+0.06986899563318777,full,test,0.706959706959707
+0.07205240174672489,full,test,0.706959706959707
+0.07205240174672489,full,test,0.7106227106227107
+0.07641921397379912,full,test,0.7106227106227107
+0.07641921397379912,full,test,0.7142857142857143
+0.07860262008733625,full,test,0.7142857142857143
+0.07860262008733625,full,test,0.717948717948718
+0.08078602620087336,full,test,0.717948717948718
+0.08078602620087336,full,test,0.7289377289377289
+0.08296943231441048,full,test,0.7289377289377289
+0.08296943231441048,full,test,0.7326007326007326
+0.09170305676855896,full,test,0.7326007326007326
+0.09170305676855896,full,test,0.7472527472527473
+0.09388646288209607,full,test,0.7472527472527473
+0.09388646288209607,full,test,0.7582417582417582
+0.09606986899563319,full,test,0.7582417582417582
+0.09606986899563319,full,test,0.7802197802197802
+0.0982532751091703,full,test,0.7802197802197802
+0.0982532751091703,full,test,0.7912087912087912
+0.10262008733624454,full,test,0.7912087912087912
+0.10262008733624454,full,test,0.7948717948717948
+0.10698689956331878,full,test,0.7948717948717948
+0.10698689956331878,full,test,0.7985347985347986
+0.11790393013100436,full,test,0.7985347985347986
+0.11790393013100436,full,test,0.8058608058608059
+0.1222707423580786,full,test,0.8058608058608059
+0.1222707423580786,full,test,0.8131868131868132
+0.12445414847161572,full,test,0.8131868131868132
+0.12445414847161572,full,test,0.8241758241758241
+0.12882096069868995,full,test,0.8241758241758241
+0.12882096069868995,full,test,0.8315018315018315
+0.13100436681222707,full,test,0.8315018315018315
+0.13100436681222707,full,test,0.8351648351648352
+0.1331877729257642,full,test,0.8351648351648352
+0.1331877729257642,full,test,0.8534798534798534
+0.13537117903930132,full,test,0.8534798534798534
+0.13537117903930132,full,test,0.8608058608058609
+0.14410480349344978,full,test,0.8608058608058609
+0.14410480349344978,full,test,0.9010989010989011
+0.14847161572052403,full,test,0.9010989010989011
+0.14847161572052403,full,test,0.9047619047619048
+0.15065502183406113,full,test,0.9047619047619048
+0.15065502183406113,full,test,0.9084249084249084
+0.15283842794759825,full,test,0.9084249084249084
+0.15283842794759825,full,test,0.9120879120879121
+0.17467248908296942,full,test,0.9120879120879121
+0.17467248908296942,full,test,0.9157509157509157
+0.2074235807860262,full,test,0.9157509157509157
+0.2074235807860262,full,test,0.9230769230769231
+0.21397379912663755,full,test,0.9230769230769231
+0.21397379912663755,full,test,0.9267399267399268
+0.2183406113537118,full,test,0.9267399267399268
+0.2183406113537118,full,test,0.9340659340659341
+0.2336244541484716,full,test,0.9340659340659341
+0.2336244541484716,full,test,0.945054945054945
+0.23799126637554585,full,test,0.945054945054945
+0.23799126637554585,full,test,0.9487179487179487
+0.24890829694323144,full,test,0.9487179487179487
+0.24890829694323144,full,test,0.9523809523809523
+0.2576419213973799,full,test,0.9523809523809523
+0.2576419213973799,full,test,0.9597069597069597
+0.259825327510917,full,test,0.9597069597069597
+0.259825327510917,full,test,0.9633699633699634
+0.26419213973799127,full,test,0.9633699633699634
+0.26419213973799127,full,test,0.967032967032967
+0.27074235807860264,full,test,0.967032967032967
+0.27074235807860264,full,test,0.9743589743589743
+0.2838427947598253,full,test,0.9743589743589743
+0.2838427947598253,full,test,0.978021978021978
+0.35152838427947597,full,test,0.978021978021978
+0.35152838427947597,full,test,0.9816849816849816
+0.39956331877729256,full,test,0.9816849816849816
+0.39956331877729256,full,test,0.9853479853479854
+0.4650655021834061,full,test,0.9853479853479854
+0.4650655021834061,full,test,0.989010989010989
+0.4868995633187773,full,test,0.989010989010989
+0.4868995633187773,full,test,0.9926739926739927
+0.5676855895196506,full,test,0.9926739926739927
+0.5676855895196506,full,test,0.9963369963369964
+0.6986899563318777,full,test,0.9963369963369964
+0.6986899563318777,full,test,1.0
+1.0,full,test,1.0
+0.0,full,train,0.0
+0.0002346866932644919,full,train,0.0
+0.0002346866932644919,full,train,0.00216076058772688
+0.0004693733865289838,full,train,0.00216076058772688
+0.0004693733865289838,full,train,0.004753673292999135
+0.0007040600797934757,full,train,0.004753673292999135
+0.0007040600797934757,full,train,0.01901469317199654
+0.0011734334663224596,full,train,0.01901469317199654
+0.0011734334663224596,full,train,0.024632670700086432
+0.0014081201595869514,full,train,0.024632670700086432
+0.0014081201595869514,full,train,0.032843560933448576
+0.0016428068528514432,full,train,0.032843560933448576
+0.0016428068528514432,full,train,0.035868625756266204
+0.0018774935461159353,full,train,0.035868625756266204
+0.0018774935461159353,full,train,0.036300777873811585
+0.0021121802393804273,full,train,0.036300777873811585
+0.0021121802393804273,full,train,0.06136560069144339
+0.002346866932644919,full,train,0.06136560069144339
+0.002346866932644919,full,train,0.06784788245462403
+0.002581553625909411,full,train,0.06784788245462403
+0.002581553625909411,full,train,0.09075194468452895
+0.002816240319173903,full,train,0.09075194468452895
+0.002816240319173903,full,train,0.09161624891961971
+0.0030509270124383947,full,train,0.09161624891961971
+0.0030509270124383947,full,train,0.11797752808988764
+0.0032856137057028865,full,train,0.11797752808988764
+0.0032856137057028865,full,train,0.12186689714779603
+0.0035203003989673787,full,train,0.12186689714779603
+0.0035203003989673787,full,train,0.12359550561797752
+0.0037549870922318706,full,train,0.12359550561797752
+0.0037549870922318706,full,train,0.12489196197061365
+0.003989673785496362,full,train,0.12489196197061365
+0.003989673785496362,full,train,0.1257562662057044
+0.004224360478760855,full,train,0.1257562662057044
+0.004224360478760855,full,train,0.13223854796888504
+0.004459047172025346,full,train,0.13223854796888504
+0.004459047172025346,full,train,0.13439930855661192
+0.00492842055855433,full,train,0.13439930855661192
+0.00492842055855433,full,train,0.1365600691443388
+0.005163107251818822,full,train,0.1365600691443388
+0.005163107251818822,full,train,0.14433880726015558
+0.005397793945083313,full,train,0.14433880726015558
+0.005397793945083313,full,train,0.14822817631806395
+0.005632480638347806,full,train,0.14822817631806395
+0.005632480638347806,full,train,0.15643906655142611
+0.005867167331612298,full,train,0.15643906655142611
+0.005867167331612298,full,train,0.16853932584269662
+0.006101854024876789,full,train,0.16853932584269662
+0.006101854024876789,full,train,0.17329299913569576
+0.0063365407181412816,full,train,0.17329299913569576
+0.0063365407181412816,full,train,0.17502160760587726
+0.006571227411405773,full,train,0.17502160760587726
+0.006571227411405773,full,train,0.17718236819360414
+0.006805914104670265,full,train,0.17718236819360414
+0.006805914104670265,full,train,0.18409680207433016
+0.0070406007979347575,full,train,0.18409680207433016
+0.0070406007979347575,full,train,0.18452895419187554
+0.007275287491199249,full,train,0.18452895419187554
+0.007275287491199249,full,train,0.18798617113223856
+0.007509974184463741,full,train,0.18798617113223856
+0.007509974184463741,full,train,0.2031114952463267
+0.0077446608777282325,full,train,0.2031114952463267
+0.0077446608777282325,full,train,0.21477960242005187
+0.007979347570992725,full,train,0.21477960242005187
+0.007979347570992725,full,train,0.2173725151253241
+0.008214034264257217,full,train,0.2173725151253241
+0.008214034264257217,full,train,0.2212618841832325
+0.00844872095752171,full,train,0.2212618841832325
+0.00844872095752171,full,train,0.22212618841832324
+0.0086834076507862,full,train,0.22212618841832324
+0.0086834076507862,full,train,0.22255834053586862
+0.008918094344050692,full,train,0.22255834053586862
+0.008918094344050692,full,train,0.2247191011235955
+0.009152781037315184,full,train,0.2247191011235955
+0.009152781037315184,full,train,0.22687986171132238
+0.009387467730579677,full,train,0.22687986171132238
+0.009387467730579677,full,train,0.22731201382886776
+0.009622154423844167,full,train,0.22731201382886776
+0.009622154423844167,full,train,0.22904062229904926
+0.00985684111710866,full,train,0.22904062229904926
+0.00985684111710866,full,train,0.22947277441659464
+0.010091527810373152,full,train,0.22947277441659464
+0.010091527810373152,full,train,0.22990492653414002
+0.010326214503637644,full,train,0.22990492653414002
+0.010326214503637644,full,train,0.2394122731201383
+0.010560901196902136,full,train,0.2394122731201383
+0.010560901196902136,full,train,0.24027657735522903
+0.010795587890166627,full,train,0.24027657735522903
+0.010795587890166627,full,train,0.2424373379429559
+0.011264961276695611,full,train,0.2424373379429559
+0.011264961276695611,full,train,0.2428694900605013
+0.011499647969960104,full,train,0.2428694900605013
+0.011499647969960104,full,train,0.24762316335350043
+0.011734334663224596,full,train,0.24762316335350043
+0.011734334663224596,full,train,0.2480553154710458
+0.011969021356489086,full,train,0.2480553154710458
+0.011969021356489086,full,train,0.25064822817631804
+0.012203708049753579,full,train,0.25064822817631804
+0.012203708049753579,full,train,0.2549697493517718
+0.012438394743018071,full,train,0.2549697493517718
+0.012438394743018071,full,train,0.26534140017286084
+0.012673081436282563,full,train,0.26534140017286084
+0.012673081436282563,full,train,0.2662057044079516
+0.012907768129547055,full,train,0.2662057044079516
+0.012907768129547055,full,train,0.27052722558340536
+0.013142454822811546,full,train,0.27052722558340536
+0.013142454822811546,full,train,0.27441659464131374
+0.013377141516076038,full,train,0.27441659464131374
+0.013377141516076038,full,train,0.287381158167675
+0.014081201595869515,full,train,0.287381158167675
+0.014081201595869515,full,train,0.2878133102852204
+0.014315888289134006,full,train,0.2878133102852204
+0.014315888289134006,full,train,0.29472774416594644
+0.014550574982398498,full,train,0.29472774416594644
+0.014550574982398498,full,train,0.2964563526361279
+0.01478526167566299,full,train,0.2964563526361279
+0.01478526167566299,full,train,0.2968885047536733
+0.015019948368927482,full,train,0.2968885047536733
+0.015019948368927482,full,train,0.29732065687121867
+0.015254635062191975,full,train,0.29732065687121867
+0.015254635062191975,full,train,0.30380293863439933
+0.015489321755456465,full,train,0.30380293863439933
+0.015489321755456465,full,train,0.30423509075194466
+0.015724008448720957,full,train,0.30423509075194466
+0.015724008448720957,full,train,0.30466724286949004
+0.01595869514198545,full,train,0.30466724286949004
+0.01595869514198545,full,train,0.3081244598098531
+0.016193381835249942,full,train,0.3081244598098531
+0.016193381835249942,full,train,0.31287813310285223
+0.016428068528514434,full,train,0.31287813310285223
+0.016428068528514434,full,train,0.31374243733794294
+0.016662755221778926,full,train,0.31374243733794294
+0.016662755221778926,full,train,0.3141745894554883
+0.01689744191504342,full,train,0.3141745894554883
+0.01689744191504342,full,train,0.317199654278306
+0.017132128608307907,full,train,0.317199654278306
+0.017132128608307907,full,train,0.3184961106309421
+0.0173668153015724,full,train,0.3184961106309421
+0.0173668153015724,full,train,0.3202247191011236
+0.017601501994836892,full,train,0.3202247191011236
+0.017601501994836892,full,train,0.32108902333621436
+0.017836188688101384,full,train,0.32108902333621436
+0.017836188688101384,full,train,0.32152117545375974
+0.018070875381365877,full,train,0.32152117545375974
+0.018070875381365877,full,train,0.3232497839239412
+0.01830556207463037,full,train,0.3232497839239412
+0.01830556207463037,full,train,0.32497839239412274
+0.01854024876789486,full,train,0.32497839239412274
+0.01854024876789486,full,train,0.3262748487467589
+0.018774935461159353,full,train,0.3262748487467589
+0.018774935461159353,full,train,0.3267070008643042
+0.019009622154423846,full,train,0.3267070008643042
+0.019009622154423846,full,train,0.33016421780466726
+0.019244308847688334,full,train,0.33016421780466726
+0.019244308847688334,full,train,0.3327571305099395
+0.019478995540952827,full,train,0.3327571305099395
+0.019478995540952827,full,train,0.34572169403630076
+0.01971368223421732,full,train,0.34572169403630076
+0.01971368223421732,full,train,0.34961106309420914
+0.01994836892748181,full,train,0.34961106309420914
+0.01994836892748181,full,train,0.3509075194468453
+0.020183055620746303,full,train,0.3509075194468453
+0.020183055620746303,full,train,0.35695764909248057
+0.020652429007275288,full,train,0.35695764909248057
+0.020652429007275288,full,train,0.35782195332757133
+0.02088711570053978,full,train,0.35782195332757133
+0.02088711570053978,full,train,0.3656006914433881
+0.021121802393804272,full,train,0.3656006914433881
+0.021121802393804272,full,train,0.36776145203111493
+0.021356489087068765,full,train,0.36776145203111493
+0.021356489087068765,full,train,0.36949006050129646
+0.021591175780333254,full,train,0.36949006050129646
+0.021591175780333254,full,train,0.3720829732065687
+0.021825862473597746,full,train,0.3720829732065687
+0.021825862473597746,full,train,0.3759723422644771
+0.022060549166862238,full,train,0.3759723422644771
+0.022060549166862238,full,train,0.378133102852204
+0.02229523586012673,full,train,0.378133102852204
+0.02229523586012673,full,train,0.38245462402765773
+0.022529922553391223,full,train,0.38245462402765773
+0.022529922553391223,full,train,0.38504753673293
+0.022764609246655715,full,train,0.38504753673293
+0.022764609246655715,full,train,0.3898012100259291
+0.022999295939920207,full,train,0.3898012100259291
+0.022999295939920207,full,train,0.395419187554019
+0.0232339826331847,full,train,0.395419187554019
+0.0232339826331847,full,train,0.39714779602420053
+0.02346866932644919,full,train,0.39714779602420053
+0.02346866932644919,full,train,0.40319792566983575
+0.023703356019713684,full,train,0.40319792566983575
+0.023703356019713684,full,train,0.40579083837510804
+0.023938042712978173,full,train,0.40579083837510804
+0.023938042712978173,full,train,0.4083837510803803
+0.024172729406242665,full,train,0.4083837510803803
+0.024172729406242665,full,train,0.40924805531547104
+0.024407416099507157,full,train,0.40924805531547104
+0.024407416099507157,full,train,0.4096802074330164
+0.02464210279277165,full,train,0.4096802074330164
+0.02464210279277165,full,train,0.4152981849611063
+0.024876789486036142,full,train,0.4152981849611063
+0.024876789486036142,full,train,0.4222126188418323
+0.025111476179300634,full,train,0.4222126188418323
+0.025111476179300634,full,train,0.42523768366465
+0.025346162872565126,full,train,0.42523768366465
+0.025346162872565126,full,train,0.4261019878997407
+0.026284909645623092,full,train,0.4261019878997407
+0.026284909645623092,full,train,0.42696629213483145
+0.026519596338887584,full,train,0.42696629213483145
+0.026519596338887584,full,train,0.42912705272255836
+0.026754283032152076,full,train,0.42912705272255836
+0.026754283032152076,full,train,0.43258426966292135
+0.02698896972541657,full,train,0.43258426966292135
+0.02698896972541657,full,train,0.4334485738980121
+0.02722365641868106,full,train,0.4334485738980121
+0.02722365641868106,full,train,0.4347450302506482
+0.027693029805210045,full,train,0.4347450302506482
+0.027693029805210045,full,train,0.4373379429559205
+0.027927716498474538,full,train,0.4373379429559205
+0.027927716498474538,full,train,0.43777009507346587
+0.02816240319173903,full,train,0.43777009507346587
+0.02816240319173903,full,train,0.43820224719101125
+0.02863177657826801,full,train,0.43820224719101125
+0.02863177657826801,full,train,0.44165946413137425
+0.029101149964796996,full,train,0.44165946413137425
+0.029101149964796996,full,train,0.4420916162489196
+0.02957052335132598,full,train,0.4420916162489196
+0.02957052335132598,full,train,0.44684528954191877
+0.029805210044590472,full,train,0.44684528954191877
+0.029805210044590472,full,train,0.45246326707000867
+0.030039896737854965,full,train,0.45246326707000867
+0.030039896737854965,full,train,0.4533275713050994
+0.030274583431119457,full,train,0.4533275713050994
+0.030274583431119457,full,train,0.4585133967156439
+0.03050927012438395,full,train,0.4585133967156439
+0.03050927012438395,full,train,0.45980985306828004
+0.030743956817648438,full,train,0.45980985306828004
+0.030743956817648438,full,train,0.46326707000864303
+0.03097864351091293,full,train,0.46326707000864303
+0.03097864351091293,full,train,0.4641313742437338
+0.031213330204177422,full,train,0.4641313742437338
+0.031213330204177422,full,train,0.4645635263612792
+0.03168270359070641,full,train,0.4645635263612792
+0.03168270359070641,full,train,0.4671564390665514
+0.0319173902839709,full,train,0.4671564390665514
+0.0319173902839709,full,train,0.4710458081244598
+0.03215207697723539,full,train,0.4710458081244598
+0.03215207697723539,full,train,0.4732065687121867
+0.032386763670499884,full,train,0.4732065687121867
+0.032386763670499884,full,train,0.47407087294727746
+0.032621450363764376,full,train,0.47407087294727746
+0.032621450363764376,full,train,0.4783923941227312
+0.03309082375029336,full,train,0.4783923941227312
+0.03309082375029336,full,train,0.4822817631806396
+0.03332551044355785,full,train,0.4822817631806396
+0.03332551044355785,full,train,0.48314606741573035
+0.033560197136822345,full,train,0.48314606741573035
+0.033560197136822345,full,train,0.4853068280034572
+0.03379488383008684,full,train,0.4853068280034572
+0.03379488383008684,full,train,0.48660328435609335
+0.03402957052335132,full,train,0.48660328435609335
+0.03402957052335132,full,train,0.4870354364736387
+0.034264257216615815,full,train,0.4870354364736387
+0.034264257216615815,full,train,0.48833189282627487
+0.0347336306031448,full,train,0.48833189282627487
+0.0347336306031448,full,train,0.49265341400172863
+0.03496831729640929,full,train,0.49265341400172863
+0.03496831729640929,full,train,0.49351771823681934
+0.035203003989673784,full,train,0.49351771823681934
+0.035203003989673784,full,train,0.49740708729472777
+0.035437690682938276,full,train,0.49740708729472777
+0.035437690682938276,full,train,0.5
+0.03567237737620277,full,train,0.5
+0.03567237737620277,full,train,0.5012964563526361
+0.03590706406946726,full,train,0.5012964563526361
+0.03590706406946726,full,train,0.5017286084701815
+0.03614175076273175,full,train,0.5017286084701815
+0.03614175076273175,full,train,0.5021607605877269
+0.036376437455996245,full,train,0.5021607605877269
+0.036376437455996245,full,train,0.513828867761452
+0.03661112414926074,full,train,0.513828867761452
+0.03661112414926074,full,train,0.5151253241140882
+0.03684581084252523,full,train,0.5151253241140882
+0.03684581084252523,full,train,0.5177182368193605
+0.03708049753578972,full,train,0.5177182368193605
+0.03708049753578972,full,train,0.5185825410544511
+0.037315184229054214,full,train,0.5185825410544511
+0.037315184229054214,full,train,0.5198789974070873
+0.03754987092231871,full,train,0.5198789974070873
+0.03754987092231871,full,train,0.5211754537597234
+0.0377845576155832,full,train,0.5211754537597234
+0.0377845576155832,full,train,0.5267934312878133
+0.03801924430884769,full,train,0.5267934312878133
+0.03801924430884769,full,train,0.5285220397579948
+0.03825393100211218,full,train,0.5285220397579948
+0.03825393100211218,full,train,0.5298184961106309
+0.03872330438864116,full,train,0.5298184961106309
+0.03872330438864116,full,train,0.5315471045808124
+0.03895799108190565,full,train,0.5315471045808124
+0.03895799108190565,full,train,0.5324114088159032
+0.039192677775170146,full,train,0.5324114088159032
+0.039192677775170146,full,train,0.5328435609334485
+0.03942736446843464,full,train,0.5328435609334485
+0.03942736446843464,full,train,0.5354364736387208
+0.03966205116169913,full,train,0.5354364736387208
+0.03966205116169913,full,train,0.5363007778738116
+0.03989673785496362,full,train,0.5363007778738116
+0.03989673785496362,full,train,0.5384615384615384
+0.040131424548228115,full,train,0.5384615384615384
+0.040131424548228115,full,train,0.5393258426966292
+0.04036611124149261,full,train,0.5393258426966292
+0.04036611124149261,full,train,0.5397579948141746
+0.0406007979347571,full,train,0.5397579948141746
+0.0406007979347571,full,train,0.54019014693172
+0.041304858014550576,full,train,0.54019014693172
+0.041304858014550576,full,train,0.5496974935177182
+0.04153954470781507,full,train,0.5496974935177182
+0.04153954470781507,full,train,0.5583405358686258
+0.04177423140107956,full,train,0.5583405358686258
+0.04177423140107956,full,train,0.5600691443388073
+0.04200891809434405,full,train,0.5600691443388073
+0.04200891809434405,full,train,0.5656871218668972
+0.04247829148087304,full,train,0.5656871218668972
+0.04247829148087304,full,train,0.5661192739844425
+0.04294766486740202,full,train,0.5661192739844425
+0.04294766486740202,full,train,0.5665514261019879
+0.04318235156066651,full,train,0.5665514261019879
+0.04318235156066651,full,train,0.5669835782195333
+0.043417038253931,full,train,0.5669835782195333
+0.043417038253931,full,train,0.5691443388072601
+0.04365172494719549,full,train,0.5691443388072601
+0.04365172494719549,full,train,0.5704407951598963
+0.043886411640459984,full,train,0.5704407951598963
+0.043886411640459984,full,train,0.5721694036300777
+0.044121098333724476,full,train,0.5721694036300777
+0.044121098333724476,full,train,0.5726015557476232
+0.04459047172025346,full,train,0.5726015557476232
+0.04459047172025346,full,train,0.5756266205704408
+0.04482515841351795,full,train,0.5756266205704408
+0.04482515841351795,full,train,0.5764909248055315
+0.04529453180004694,full,train,0.5764909248055315
+0.04529453180004694,full,train,0.5773552290406223
+0.04552921849331143,full,train,0.5773552290406223
+0.04552921849331143,full,train,0.5786516853932584
+0.045998591879840414,full,train,0.5786516853932584
+0.045998591879840414,full,train,0.5795159896283492
+0.046233278573104906,full,train,0.5795159896283492
+0.046233278573104906,full,train,0.5799481417458946
+0.04670265195963389,full,train,0.5799481417458946
+0.04670265195963389,full,train,0.5821089023336214
+0.04693733865289838,full,train,0.5821089023336214
+0.04693733865289838,full,train,0.5825410544511668
+0.047172025346162876,full,train,0.5825410544511668
+0.047172025346162876,full,train,0.5834053586862575
+0.04740671203942737,full,train,0.5834053586862575
+0.04740671203942737,full,train,0.583837510803803
+0.047876085425956345,full,train,0.583837510803803
+0.047876085425956345,full,train,0.5903197925669835
+0.04811077211922084,full,train,0.5903197925669835
+0.04811077211922084,full,train,0.5955056179775281
+0.04834545881248533,full,train,0.5955056179775281
+0.04834545881248533,full,train,0.5989628349178912
+0.04858014550574982,full,train,0.5989628349178912
+0.04858014550574982,full,train,0.5993949870354365
+0.04904951889227881,full,train,0.5993949870354365
+0.04904951889227881,full,train,0.6002592912705272
+0.0492842055855433,full,train,0.6002592912705272
+0.0492842055855433,full,train,0.601123595505618
+0.04951889227880779,full,train,0.601123595505618
+0.04951889227880779,full,train,0.6037165082108902
+0.049753578972072283,full,train,0.6037165082108902
+0.049753578972072283,full,train,0.6050129645635264
+0.05022295235860127,full,train,0.6050129645635264
+0.05022295235860127,full,train,0.6058772687986171
+0.05045763905186576,full,train,0.6058772687986171
+0.05045763905186576,full,train,0.6067415730337079
+0.05069232574513025,full,train,0.6067415730337079
+0.05069232574513025,full,train,0.6071737251512532
+0.050927012438394745,full,train,0.6071737251512532
+0.050927012438394745,full,train,0.6089023336214348
+0.05116169913165924,full,train,0.6089023336214348
+0.05116169913165924,full,train,0.6097666378565255
+0.05139638582492373,full,train,0.6097666378565255
+0.05139638582492373,full,train,0.6106309420916163
+0.051865759211452714,full,train,0.6106309420916163
+0.051865759211452714,full,train,0.6119273984442524
+0.0521004459047172,full,train,0.6119273984442524
+0.0521004459047172,full,train,0.6205704407951599
+0.05233513259798169,full,train,0.6205704407951599
+0.05233513259798169,full,train,0.6214347450302506
+0.052569819291246184,full,train,0.6214347450302506
+0.052569819291246184,full,train,0.6222990492653414
+0.052804505984510676,full,train,0.6222990492653414
+0.052804505984510676,full,train,0.6244598098530683
+0.05303919267777517,full,train,0.6244598098530683
+0.05303919267777517,full,train,0.625324114088159
+0.05327387937103966,full,train,0.625324114088159
+0.05327387937103966,full,train,0.6261884183232498
+0.05350856606430415,full,train,0.6261884183232498
+0.05350856606430415,full,train,0.6266205704407951
+0.053743252757568645,full,train,0.6266205704407951
+0.053743252757568645,full,train,0.6283491789109766
+0.05397793945083314,full,train,0.6283491789109766
+0.05397793945083314,full,train,0.6287813310285221
+0.05421262614409763,full,train,0.6287813310285221
+0.05421262614409763,full,train,0.6313742437337942
+0.05444731283736212,full,train,0.6313742437337942
+0.05444731283736212,full,train,0.6339671564390665
+0.054681999530626614,full,train,0.6339671564390665
+0.054681999530626614,full,train,0.6382886776145204
+0.054916686223891106,full,train,0.6382886776145204
+0.054916686223891106,full,train,0.6387208297320657
+0.05562074630368458,full,train,0.6387208297320657
+0.05562074630368458,full,train,0.6400172860847018
+0.055855432996949075,full,train,0.6400172860847018
+0.055855432996949075,full,train,0.642610198789974
+0.05609011969021357,full,train,0.642610198789974
+0.05609011969021357,full,train,0.6434745030250648
+0.05632480638347806,full,train,0.6434745030250648
+0.05632480638347806,full,train,0.6439066551426103
+0.05655949307674255,full,train,0.6439066551426103
+0.05655949307674255,full,train,0.6443388072601556
+0.05679417977000704,full,train,0.6443388072601556
+0.05679417977000704,full,train,0.6447709593777009
+0.05726355315653602,full,train,0.6447709593777009
+0.05726355315653602,full,train,0.6456352636127917
+0.057498239849800514,full,train,0.6456352636127917
+0.057498239849800514,full,train,0.6477960242005186
+0.0579676132363295,full,train,0.6477960242005186
+0.0579676132363295,full,train,0.6486603284356093
+0.05820229992959399,full,train,0.6486603284356093
+0.05820229992959399,full,train,0.6490924805531547
+0.05843698662285848,full,train,0.6490924805531547
+0.05843698662285848,full,train,0.6529818496110631
+0.058671673316122976,full,train,0.6529818496110631
+0.058671673316122976,full,train,0.6538461538461539
+0.05890636000938747,full,train,0.6538461538461539
+0.05890636000938747,full,train,0.6555747623163354
+0.05914104670265196,full,train,0.6555747623163354
+0.05914104670265196,full,train,0.6581676750216076
+0.05937573339591645,full,train,0.6581676750216076
+0.05937573339591645,full,train,0.6616248919619706
+0.059610420089180945,full,train,0.6616248919619706
+0.059610420089180945,full,train,0.6624891961970614
+0.06007979347570993,full,train,0.6624891961970614
+0.06007979347570993,full,train,0.6637856525496975
+0.06031448016897442,full,train,0.6637856525496975
+0.06031448016897442,full,train,0.6642178046672429
+0.0610185402487679,full,train,0.6642178046672429
+0.0610185402487679,full,train,0.6663785652549697
+0.061253226942032384,full,train,0.6663785652549697
+0.061253226942032384,full,train,0.6676750216076058
+0.061487913635296876,full,train,0.6676750216076058
+0.061487913635296876,full,train,0.668971477960242
+0.06172260032856137,full,train,0.668971477960242
+0.06172260032856137,full,train,0.6698357821953328
+0.06195728702182586,full,train,0.6698357821953328
+0.06195728702182586,full,train,0.6707000864304236
+0.06219197371509035,full,train,0.6707000864304236
+0.06219197371509035,full,train,0.6719965427830596
+0.06266134710161934,full,train,0.6719965427830596
+0.06266134710161934,full,train,0.6732929991356957
+0.06289603379488383,full,train,0.6732929991356957
+0.06289603379488383,full,train,0.6737251512532412
+0.06336540718141281,full,train,0.6737251512532412
+0.06336540718141281,full,train,0.6750216076058773
+0.0636000938746773,full,train,0.6750216076058773
+0.0636000938746773,full,train,0.6763180639585133
+0.06406946726120628,full,train,0.6763180639585133
+0.06406946726120628,full,train,0.6780466724286949
+0.06430415395447078,full,train,0.6780466724286949
+0.06430415395447078,full,train,0.6815038893690579
+0.06500821403426425,full,train,0.6815038893690579
+0.06500821403426425,full,train,0.6823681936041487
+0.06524290072752875,full,train,0.6823681936041487
+0.06524290072752875,full,train,0.6849611063094209
+0.06547758742079324,full,train,0.6849611063094209
+0.06547758742079324,full,train,0.6901469317199654
+0.06571227411405774,full,train,0.6901469317199654
+0.06571227411405774,full,train,0.6944684528954191
+0.06594696080732222,full,train,0.6944684528954191
+0.06594696080732222,full,train,0.6949006050129646
+0.06618164750058672,full,train,0.6949006050129646
+0.06618164750058672,full,train,0.6957649092480553
+0.0666510208871157,full,train,0.6957649092480553
+0.0666510208871157,full,train,0.6966292134831461
+0.06688570758038019,full,train,0.6966292134831461
+0.06688570758038019,full,train,0.6974935177182369
+0.06712039427364469,full,train,0.6974935177182369
+0.06712039427364469,full,train,0.6992221261884183
+0.06735508096690918,full,train,0.6992221261884183
+0.06735508096690918,full,train,0.700086430423509
+0.06782445435343816,full,train,0.700086430423509
+0.06782445435343816,full,train,0.7009507346585998
+0.06805914104670265,full,train,0.7009507346585998
+0.06805914104670265,full,train,0.7026793431287813
+0.06852851443323163,full,train,0.7026793431287813
+0.06852851443323163,full,train,0.7057044079515989
+0.06876320112649613,full,train,0.7057044079515989
+0.06876320112649613,full,train,0.7078651685393258
+0.06899788781976061,full,train,0.7078651685393258
+0.06899788781976061,full,train,0.7082973206568712
+0.06923257451302511,full,train,0.7082973206568712
+0.06923257451302511,full,train,0.7095937770095073
+0.0694672612062896,full,train,0.7095937770095073
+0.0694672612062896,full,train,0.7113223854796888
+0.0697019478995541,full,train,0.7113223854796888
+0.0697019478995541,full,train,0.7126188418323249
+0.06993663459281858,full,train,0.7126188418323249
+0.06993663459281858,full,train,0.7134831460674157
+0.07017132128608308,full,train,0.7134831460674157
+0.07017132128608308,full,train,0.7147796024200519
+0.07040600797934757,full,train,0.7147796024200519
+0.07040600797934757,full,train,0.716076058772688
+0.07064069467261207,full,train,0.716076058772688
+0.07064069467261207,full,train,0.7169403630077787
+0.07181412813893452,full,train,0.7169403630077787
+0.07181412813893452,full,train,0.7173725151253241
+0.07204881483219902,full,train,0.7173725151253241
+0.07204881483219902,full,train,0.719533275713051
+0.07251818821872799,full,train,0.719533275713051
+0.07251818821872799,full,train,0.7216940363007779
+0.07275287491199249,full,train,0.7216940363007779
+0.07275287491199249,full,train,0.722990492653414
+0.07298756160525698,full,train,0.722990492653414
+0.07298756160525698,full,train,0.7234226447709594
+0.07369162168505046,full,train,0.7234226447709594
+0.07369162168505046,full,train,0.7247191011235955
+0.07392630837831494,full,train,0.7247191011235955
+0.07392630837831494,full,train,0.7251512532411409
+0.07416099507157944,full,train,0.7251512532411409
+0.07416099507157944,full,train,0.7255834053586863
+0.07439568176484393,full,train,0.7255834053586863
+0.07439568176484393,full,train,0.726447709593777
+0.07463036845810843,full,train,0.726447709593777
+0.07463036845810843,full,train,0.7268798617113224
+0.07486505515137291,full,train,0.7268798617113224
+0.07486505515137291,full,train,0.7273120138288678
+0.07509974184463741,full,train,0.7273120138288678
+0.07509974184463741,full,train,0.7290406222990493
+0.0755691152311664,full,train,0.7290406222990493
+0.0755691152311664,full,train,0.7307692307692307
+0.07603848861769538,full,train,0.7307692307692307
+0.07603848861769538,full,train,0.7312013828867762
+0.07627317531095987,full,train,0.7312013828867762
+0.07627317531095987,full,train,0.7316335350043215
+0.07650786200422437,full,train,0.7316335350043215
+0.07650786200422437,full,train,0.7324978392394123
+0.07674254869748885,full,train,0.7324978392394123
+0.07674254869748885,full,train,0.7350907519446845
+0.07697723539075334,full,train,0.7350907519446845
+0.07697723539075334,full,train,0.7372515125324114
+0.07721192208401784,full,train,0.7372515125324114
+0.07721192208401784,full,train,0.7376836646499568
+0.07744660877728232,full,train,0.7376836646499568
+0.07744660877728232,full,train,0.7398444252376837
+0.07768129547054682,full,train,0.7398444252376837
+0.07768129547054682,full,train,0.740276577355229
+0.0779159821638113,full,train,0.740276577355229
+0.0779159821638113,full,train,0.7415730337078652
+0.0781506688570758,full,train,0.7415730337078652
+0.0781506688570758,full,train,0.7428694900605013
+0.07838535555034029,full,train,0.7428694900605013
+0.07838535555034029,full,train,0.743733794295592
+0.07885472893686928,full,train,0.743733794295592
+0.07885472893686928,full,train,0.7441659464131374
+0.07932410232339826,full,train,0.7441659464131374
+0.07932410232339826,full,train,0.7458945548833189
+0.07955878901666276,full,train,0.7458945548833189
+0.07955878901666276,full,train,0.7467588591184097
+0.07979347570992724,full,train,0.7467588591184097
+0.07979347570992724,full,train,0.7471910112359551
+0.08002816240319174,full,train,0.7471910112359551
+0.08002816240319174,full,train,0.7476231633535004
+0.0812015958695142,full,train,0.7476231633535004
+0.0812015958695142,full,train,0.7489196197061365
+0.08190565594930767,full,train,0.7489196197061365
+0.08190565594930767,full,train,0.7497839239412273
+0.08214034264257217,full,train,0.7497839239412273
+0.08214034264257217,full,train,0.7519446845289542
+0.08260971602910115,full,train,0.7519446845289542
+0.08260971602910115,full,train,0.7528089887640449
+0.08284440272236564,full,train,0.7528089887640449
+0.08284440272236564,full,train,0.7532411408815903
+0.08307908941563014,full,train,0.7532411408815903
+0.08307908941563014,full,train,0.7549697493517719
+0.08425252288195259,full,train,0.7549697493517719
+0.08425252288195259,full,train,0.756266205704408
+0.08495658296174607,full,train,0.756266205704408
+0.08495658296174607,full,train,0.7592912705272256
+0.08589532973480404,full,train,0.7592912705272256
+0.08589532973480404,full,train,0.7605877268798618
+0.08636470312133301,full,train,0.7605877268798618
+0.08636470312133301,full,train,0.7623163353500432
+0.08659938981459751,full,train,0.7623163353500432
+0.08659938981459751,full,train,0.7631806395851339
+0.086834076507862,full,train,0.7631806395851339
+0.086834076507862,full,train,0.7640449438202247
+0.0870687632011265,full,train,0.7640449438202247
+0.0870687632011265,full,train,0.7649092480553155
+0.08730344989439098,full,train,0.7649092480553155
+0.08730344989439098,full,train,0.7653414001728609
+0.08753813658765548,full,train,0.7653414001728609
+0.08753813658765548,full,train,0.7657735522904062
+0.08777282328091997,full,train,0.7657735522904062
+0.08777282328091997,full,train,0.7662057044079515
+0.08800750997418447,full,train,0.7662057044079515
+0.08800750997418447,full,train,0.7675021607605877
+0.08824219666744895,full,train,0.7675021607605877
+0.08824219666744895,full,train,0.7679343128781331
+0.08847688336071345,full,train,0.7679343128781331
+0.08847688336071345,full,train,0.7687986171132238
+0.08871157005397794,full,train,0.7687986171132238
+0.08871157005397794,full,train,0.77009507346586
+0.08918094344050692,full,train,0.77009507346586
+0.08918094344050692,full,train,0.7705272255834054
+0.0898850035203004,full,train,0.7705272255834054
+0.0898850035203004,full,train,0.7709593777009507
+0.09035437690682939,full,train,0.7709593777009507
+0.09035437690682939,full,train,0.7713915298184961
+0.09105843698662286,full,train,0.7713915298184961
+0.09105843698662286,full,train,0.7726879861711322
+0.09152781037315184,full,train,0.7726879861711322
+0.09152781037315184,full,train,0.7757130509939498
+0.09176249706641633,full,train,0.7757130509939498
+0.09176249706641633,full,train,0.7761452031114953
+0.09199718375968083,full,train,0.7761452031114953
+0.09199718375968083,full,train,0.7765773552290406
+0.09223187045294531,full,train,0.7765773552290406
+0.09223187045294531,full,train,0.777009507346586
+0.09410936399906125,full,train,0.777009507346586
+0.09410936399906125,full,train,0.7774416594641314
+0.09434405069232575,full,train,0.7774416594641314
+0.09434405069232575,full,train,0.7787381158167676
+0.09504811077211922,full,train,0.7787381158167676
+0.09504811077211922,full,train,0.7791702679343129
+0.09575217085191269,full,train,0.7791702679343129
+0.09575217085191269,full,train,0.7813310285220397
+0.09622154423844168,full,train,0.7813310285220397
+0.09622154423844168,full,train,0.7817631806395852
+0.09692560431823516,full,train,0.7817631806395852
+0.09692560431823516,full,train,0.7830596369922213
+0.09716029101149964,full,train,0.7830596369922213
+0.09716029101149964,full,train,0.783923941227312
+0.09739497770476414,full,train,0.783923941227312
+0.09739497770476414,full,train,0.7847882454624028
+0.0988030978643511,full,train,0.7847882454624028
+0.0988030978643511,full,train,0.7852203975799481
+0.09950715794414457,full,train,0.7852203975799481
+0.09950715794414457,full,train,0.7856525496974935
+0.09974184463740905,full,train,0.7856525496974935
+0.09974184463740905,full,train,0.7865168539325843
+0.10021121802393804,full,train,0.7865168539325843
+0.10021121802393804,full,train,0.7873811581676751
+0.10044590471720254,full,train,0.7873811581676751
+0.10044590471720254,full,train,0.7878133102852204
+0.10068059141046702,full,train,0.7878133102852204
+0.10068059141046702,full,train,0.7886776145203112
+0.10091527810373152,full,train,0.7886776145203112
+0.10091527810373152,full,train,0.7895419187554019
+0.101149964796996,full,train,0.7895419187554019
+0.101149964796996,full,train,0.7899740708729472
+0.10185402487678949,full,train,0.7899740708729472
+0.10185402487678949,full,train,0.7904062229904927
+0.10232339826331847,full,train,0.7904062229904927
+0.10232339826331847,full,train,0.7929991356957649
+0.10255808495658296,full,train,0.7929991356957649
+0.10255808495658296,full,train,0.7934312878133103
+0.10279277164984746,full,train,0.7934312878133103
+0.10279277164984746,full,train,0.7942955920484011
+0.10349683172964093,full,train,0.7942955920484011
+0.10349683172964093,full,train,0.7947277441659464
+0.1044355785026989,full,train,0.7947277441659464
+0.1044355785026989,full,train,0.7964563526361279
+0.10467026519596338,full,train,0.7964563526361279
+0.10467026519596338,full,train,0.7973206568712187
+0.10537432527575687,full,train,0.7973206568712187
+0.10537432527575687,full,train,0.797752808988764
+0.10607838535555034,full,train,0.797752808988764
+0.10607838535555034,full,train,0.7994814174589455
+0.1070171321286083,full,train,0.7994814174589455
+0.1070171321286083,full,train,0.799913569576491
+0.10748650551513729,full,train,0.799913569576491
+0.10748650551513729,full,train,0.801210025929127
+0.10842525228819526,full,train,0.801210025929127
+0.10842525228819526,full,train,0.8016421780466725
+0.10889462567472424,full,train,0.8016421780466725
+0.10889462567472424,full,train,0.8020743301642178
+0.10912931236798873,full,train,0.8020743301642178
+0.10912931236798873,full,train,0.8029386343993086
+0.10936399906125323,full,train,0.8029386343993086
+0.10936399906125323,full,train,0.8033707865168539
+0.10959868575451771,full,train,0.8033707865168539
+0.10959868575451771,full,train,0.8059636992221262
+0.10983337244778221,full,train,0.8059636992221262
+0.10983337244778221,full,train,0.8094209161624892
+0.1100680591410467,full,train,0.8094209161624892
+0.1100680591410467,full,train,0.8098530682800346
+0.11053743252757568,full,train,0.8098530682800346
+0.11053743252757568,full,train,0.81028522039758
+0.11077211922084018,full,train,0.81028522039758
+0.11077211922084018,full,train,0.8107173725151253
+0.11124149260736917,full,train,0.8107173725151253
+0.11124149260736917,full,train,0.8133102852203976
+0.11147617930063365,full,train,0.8133102852203976
+0.11147617930063365,full,train,0.8159031979256698
+0.11218023938042714,full,train,0.8159031979256698
+0.11218023938042714,full,train,0.8176318063958513
+0.11264961276695612,full,train,0.8176318063958513
+0.11264961276695612,full,train,0.8180639585133967
+0.1131189861534851,full,train,0.8180639585133967
+0.1131189861534851,full,train,0.8202247191011236
+0.11335367284674959,full,train,0.8202247191011236
+0.11335367284674959,full,train,0.8206568712186689
+0.11382304623327857,full,train,0.8206568712186689
+0.11382304623327857,full,train,0.8223854796888505
+0.11405773292654306,full,train,0.8223854796888505
+0.11405773292654306,full,train,0.8232497839239412
+0.11476179300633654,full,train,0.8232497839239412
+0.11476179300633654,full,train,0.8236819360414867
+0.11499647969960103,full,train,0.8236819360414867
+0.11499647969960103,full,train,0.8249783923941227
+0.11546585308613001,full,train,0.8249783923941227
+0.11546585308613001,full,train,0.8258426966292135
+0.11570053977939451,full,train,0.8258426966292135
+0.11570053977939451,full,train,0.8262748487467588
+0.1161699131659235,full,train,0.8262748487467588
+0.1161699131659235,full,train,0.8267070008643043
+0.11640459985918798,full,train,0.8267070008643043
+0.11640459985918798,full,train,0.827571305099395
+0.11663928655245248,full,train,0.827571305099395
+0.11663928655245248,full,train,0.8288677614520311
+0.11710865993898147,full,train,0.8288677614520311
+0.11710865993898147,full,train,0.8292999135695764
+0.1187514667918329,full,train,0.8292999135695764
+0.1187514667918329,full,train,0.8297320656871219
+0.11898615348509739,full,train,0.8297320656871219
+0.11898615348509739,full,train,0.8301642178046672
+0.11922084017836189,full,train,0.8301642178046672
+0.11922084017836189,full,train,0.8327571305099395
+0.11945552687162637,full,train,0.8327571305099395
+0.11945552687162637,full,train,0.8331892826274849
+0.11969021356489087,full,train,0.8331892826274849
+0.11969021356489087,full,train,0.8336214347450303
+0.11992490025815536,full,train,0.8336214347450303
+0.11992490025815536,full,train,0.8340535868625756
+0.12039427364468434,full,train,0.8340535868625756
+0.12039427364468434,full,train,0.8349178910976663
+0.12062896033794884,full,train,0.8349178910976663
+0.12062896033794884,full,train,0.8357821953327571
+0.1220370804975358,full,train,0.8357821953327571
+0.1220370804975358,full,train,0.8370786516853933
+0.12227176719080028,full,train,0.8370786516853933
+0.12227176719080028,full,train,0.837942955920484
+0.12367988735038724,full,train,0.837942955920484
+0.12367988735038724,full,train,0.8396715643906655
+0.1246186341234452,full,train,0.8396715643906655
+0.1246186341234452,full,train,0.8401037165082109
+0.12485332081670969,full,train,0.8401037165082109
+0.12485332081670969,full,train,0.8426966292134831
+0.12555738089650317,full,train,0.8426966292134831
+0.12555738089650317,full,train,0.8435609334485739
+0.12602675428303214,full,train,0.8435609334485739
+0.12602675428303214,full,train,0.8444252376836646
+0.1272001877493546,full,train,0.8444252376836646
+0.1272001877493546,full,train,0.8452895419187554
+0.12813893452241257,full,train,0.8452895419187554
+0.12813893452241257,full,train,0.8457216940363008
+0.12884299460220605,full,train,0.8457216940363008
+0.12884299460220605,full,train,0.8461538461538461
+0.1300164280685285,full,train,0.8461538461538461
+0.1300164280685285,full,train,0.8465859982713916
+0.13025111476179302,full,train,0.8465859982713916
+0.13025111476179302,full,train,0.848314606741573
+0.13095517484158647,full,train,0.848314606741573
+0.13095517484158647,full,train,0.8496110630942092
+0.131189861534851,full,train,0.8496110630942092
+0.131189861534851,full,train,0.8509075194468453
+0.13142454822811547,full,train,0.8509075194468453
+0.13142454822811547,full,train,0.8526361279170268
+0.13259798169443793,full,train,0.8526361279170268
+0.13259798169443793,full,train,0.8530682800345721
+0.1328326683877024,full,train,0.8530682800345721
+0.1328326683877024,full,train,0.8535004321521176
+0.1333020417742314,full,train,0.8535004321521176
+0.1333020417742314,full,train,0.8556611927398444
+0.1335367284674959,full,train,0.8556611927398444
+0.1335367284674959,full,train,0.8560933448573897
+0.13447547524055387,full,train,0.8560933448573897
+0.13447547524055387,full,train,0.8565254969749352
+0.13541422201361183,full,train,0.8565254969749352
+0.13541422201361183,full,train,0.8569576490924805
+0.1363529687866698,full,train,0.8569576490924805
+0.1363529687866698,full,train,0.857389801210026
+0.1365876554799343,full,train,0.857389801210026
+0.1365876554799343,full,train,0.8578219533275713
+0.13682234217319877,full,train,0.8578219533275713
+0.13682234217319877,full,train,0.8599827139152982
+0.13752640225299226,full,train,0.8599827139152982
+0.13752640225299226,full,train,0.8604148660328436
+0.13776108894625674,full,train,0.8604148660328436
+0.13776108894625674,full,train,0.8608470181503889
+0.13846514902605023,full,train,0.8608470181503889
+0.13846514902605023,full,train,0.8617113223854796
+0.1391692091058437,full,train,0.8617113223854796
+0.1391692091058437,full,train,0.8621434745030251
+0.1394038957991082,full,train,0.8621434745030251
+0.1394038957991082,full,train,0.8625756266205704
+0.13963858249237268,full,train,0.8625756266205704
+0.13963858249237268,full,train,0.8630077787381158
+0.13987326918563717,full,train,0.8630077787381158
+0.13987326918563717,full,train,0.8634399308556612
+0.14010795587890168,full,train,0.8634399308556612
+0.14010795587890168,full,train,0.8638720829732066
+0.14081201595869514,full,train,0.8638720829732066
+0.14081201595869514,full,train,0.8643042350907519
+0.1417507627317531,full,train,0.8643042350907519
+0.1417507627317531,full,train,0.8664649956784788
+0.14292419619807556,full,train,0.8664649956784788
+0.14292419619807556,full,train,0.8673292999135696
+0.14315888289134007,full,train,0.8673292999135696
+0.14315888289134007,full,train,0.8681936041486603
+0.14339356958460456,full,train,0.8681936041486603
+0.14339356958460456,full,train,0.8686257562662058
+0.14362825627786904,full,train,0.8686257562662058
+0.14362825627786904,full,train,0.8690579083837511
+0.144567003050927,full,train,0.8690579083837511
+0.144567003050927,full,train,0.8703543647363872
+0.14550574982398498,full,train,0.8703543647363872
+0.14550574982398498,full,train,0.8707865168539326
+0.14574043651724947,full,train,0.8707865168539326
+0.14574043651724947,full,train,0.8716508210890234
+0.14691386998357192,full,train,0.8716508210890234
+0.14691386998357192,full,train,0.8720829732065687
+0.1483219901431589,full,train,0.8720829732065687
+0.1483219901431589,full,train,0.8725151253241141
+0.14879136352968786,full,train,0.8725151253241141
+0.14879136352968786,full,train,0.8729472774416595
+0.1504341703825393,full,train,0.8729472774416595
+0.1504341703825393,full,train,0.8733794295592049
+0.15090354376906828,full,train,0.8733794295592049
+0.15090354376906828,full,train,0.8738115816767502
+0.15137291715559728,full,train,0.8738115816767502
+0.15137291715559728,full,train,0.8742437337942955
+0.15160760384886177,full,train,0.8742437337942955
+0.15160760384886177,full,train,0.8751080380293863
+0.15231166392865525,full,train,0.8751080380293863
+0.15231166392865525,full,train,0.8755401901469317
+0.15278103731518422,full,train,0.8755401901469317
+0.15278103731518422,full,train,0.8759723422644771
+0.15301572400844873,full,train,0.8759723422644771
+0.15301572400844873,full,train,0.8772687986171133
+0.15512790424782916,full,train,0.8772687986171133
+0.15512790424782916,full,train,0.878133102852204
+0.15536259094109364,full,train,0.878133102852204
+0.15536259094109364,full,train,0.8789974070872947
+0.1563013377141516,full,train,0.8789974070872947
+0.1563013377141516,full,train,0.8794295592048401
+0.15677071110068058,full,train,0.8794295592048401
+0.15677071110068058,full,train,0.8811581676750216
+0.15747477118047407,full,train,0.8811581676750216
+0.15747477118047407,full,train,0.881590319792567
+0.15770945787373855,full,train,0.881590319792567
+0.15770945787373855,full,train,0.8820224719101124
+0.15864820464679652,full,train,0.8820224719101124
+0.15864820464679652,full,train,0.8824546240276577
+0.1595869514198545,full,train,0.8824546240276577
+0.1595869514198545,full,train,0.8828867761452031
+0.1600563248063835,full,train,0.8828867761452031
+0.1600563248063835,full,train,0.8837510803802938
+0.1628725651255574,full,train,0.8837510803802938
+0.1628725651255574,full,train,0.8841832324978393
+0.16334193851208637,full,train,0.8841832324978393
+0.16334193851208637,full,train,0.8846153846153846
+0.16381131189861534,full,train,0.8846153846153846
+0.16381131189861534,full,train,0.88504753673293
+0.16428068528514433,full,train,0.88504753673293
+0.16428068528514433,full,train,0.8854796888504753
+0.1647500586716733,full,train,0.8854796888504753
+0.1647500586716733,full,train,0.8863439930855661
+0.16498474536493782,full,train,0.8863439930855661
+0.16498474536493782,full,train,0.8867761452031115
+0.16568880544473127,full,train,0.8867761452031115
+0.16568880544473127,full,train,0.8872082973206569
+0.16615817883126027,full,train,0.8872082973206569
+0.16615817883126027,full,train,0.8880726015557476
+0.16662755221778924,full,train,0.8880726015557476
+0.16662755221778924,full,train,0.8889369057908384
+0.16709692560431824,full,train,0.8889369057908384
+0.16709692560431824,full,train,0.8898012100259292
+0.1678009856841117,full,train,0.8898012100259292
+0.1678009856841117,full,train,0.8902333621434745
+0.1682703590706407,full,train,0.8902333621434745
+0.1682703590706407,full,train,0.8915298184961107
+0.16850504576390518,full,train,0.8915298184961107
+0.16850504576390518,full,train,0.891961970613656
+0.16873973245716967,full,train,0.891961970613656
+0.16873973245716967,full,train,0.8928262748487468
+0.16967847923022764,full,train,0.8928262748487468
+0.16967847923022764,full,train,0.8932584269662921
+0.17085191269655012,full,train,0.8932584269662921
+0.17085191269655012,full,train,0.8936905790838375
+0.1713212860830791,full,train,0.8936905790838375
+0.1713212860830791,full,train,0.8945548833189283
+0.1734334663224595,full,train,0.8945548833189283
+0.1734334663224595,full,train,0.8949870354364736
+0.174137526402253,full,train,0.8949870354364736
+0.174137526402253,full,train,0.8954191875540191
+0.17460689978878197,full,train,0.8954191875540191
+0.17460689978878197,full,train,0.8958513396715644
+0.17507627317531096,full,train,0.8958513396715644
+0.17507627317531096,full,train,0.8962834917891098
+0.17578033325510445,full,train,0.8962834917891098
+0.17578033325510445,full,train,0.8967156439066551
+0.1764843933348979,full,train,0.8967156439066551
+0.1764843933348979,full,train,0.8971477960242005
+0.1769537667214269,full,train,0.8971477960242005
+0.1769537667214269,full,train,0.8975799481417459
+0.1771884534146914,full,train,0.8975799481417459
+0.1771884534146914,full,train,0.8980121002592912
+0.17765782680122036,full,train,0.8980121002592912
+0.17765782680122036,full,train,0.9001728608470182
+0.1793006336540718,full,train,0.9001728608470182
+0.1793006336540718,full,train,0.9006050129645635
+0.1795353203473363,full,train,0.9006050129645635
+0.1795353203473363,full,train,0.9010371650821088
+0.1797700070406008,full,train,0.9010371650821088
+0.1797700070406008,full,train,0.9014693171996543
+0.1828209340530392,full,train,0.9014693171996543
+0.1828209340530392,full,train,0.9019014693171996
+0.18399436751936166,full,train,0.9019014693171996
+0.18399436751936166,full,train,0.902333621434745
+0.1854024876789486,full,train,0.902333621434745
+0.1854024876789486,full,train,0.9027657735522904
+0.18563717437221308,full,train,0.9027657735522904
+0.18563717437221308,full,train,0.9031979256698358
+0.18681060783853556,full,train,0.9031979256698358
+0.18681060783853556,full,train,0.9040622299049266
+0.18727998122506453,full,train,0.9040622299049266
+0.18727998122506453,full,train,0.9044943820224719
+0.18774935461159353,full,train,0.9044943820224719
+0.18774935461159353,full,train,0.9049265341400173
+0.18986153485097396,full,train,0.9049265341400173
+0.18986153485097396,full,train,0.9062229904926534
+0.19009622154423844,full,train,0.9062229904926534
+0.19009622154423844,full,train,0.9066551426101987
+0.19033090823750293,full,train,0.9066551426101987
+0.19033090823750293,full,train,0.9075194468452895
+0.1912696550105609,full,train,0.9075194468452895
+0.1912696550105609,full,train,0.907951598962835
+0.1917390283970899,full,train,0.907951598962835
+0.1917390283970899,full,train,0.9083837510803803
+0.19267777517014786,full,train,0.9083837510803803
+0.19267777517014786,full,train,0.9088159031979257
+0.19291246186341235,full,train,0.9088159031979257
+0.19291246186341235,full,train,0.909248055315471
+0.19361652194320583,full,train,0.909248055315471
+0.19361652194320583,full,train,0.9101123595505618
+0.19385120863647032,full,train,0.9101123595505618
+0.19385120863647032,full,train,0.9122731201382887
+0.19502464210279277,full,train,0.9122731201382887
+0.19502464210279277,full,train,0.9127052722558341
+0.19572870218258626,full,train,0.9127052722558341
+0.19572870218258626,full,train,0.9131374243733794
+0.19596338887585074,full,train,0.9131374243733794
+0.19596338887585074,full,train,0.9135695764909249
+0.1964327622623797,full,train,0.9135695764909249
+0.1964327622623797,full,train,0.9140017286084702
+0.1969021356489087,full,train,0.9140017286084702
+0.1969021356489087,full,train,0.9148660328435609
+0.19784088242196668,full,train,0.9148660328435609
+0.19784088242196668,full,train,0.9152981849611063
+0.19854494250176016,full,train,0.9152981849611063
+0.19854494250176016,full,train,0.9157303370786517
+0.19877962919502465,full,train,0.9157303370786517
+0.19877962919502465,full,train,0.916162489196197
+0.19924900258155362,full,train,0.916162489196197
+0.19924900258155362,full,train,0.9165946413137425
+0.1999530626613471,full,train,0.9165946413137425
+0.1999530626613471,full,train,0.9174589455488332
+0.20042243604787607,full,train,0.9174589455488332
+0.20042243604787607,full,train,0.918323249783924
+0.20112649612766956,full,train,0.918323249783924
+0.20112649612766956,full,train,0.9200518582541054
+0.20136118282093404,full,train,0.9200518582541054
+0.20136118282093404,full,train,0.9204840103716508
+0.20323867636704998,full,train,0.9204840103716508
+0.20323867636704998,full,train,0.9209161624891962
+0.20370804975357898,full,train,0.9209161624891962
+0.20370804975357898,full,train,0.9222126188418324
+0.2053508566064304,full,train,0.9222126188418324
+0.2053508566064304,full,train,0.9230769230769231
+0.20628960337948837,full,train,0.9230769230769231
+0.20628960337948837,full,train,0.9235090751944685
+0.20722835015254634,full,train,0.9235090751944685
+0.20722835015254634,full,train,0.9239412273120138
+0.20769772353907534,full,train,0.9239412273120138
+0.20769772353907534,full,train,0.92523768366465
+0.2084017836188688,full,train,0.92523768366465
+0.2084017836188688,full,train,0.9265341400172861
+0.21051396385824925,full,train,0.9265341400172861
+0.21051396385824925,full,train,0.9273984442523768
+0.2116873973245717,full,train,0.9273984442523768
+0.2116873973245717,full,train,0.9282627484874676
+0.21239145740436519,full,train,0.9282627484874676
+0.21239145740436519,full,train,0.9286949006050129
+0.21286083079089416,full,train,0.9286949006050129
+0.21286083079089416,full,train,0.9291270527225584
+0.21309551748415864,full,train,0.9291270527225584
+0.21309551748415864,full,train,0.9295592048401037
+0.21356489087068764,full,train,0.9295592048401037
+0.21356489087068764,full,train,0.9299913569576491
+0.21379957756395213,full,train,0.9299913569576491
+0.21379957756395213,full,train,0.9304235090751944
+0.2142689509504811,full,train,0.9304235090751944
+0.2142689509504811,full,train,0.9308556611927399
+0.2145036376437456,full,train,0.9308556611927399
+0.2145036376437456,full,train,0.9312878133102852
+0.21567707111006806,full,train,0.9312878133102852
+0.21567707111006806,full,train,0.9317199654278306
+0.21591175780333255,full,train,0.9317199654278306
+0.21591175780333255,full,train,0.932152117545376
+0.21661581788312603,full,train,0.932152117545376
+0.21661581788312603,full,train,0.9325842696629213
+0.217085191269655,full,train,0.9325842696629213
+0.217085191269655,full,train,0.9330164217804667
+0.2177892513494485,full,train,0.9330164217804667
+0.2177892513494485,full,train,0.9334485738980121
+0.21943205820229994,full,train,0.9334485738980121
+0.21943205820229994,full,train,0.9338807260155575
+0.2206054916686224,full,train,0.9338807260155575
+0.2206054916686224,full,train,0.9343128781331028
+0.22271767190800282,full,train,0.9343128781331028
+0.22271767190800282,full,train,0.9351771823681936
+0.2229523586012673,full,train,0.9351771823681936
+0.2229523586012673,full,train,0.935609334485739
+0.2234217319877963,full,train,0.935609334485739
+0.2234217319877963,full,train,0.9360414866032843
+0.22529922553391224,full,train,0.9360414866032843
+0.22529922553391224,full,train,0.9364736387208298
+0.22553391222717672,full,train,0.9364736387208298
+0.22553391222717672,full,train,0.9373379429559204
+0.22975827270593757,full,train,0.9373379429559204
+0.22975827270593757,full,train,0.9377700950734659
+0.23022764609246657,full,train,0.9377700950734659
+0.23022764609246657,full,train,0.9382022471910112
+0.23046233278573106,full,train,0.9382022471910112
+0.23046233278573106,full,train,0.9394987035436474
+0.23398263318469842,full,train,0.9394987035436474
+0.23398263318469842,full,train,0.9399308556611927
+0.23421731987796293,full,train,0.9399308556611927
+0.23421731987796293,full,train,0.9403630077787382
+0.23609481342407884,full,train,0.9403630077787382
+0.23609481342407884,full,train,0.9407951598962835
+0.2375029335836658,full,train,0.9407951598962835
+0.2375029335836658,full,train,0.9420916162489196
+0.24149260736916217,full,train,0.9420916162489196
+0.24149260736916217,full,train,0.942523768366465
+0.24196198075569114,full,train,0.942523768366465
+0.24196198075569114,full,train,0.9429559204840103
+0.24219666744895565,full,train,0.9429559204840103
+0.24219666744895565,full,train,0.9433880726015558
+0.24383947430180708,full,train,0.9433880726015558
+0.24383947430180708,full,train,0.9442523768366465
+0.24806383478056795,full,train,0.9442523768366465
+0.24806383478056795,full,train,0.9451166810717373
+0.24829852147383244,full,train,0.9451166810717373
+0.24829852147383244,full,train,0.9455488331892826
+0.24970664163341938,full,train,0.9455488331892826
+0.24970664163341938,full,train,0.945980985306828
+0.24994132832668386,full,train,0.945980985306828
+0.24994132832668386,full,train,0.9464131374243734
+0.25017601501994835,full,train,0.9464131374243734
+0.25017601501994835,full,train,0.9468452895419187
+0.25111476179300635,full,train,0.9468452895419187
+0.25111476179300635,full,train,0.9472774416594641
+0.25134944848627083,full,train,0.9472774416594641
+0.25134944848627083,full,train,0.9477095937770095
+0.2515841351795353,full,train,0.9477095937770095
+0.2515841351795353,full,train,0.9481417458945549
+0.2529922553391223,full,train,0.9481417458945549
+0.2529922553391223,full,train,0.9485738980121002
+0.25369631541891574,full,train,0.9485738980121002
+0.25369631541891574,full,train,0.9490060501296457
+0.2551044355785027,full,train,0.9490060501296457
+0.2551044355785027,full,train,0.949438202247191
+0.2555738089650317,full,train,0.949438202247191
+0.2555738089650317,full,train,0.9498703543647364
+0.25909410936399907,full,train,0.9498703543647364
+0.25909410936399907,full,train,0.9503025064822818
+0.25932879605726356,full,train,0.9503025064822818
+0.25932879605726356,full,train,0.9507346585998271
+0.261440976296644,full,train,0.9507346585998271
+0.261440976296644,full,train,0.9511668107173725
+0.2637878432292889,full,train,0.9511668107173725
+0.2637878432292889,full,train,0.9515989628349178
+0.2659000234686693,full,train,0.9515989628349178
+0.2659000234686693,full,train,0.9520311149524633
+0.2673081436282563,full,train,0.9520311149524633
+0.2673081436282563,full,train,0.9524632670700086
+0.26754283032152076,full,train,0.9524632670700086
+0.26754283032152076,full,train,0.952895419187554
+0.2682468904013142,full,train,0.952895419187554
+0.2682468904013142,full,train,0.9533275713050994
+0.2694203238676367,full,train,0.9533275713050994
+0.2694203238676367,full,train,0.9537597234226448
+0.27012438394743016,full,train,0.9537597234226448
+0.27012438394743016,full,train,0.9541918755401901
+0.2703590706406947,full,train,0.9541918755401901
+0.2703590706406947,full,train,0.9546240276577356
+0.2705937573339592,full,train,0.9546240276577356
+0.2705937573339592,full,train,0.9550561797752809
+0.2715325041070171,full,train,0.9550561797752809
+0.2715325041070171,full,train,0.9554883318928262
+0.2724712508800751,full,train,0.9554883318928262
+0.2724712508800751,full,train,0.9559204840103717
+0.27364468434639755,full,train,0.9559204840103717
+0.27364468434639755,full,train,0.956352636127917
+0.27458343111945555,full,train,0.956352636127917
+0.27458343111945555,full,train,0.9567847882454624
+0.27575686458577797,full,train,0.9567847882454624
+0.27575686458577797,full,train,0.9572169403630078
+0.2764609246655715,full,train,0.9572169403630078
+0.2764609246655715,full,train,0.9576490924805532
+0.2785731049049519,full,train,0.9576490924805532
+0.2785731049049519,full,train,0.9580812445980985
+0.28068528514433233,full,train,0.9580812445980985
+0.28068528514433233,full,train,0.958513396715644
+0.2823280919971838,full,train,0.958513396715644
+0.2823280919971838,full,train,0.9589455488331893
+0.28303215207697724,full,train,0.9589455488331893
+0.28303215207697724,full,train,0.95980985306828
+0.28772588594226706,full,train,0.95980985306828
+0.28772588594226706,full,train,0.9602420051858254
+0.29007275287491197,full,train,0.9602420051858254
+0.29007275287491197,full,train,0.9615384615384616
+0.2950011734334663,full,train,0.9615384615384616
+0.2950011734334663,full,train,0.9619706136560069
+0.2954705468199953,full,train,0.9619706136560069
+0.2954705468199953,full,train,0.9624027657735523
+0.29593992020652427,full,train,0.9624027657735523
+0.29593992020652427,full,train,0.9628349178910977
+0.2964092935930533,full,train,0.9628349178910977
+0.2964092935930533,full,train,0.9632670700086431
+0.29805210044590474,full,train,0.9632670700086431
+0.29805210044590474,full,train,0.9636992221261884
+0.2987561605256982,full,train,0.9636992221261884
+0.2987561605256982,full,train,0.9641313742437337
+0.29969490729875614,full,train,0.9641313742437337
+0.29969490729875614,full,train,0.9645635263612792
+0.30063365407181414,full,train,0.9645635263612792
+0.30063365407181414,full,train,0.9649956784788245
+0.3013377141516076,full,train,0.9649956784788245
+0.3013377141516076,full,train,0.9654278305963699
+0.30298052100445905,full,train,0.9654278305963699
+0.30298052100445905,full,train,0.9658599827139153
+0.3074395681764844,full,train,0.9658599827139153
+0.3074395681764844,full,train,0.9662921348314607
+0.30884768833607135,full,train,0.9662921348314607
+0.30884768833607135,full,train,0.966724286949006
+0.31142924196198074,full,train,0.966724286949006
+0.31142924196198074,full,train,0.9671564390665515
+0.31471485566768365,full,train,0.9671564390665515
+0.31471485566768365,full,train,0.9675885911840968
+0.3154189157474771,full,train,0.9675885911840968
+0.3154189157474771,full,train,0.9680207433016422
+0.31588828913400613,full,train,0.9680207433016422
+0.31588828913400613,full,train,0.9684528954191876
+0.31964327622623795,full,train,0.9684528954191876
+0.31964327622623795,full,train,0.9688850475367329
+0.3233982633184698,full,train,0.9688850475367329
+0.3233982633184698,full,train,0.9693171996542783
+0.32527575686458576,full,train,0.9693171996542783
+0.32527575686458576,full,train,0.9697493517718236
+0.3259798169443793,full,train,0.9697493517718236
+0.3259798169443793,full,train,0.9701815038893691
+0.32621450363764376,full,train,0.9701815038893691
+0.32621450363764376,full,train,0.9706136560069144
+0.32644919033090825,full,train,0.9706136560069144
+0.32644919033090825,full,train,0.9714779602420052
+0.32856137057028867,full,train,0.9714779602420052
+0.32856137057028867,full,train,0.9719101123595506
+0.3292654306500821,full,train,0.9719101123595506
+0.3292654306500821,full,train,0.9727744165946414
+0.32996949072987564,full,train,0.9727744165946414
+0.32996949072987564,full,train,0.9732065687121867
+0.33231635766252055,full,train,0.9732065687121867
+0.33231635766252055,full,train,0.973638720829732
+0.33466322459516545,full,train,0.973638720829732
+0.33466322459516545,full,train,0.9740708729472775
+0.33747946491433933,full,train,0.9740708729472775
+0.33747946491433933,full,train,0.9745030250648228
+0.33794883830086836,full,train,0.9745030250648228
+0.33794883830086836,full,train,0.9749351771823682
+0.33959164515371976,full,train,0.9749351771823682
+0.33959164515371976,full,train,0.9753673292999135
+0.34029570523351327,full,train,0.9753673292999135
+0.34029570523351327,full,train,0.975799481417459
+0.3414691386998357,full,train,0.975799481417459
+0.3414691386998357,full,train,0.9762316335350043
+0.3447547524055386,full,train,0.9762316335350043
+0.3447547524055386,full,train,0.9766637856525497
+0.34639755925839005,full,train,0.9766637856525497
+0.34639755925839005,full,train,0.9770959377700951
+0.35203003989673787,full,train,0.9770959377700951
+0.35203003989673787,full,train,0.9775280898876404
+0.35249941328326684,full,train,0.9775280898876404
+0.35249941328326684,full,train,0.9779602420051858
+0.3532034733630603,full,train,0.9779602420051858
+0.3532034733630603,full,train,0.9783923941227312
+0.3534381600563248,full,train,0.9783923941227312
+0.3534381600563248,full,train,0.9788245462402766
+0.3536728467495893,full,train,0.9788245462402766
+0.3536728467495893,full,train,0.9792566983578219
+0.362121567707111,full,train,0.9792566983578219
+0.362121567707111,full,train,0.9796888504753674
+0.37714151607603846,full,train,0.9796888504753674
+0.37714151607603846,full,train,0.9801210025929127
+0.37925369631541894,full,train,0.9801210025929127
+0.37925369631541894,full,train,0.9805531547104581
+0.3797230697019479,full,train,0.9805531547104581
+0.3797230697019479,full,train,0.9809853068280034
+0.3801924430884769,full,train,0.9809853068280034
+0.3801924430884769,full,train,0.9814174589455489
+0.3853555503402957,full,train,0.9814174589455489
+0.3853555503402957,full,train,0.9818496110630942
+0.38652898380661815,full,train,0.9818496110630942
+0.38652898380661815,full,train,0.9822817631806395
+0.3891105374325276,full,train,0.9822817631806395
+0.3891105374325276,full,train,0.982713915298185
+0.39216146444496597,full,train,0.982713915298185
+0.39216146444496597,full,train,0.9831460674157303
+0.4010795587890167,full,train,0.9831460674157303
+0.4010795587890167,full,train,0.9835782195332757
+0.4013142454822812,full,train,0.9835782195332757
+0.4013142454822812,full,train,0.9840103716508211
+0.40201830556207463,full,train,0.9840103716508211
+0.40201830556207463,full,train,0.9844425237683665
+0.4022529922553391,full,train,0.9844425237683665
+0.4022529922553391,full,train,0.9848746758859118
+0.4236094813424079,full,train,0.9848746758859118
+0.4236094813424079,full,train,0.9853068280034573
+0.4294766486740202,full,train,0.9853068280034573
+0.4294766486740202,full,train,0.9857389801210026
+0.4320582022999296,full,train,0.9857389801210026
+0.4320582022999296,full,train,0.986171132238548
+0.4348744426191035,full,train,0.986171132238548
+0.4348744426191035,full,train,0.9866032843560933
+0.43816005632480637,full,train,0.9866032843560933
+0.43816005632480637,full,train,0.9870354364736387
+0.44168035672377376,full,train,0.9870354364736387
+0.44168035672377376,full,train,0.9874675885911841
+0.4670265195963389,full,train,0.9874675885911841
+0.4670265195963389,full,train,0.9878997407087294
+0.4740671203942736,full,train,0.9878997407087294
+0.4740671203942736,full,train,0.9883318928262749
+0.4867402018305562,full,train,0.9883318928262749
+0.4867402018305562,full,train,0.9887640449438202
+0.48838300868340767,full,train,0.9887640449438202
+0.48838300868340767,full,train,0.9891961970613656
+0.5127904247829148,full,train,0.9891961970613656
+0.5127904247829148,full,train,0.989628349178911
+0.5144332316357663,full,train,0.989628349178911
+0.5144332316357663,full,train,0.9900605012964564
+0.5217085191269655,full,train,0.9900605012964564
+0.5217085191269655,full,train,0.9904926534140017
+0.5524524759446139,full,train,0.9904926534140017
+0.5524524759446139,full,train,0.9909248055315472
+0.5545646561839944,full,train,0.9909248055315472
+0.5545646561839944,full,train,0.9913569576490925
+0.5681764843933349,full,train,0.9913569576490925
+0.5681764843933349,full,train,0.9917891097666378
+0.5780333255104435,full,train,0.9917891097666378
+0.5780333255104435,full,train,0.9922212618841832
+0.5979816944379254,full,train,0.9922212618841832
+0.5979816944379254,full,train,0.9926534140017286
+0.608777282328092,full,train,0.9926534140017286
+0.608777282328092,full,train,0.993085566119274
+0.6111241492607369,full,train,0.993085566119274
+0.6111241492607369,full,train,0.9935177182368193
+0.621685050457639,full,train,0.9935177182368193
+0.621685050457639,full,train,0.9939498703543648
+0.6324806383478057,full,train,0.9939498703543648
+0.6324806383478057,full,train,0.9943820224719101
+0.6550105609011969,full,train,0.9943820224719101
+0.6550105609011969,full,train,0.9948141745894555
+0.6728467495892982,full,train,0.9948141745894555
+0.6728467495892982,full,train,0.9952463267070009
+0.6911523116639287,full,train,0.9952463267070009
+0.6911523116639287,full,train,0.9956784788245462
+0.7019478995540953,full,train,0.9956784788245462
+0.7019478995540953,full,train,0.9961106309420916
+0.7209575217085191,full,train,0.9961106309420916
+0.7209575217085191,full,train,0.996542783059637
+0.7308143628256278,full,train,0.996542783059637
+0.7308143628256278,full,train,0.9969749351771824
+0.7749354611593523,full,train,0.9969749351771824
+0.7749354611593523,full,train,0.9974070872947277
+0.7836188688101384,full,train,0.9974070872947277
+0.7836188688101384,full,train,0.9978392394122731
+0.7988735038723305,full,train,0.9978392394122731
+0.7988735038723305,full,train,0.9982713915298185
+0.8528514433231635,full,train,0.9982713915298185
+0.8528514433231635,full,train,0.9987035436473639
+0.929359305327388,full,train,0.9987035436473639
+0.929359305327388,full,train,0.9991356957649092
+0.9434405069232574,full,train,0.9991356957649092
+0.9434405069232574,full,train,0.9995678478824547
+0.9443792536963154,full,train,0.9995678478824547
+0.9443792536963154,full,train,1.0
+1.0,full,train,1.0
+0.0,expressions,test,0.0
+0.002183406113537118,expressions,test,0.0
+0.002183406113537118,expressions,test,0.03663003663003663
+0.004366812227074236,expressions,test,0.03663003663003663
+0.004366812227074236,expressions,test,0.10256410256410256
+0.006550218340611353,expressions,test,0.10256410256410256
+0.006550218340611353,expressions,test,0.15384615384615385
+0.008733624454148471,expressions,test,0.15384615384615385
+0.008733624454148471,expressions,test,0.18681318681318682
+0.013100436681222707,expressions,test,0.18681318681318682
+0.013100436681222707,expressions,test,0.19413919413919414
+0.015283842794759825,expressions,test,0.19413919413919414
+0.015283842794759825,expressions,test,0.23443223443223443
+0.017467248908296942,expressions,test,0.23443223443223443
+0.017467248908296942,expressions,test,0.304029304029304
+0.019650655021834062,expressions,test,0.304029304029304
+0.019650655021834062,expressions,test,0.32234432234432236
+0.021834061135371178,expressions,test,0.32234432234432236
+0.021834061135371178,expressions,test,0.32967032967032966
+0.024017467248908297,expressions,test,0.32967032967032966
+0.024017467248908297,expressions,test,0.3516483516483517
+0.026200873362445413,expressions,test,0.3516483516483517
+0.026200873362445413,expressions,test,0.358974358974359
+0.028384279475982533,expressions,test,0.358974358974359
+0.028384279475982533,expressions,test,0.3882783882783883
+0.03056768558951965,expressions,test,0.3882783882783883
+0.03056768558951965,expressions,test,0.3992673992673993
+0.03275109170305677,expressions,test,0.3992673992673993
+0.03275109170305677,expressions,test,0.5054945054945055
+0.03711790393013101,expressions,test,0.5054945054945055
+0.03711790393013101,expressions,test,0.5201465201465202
+0.039301310043668124,expressions,test,0.5201465201465202
+0.039301310043668124,expressions,test,0.5494505494505495
+0.04148471615720524,expressions,test,0.5494505494505495
+0.04148471615720524,expressions,test,0.5531135531135531
+0.043668122270742356,expressions,test,0.5531135531135531
+0.043668122270742356,expressions,test,0.5787545787545788
+0.05240174672489083,expressions,test,0.5787545787545788
+0.05240174672489083,expressions,test,0.5934065934065934
+0.05458515283842795,expressions,test,0.5934065934065934
+0.05458515283842795,expressions,test,0.6007326007326007
+0.056768558951965066,expressions,test,0.6007326007326007
+0.056768558951965066,expressions,test,0.6043956043956044
+0.05895196506550218,expressions,test,0.6043956043956044
+0.05895196506550218,expressions,test,0.6263736263736264
+0.0611353711790393,expressions,test,0.6263736263736264
+0.0611353711790393,expressions,test,0.6446886446886447
+0.06331877729257641,expressions,test,0.6446886446886447
+0.06331877729257641,expressions,test,0.6666666666666666
+0.06550218340611354,expressions,test,0.6666666666666666
+0.06550218340611354,expressions,test,0.6776556776556777
+0.06768558951965066,expressions,test,0.6776556776556777
+0.06768558951965066,expressions,test,0.6813186813186813
+0.06986899563318777,expressions,test,0.6813186813186813
+0.06986899563318777,expressions,test,0.684981684981685
+0.07205240174672489,expressions,test,0.684981684981685
+0.07205240174672489,expressions,test,0.6923076923076923
+0.07423580786026202,expressions,test,0.6923076923076923
+0.07423580786026202,expressions,test,0.6959706959706959
+0.07641921397379912,expressions,test,0.6959706959706959
+0.07641921397379912,expressions,test,0.7106227106227107
+0.07860262008733625,expressions,test,0.7106227106227107
+0.07860262008733625,expressions,test,0.717948717948718
+0.08078602620087336,expressions,test,0.717948717948718
+0.08078602620087336,expressions,test,0.7216117216117216
+0.08296943231441048,expressions,test,0.7216117216117216
+0.08296943231441048,expressions,test,0.7289377289377289
+0.09170305676855896,expressions,test,0.7289377289377289
+0.09170305676855896,expressions,test,0.73992673992674
+0.09388646288209607,expressions,test,0.73992673992674
+0.09388646288209607,expressions,test,0.7472527472527473
+0.09606986899563319,expressions,test,0.7472527472527473
+0.09606986899563319,expressions,test,0.7509157509157509
+0.0982532751091703,expressions,test,0.7509157509157509
+0.0982532751091703,expressions,test,0.7545787545787546
+0.10262008733624454,expressions,test,0.7545787545787546
+0.10262008733624454,expressions,test,0.7728937728937729
+0.10480349344978165,expressions,test,0.7728937728937729
+0.10480349344978165,expressions,test,0.7765567765567766
+0.10698689956331878,expressions,test,0.7765567765567766
+0.10698689956331878,expressions,test,0.7802197802197802
+0.1091703056768559,expressions,test,0.7802197802197802
+0.1091703056768559,expressions,test,0.7948717948717948
+0.11135371179039301,expressions,test,0.7948717948717948
+0.11135371179039301,expressions,test,0.7985347985347986
+0.12008733624454149,expressions,test,0.7985347985347986
+0.12008733624454149,expressions,test,0.8205128205128205
+0.12663755458515283,expressions,test,0.8205128205128205
+0.12663755458515283,expressions,test,0.8315018315018315
+0.12882096069868995,expressions,test,0.8315018315018315
+0.12882096069868995,expressions,test,0.8424908424908425
+0.1331877729257642,expressions,test,0.8424908424908425
+0.1331877729257642,expressions,test,0.8461538461538461
+0.13973799126637554,expressions,test,0.8461538461538461
+0.13973799126637554,expressions,test,0.8498168498168498
+0.14192139737991266,expressions,test,0.8498168498168498
+0.14192139737991266,expressions,test,0.8534798534798534
+0.15065502183406113,expressions,test,0.8534798534798534
+0.15065502183406113,expressions,test,0.8571428571428571
+0.15938864628820962,expressions,test,0.8571428571428571
+0.15938864628820962,expressions,test,0.8608058608058609
+0.1615720524017467,expressions,test,0.8608058608058609
+0.1615720524017467,expressions,test,0.8681318681318682
+0.16375545851528384,expressions,test,0.8681318681318682
+0.16375545851528384,expressions,test,0.8791208791208791
+0.17685589519650655,expressions,test,0.8791208791208791
+0.17685589519650655,expressions,test,0.8901098901098901
+0.1812227074235808,expressions,test,0.8901098901098901
+0.1812227074235808,expressions,test,0.8974358974358975
+0.18340611353711792,expressions,test,0.8974358974358975
+0.18340611353711792,expressions,test,0.9010989010989011
+0.18777292576419213,expressions,test,0.9010989010989011
+0.18777292576419213,expressions,test,0.9084249084249084
+0.18995633187772926,expressions,test,0.9084249084249084
+0.18995633187772926,expressions,test,0.9157509157509157
+0.1965065502183406,expressions,test,0.9157509157509157
+0.1965065502183406,expressions,test,0.9194139194139194
+0.2096069868995633,expressions,test,0.9194139194139194
+0.2096069868995633,expressions,test,0.9267399267399268
+0.21615720524017468,expressions,test,0.9267399267399268
+0.21615720524017468,expressions,test,0.9304029304029304
+0.22489082969432314,expressions,test,0.9304029304029304
+0.22489082969432314,expressions,test,0.9340659340659341
+0.2292576419213974,expressions,test,0.9340659340659341
+0.2292576419213974,expressions,test,0.9377289377289377
+0.2314410480349345,expressions,test,0.9377289377289377
+0.2314410480349345,expressions,test,0.9413919413919414
+0.23799126637554585,expressions,test,0.9413919413919414
+0.23799126637554585,expressions,test,0.945054945054945
+0.2423580786026201,expressions,test,0.945054945054945
+0.2423580786026201,expressions,test,0.9560439560439561
+0.2445414847161572,expressions,test,0.9560439560439561
+0.2445414847161572,expressions,test,0.9597069597069597
+0.26419213973799127,expressions,test,0.9597069597069597
+0.26419213973799127,expressions,test,0.9633699633699634
+0.2794759825327511,expressions,test,0.9633699633699634
+0.2794759825327511,expressions,test,0.967032967032967
+0.29694323144104806,expressions,test,0.967032967032967
+0.29694323144104806,expressions,test,0.9706959706959707
+0.3056768558951965,expressions,test,0.9706959706959707
+0.3056768558951965,expressions,test,0.9743589743589743
+0.39082969432314413,expressions,test,0.9743589743589743
+0.39082969432314413,expressions,test,0.978021978021978
+0.4192139737991266,expressions,test,0.978021978021978
+0.4192139737991266,expressions,test,0.9816849816849816
+0.43013100436681223,expressions,test,0.9816849816849816
+0.43013100436681223,expressions,test,0.9853479853479854
+0.5502183406113537,expressions,test,0.9853479853479854
+0.5502183406113537,expressions,test,0.989010989010989
+0.7074235807860262,expressions,test,0.989010989010989
+0.7074235807860262,expressions,test,0.9926739926739927
+0.7379912663755459,expressions,test,0.9926739926739927
+0.7379912663755459,expressions,test,0.9963369963369964
+0.8755458515283843,expressions,test,0.9963369963369964
+0.8755458515283843,expressions,test,1.0
+1.0,expressions,test,1.0
+0.0,expressions,train,0.0
+0.0002346866932644919,expressions,train,0.0
+0.0002346866932644919,expressions,train,0.0012964563526361278
+0.0004693733865289838,expressions,train,0.0012964563526361278
+0.0004693733865289838,expressions,train,0.007346585998271392
+0.0007040600797934757,expressions,train,0.007346585998271392
+0.0007040600797934757,expressions,train,0.013828867761452032
+0.0009387467730579676,expressions,train,0.013828867761452032
+0.0009387467730579676,expressions,train,0.01728608470181504
+0.0011734334663224596,expressions,train,0.01728608470181504
+0.0011734334663224596,expressions,train,0.01901469317199654
+0.0014081201595869514,expressions,train,0.01901469317199654
+0.0014081201595869514,expressions,train,0.028522039757994815
+0.0016428068528514432,expressions,train,0.028522039757994815
+0.0016428068528514432,expressions,train,0.03025064822817632
+0.0018774935461159353,expressions,train,0.03025064822817632
+0.0018774935461159353,expressions,train,0.038461538461538464
+0.0021121802393804273,expressions,train,0.038461538461538464
+0.0021121802393804273,expressions,train,0.04407951598962835
+0.002346866932644919,expressions,train,0.04407951598962835
+0.002346866932644919,expressions,train,0.04969749351771824
+0.002581553625909411,expressions,train,0.04969749351771824
+0.002581553625909411,expressions,train,0.05445116681071737
+0.002816240319173903,expressions,train,0.05445116681071737
+0.002816240319173903,expressions,train,0.059636992221261884
+0.0030509270124383947,expressions,train,0.059636992221261884
+0.0030509270124383947,expressions,train,0.06050129645635264
+0.0035203003989673787,expressions,train,0.06050129645635264
+0.0035203003989673787,expressions,train,0.06482281763180639
+0.0037549870922318706,expressions,train,0.06482281763180639
+0.0037549870922318706,expressions,train,0.08167675021607605
+0.004224360478760855,expressions,train,0.08167675021607605
+0.004224360478760855,expressions,train,0.0898876404494382
+0.004459047172025346,expressions,train,0.0898876404494382
+0.004459047172025346,expressions,train,0.09420916162489196
+0.004693733865289838,expressions,train,0.09420916162489196
+0.004693733865289838,expressions,train,0.09939498703543648
+0.00492842055855433,expressions,train,0.09939498703543648
+0.00492842055855433,expressions,train,0.10285220397579949
+0.005163107251818822,expressions,train,0.10285220397579949
+0.005163107251818822,expressions,train,0.10847018150388937
+0.005397793945083313,expressions,train,0.10847018150388937
+0.005397793945083313,expressions,train,0.10933448573898012
+0.005632480638347806,expressions,train,0.10933448573898012
+0.005632480638347806,expressions,train,0.11279170267934313
+0.005867167331612298,expressions,train,0.11279170267934313
+0.005867167331612298,expressions,train,0.11711322385479689
+0.006101854024876789,expressions,train,0.11711322385479689
+0.006101854024876789,expressions,train,0.12013828867761452
+0.0063365407181412816,expressions,train,0.12013828867761452
+0.0063365407181412816,expressions,train,0.12316335350043216
+0.006571227411405773,expressions,train,0.12316335350043216
+0.006571227411405773,expressions,train,0.12878133102852204
+0.006805914104670265,expressions,train,0.12878133102852204
+0.006805914104670265,expressions,train,0.1313742437337943
+0.0070406007979347575,expressions,train,0.1313742437337943
+0.0070406007979347575,expressions,train,0.13526361279170268
+0.007275287491199249,expressions,train,0.13526361279170268
+0.007275287491199249,expressions,train,0.13958513396715644
+0.007509974184463741,expressions,train,0.13958513396715644
+0.007509974184463741,expressions,train,0.1512532411408816
+0.0077446608777282325,expressions,train,0.1512532411408816
+0.0077446608777282325,expressions,train,0.16248919619706137
+0.007979347570992725,expressions,train,0.16248919619706137
+0.007979347570992725,expressions,train,0.1633535004321521
+0.008214034264257217,expressions,train,0.1633535004321521
+0.008214034264257217,expressions,train,0.165514261019879
+0.00844872095752171,expressions,train,0.165514261019879
+0.00844872095752171,expressions,train,0.1694036300777874
+0.0086834076507862,expressions,train,0.1694036300777874
+0.0086834076507862,expressions,train,0.1707000864304235
+0.008918094344050692,expressions,train,0.1707000864304235
+0.008918094344050692,expressions,train,0.17329299913569576
+0.009387467730579677,expressions,train,0.17329299913569576
+0.009387467730579677,expressions,train,0.1763180639585134
+0.009622154423844167,expressions,train,0.1763180639585134
+0.009622154423844167,expressions,train,0.17761452031114952
+0.00985684111710866,expressions,train,0.17761452031114952
+0.00985684111710866,expressions,train,0.1853932584269663
+0.010091527810373152,expressions,train,0.1853932584269663
+0.010091527810373152,expressions,train,0.19230769230769232
+0.010560901196902136,expressions,train,0.19230769230769232
+0.010560901196902136,expressions,train,0.20959377700950735
+0.010795587890166627,expressions,train,0.20959377700950735
+0.010795587890166627,expressions,train,0.21002592912705273
+0.011030274583431119,expressions,train,0.21002592912705273
+0.011030274583431119,expressions,train,0.2121866897147796
+0.011264961276695611,expressions,train,0.2121866897147796
+0.011264961276695611,expressions,train,0.2143474503025065
+0.011499647969960104,expressions,train,0.2143474503025065
+0.011499647969960104,expressions,train,0.21521175453759722
+0.011734334663224596,expressions,train,0.21521175453759722
+0.011734334663224596,expressions,train,0.22082973206568712
+0.011969021356489086,expressions,train,0.22082973206568712
+0.011969021356489086,expressions,train,0.22342264477095938
+0.012438394743018071,expressions,train,0.22342264477095938
+0.012438394743018071,expressions,train,0.22428694900605012
+0.012673081436282563,expressions,train,0.22428694900605012
+0.012673081436282563,expressions,train,0.23120138288677614
+0.012907768129547055,expressions,train,0.23120138288677614
+0.012907768129547055,expressions,train,0.23336214347450301
+0.013142454822811546,expressions,train,0.23336214347450301
+0.013142454822811546,expressions,train,0.23465859982713916
+0.013377141516076038,expressions,train,0.23465859982713916
+0.013377141516076038,expressions,train,0.23638720829732066
+0.01361182820934053,expressions,train,0.23638720829732066
+0.01361182820934053,expressions,train,0.23725151253241142
+0.013846514902605023,expressions,train,0.23725151253241142
+0.013846514902605023,expressions,train,0.2428694900605013
+0.014081201595869515,expressions,train,0.2428694900605013
+0.014081201595869515,expressions,train,0.24503025064822817
+0.014315888289134006,expressions,train,0.24503025064822817
+0.014315888289134006,expressions,train,0.24589455488331893
+0.014550574982398498,expressions,train,0.24589455488331893
+0.014550574982398498,expressions,train,0.24719101123595505
+0.01478526167566299,expressions,train,0.24719101123595505
+0.01478526167566299,expressions,train,0.25280898876404495
+0.015019948368927482,expressions,train,0.25280898876404495
+0.015019948368927482,expressions,train,0.2536732929991357
+0.015254635062191975,expressions,train,0.2536732929991357
+0.015254635062191975,expressions,train,0.2610198789974071
+0.015489321755456465,expressions,train,0.2610198789974071
+0.015489321755456465,expressions,train,0.26188418323249785
+0.015724008448720957,expressions,train,0.26188418323249785
+0.015724008448720957,expressions,train,0.2636127917026793
+0.01595869514198545,expressions,train,0.2636127917026793
+0.01595869514198545,expressions,train,0.27095937770095074
+0.016193381835249942,expressions,train,0.27095937770095074
+0.016193381835249942,expressions,train,0.2817631806395851
+0.016428068528514434,expressions,train,0.2817631806395851
+0.016428068528514434,expressions,train,0.28349178910976663
+0.016662755221778926,expressions,train,0.28349178910976663
+0.016662755221778926,expressions,train,0.28867761452031115
+0.01689744191504342,expressions,train,0.28867761452031115
+0.01689744191504342,expressions,train,0.290838375108038
+0.017132128608307907,expressions,train,0.290838375108038
+0.017132128608307907,expressions,train,0.29213483146067415
+0.0173668153015724,expressions,train,0.29213483146067415
+0.0173668153015724,expressions,train,0.2934312878133103
+0.017601501994836892,expressions,train,0.2934312878133103
+0.017601501994836892,expressions,train,0.29472774416594644
+0.017836188688101384,expressions,train,0.29472774416594644
+0.017836188688101384,expressions,train,0.29515989628349176
+0.018070875381365877,expressions,train,0.29515989628349176
+0.018070875381365877,expressions,train,0.29818496110630943
+0.01854024876789486,expressions,train,0.29818496110630943
+0.01854024876789486,expressions,train,0.3050993949870354
+0.019009622154423846,expressions,train,0.3050993949870354
+0.019009622154423846,expressions,train,0.30639585133967157
+0.019244308847688334,expressions,train,0.30639585133967157
+0.019244308847688334,expressions,train,0.3111495246326707
+0.019478995540952827,expressions,train,0.3111495246326707
+0.019478995540952827,expressions,train,0.3115816767502161
+0.01971368223421732,expressions,train,0.3115816767502161
+0.01971368223421732,expressions,train,0.31590319792566984
+0.01994836892748181,expressions,train,0.31590319792566984
+0.01994836892748181,expressions,train,0.3184961106309421
+0.020183055620746303,expressions,train,0.3184961106309421
+0.020183055620746303,expressions,train,0.31936041486603284
+0.020652429007275288,expressions,train,0.31936041486603284
+0.020652429007275288,expressions,train,0.3197925669835782
+0.02088711570053978,expressions,train,0.3197925669835782
+0.02088711570053978,expressions,train,0.3202247191011236
+0.021121802393804272,expressions,train,0.3202247191011236
+0.021121802393804272,expressions,train,0.320656871218669
+0.021591175780333254,expressions,train,0.320656871218669
+0.021591175780333254,expressions,train,0.32843560933448573
+0.021825862473597746,expressions,train,0.32843560933448573
+0.021825862473597746,expressions,train,0.331028522039758
+0.022060549166862238,expressions,train,0.331028522039758
+0.022060549166862238,expressions,train,0.3331892826274849
+0.02229523586012673,expressions,train,0.3331892826274849
+0.02229523586012673,expressions,train,0.3349178910976664
+0.022529922553391223,expressions,train,0.3349178910976664
+0.022529922553391223,expressions,train,0.3362143474503025
+0.022764609246655715,expressions,train,0.3362143474503025
+0.022764609246655715,expressions,train,0.33707865168539325
+0.0232339826331847,expressions,train,0.33707865168539325
+0.0232339826331847,expressions,train,0.3409680207433016
+0.02346866932644919,expressions,train,0.3409680207433016
+0.02346866932644919,expressions,train,0.341400172860847
+0.023703356019713684,expressions,train,0.341400172860847
+0.023703356019713684,expressions,train,0.34312878133102853
+0.023938042712978173,expressions,train,0.34312878133102853
+0.023938042712978173,expressions,train,0.3435609334485739
+0.024407416099507157,expressions,train,0.3435609334485739
+0.024407416099507157,expressions,train,0.3470181503889369
+0.02464210279277165,expressions,train,0.3470181503889369
+0.02464210279277165,expressions,train,0.34831460674157305
+0.024876789486036142,expressions,train,0.34831460674157305
+0.024876789486036142,expressions,train,0.34874675885911843
+0.025111476179300634,expressions,train,0.34874675885911843
+0.025111476179300634,expressions,train,0.3500432152117545
+0.025346162872565126,expressions,train,0.3500432152117545
+0.025346162872565126,expressions,train,0.35133967156439067
+0.02558084956582962,expressions,train,0.35133967156439067
+0.02558084956582962,expressions,train,0.3530682800345722
+0.02581553625909411,expressions,train,0.3530682800345722
+0.02581553625909411,expressions,train,0.3599827139152982
+0.026519596338887584,expressions,train,0.3599827139152982
+0.026519596338887584,expressions,train,0.3630077787381158
+0.026754283032152076,expressions,train,0.3630077787381158
+0.026754283032152076,expressions,train,0.36387208297320656
+0.02722365641868106,expressions,train,0.36387208297320656
+0.02722365641868106,expressions,train,0.36430423509075194
+0.027458343111945553,expressions,train,0.36430423509075194
+0.027458343111945553,expressions,train,0.3703543647363872
+0.027693029805210045,expressions,train,0.3703543647363872
+0.027693029805210045,expressions,train,0.37294727744165945
+0.027927716498474538,expressions,train,0.37294727744165945
+0.027927716498474538,expressions,train,0.374675885911841
+0.02816240319173903,expressions,train,0.374675885911841
+0.02816240319173903,expressions,train,0.37640449438202245
+0.02839708988500352,expressions,train,0.37640449438202245
+0.02839708988500352,expressions,train,0.3798617113223855
+0.02863177657826801,expressions,train,0.3798617113223855
+0.02863177657826801,expressions,train,0.3828867761452031
+0.028866463271532503,expressions,train,0.3828867761452031
+0.028866463271532503,expressions,train,0.38504753673293
+0.029101149964796996,expressions,train,0.38504753673293
+0.029101149964796996,expressions,train,0.38720829732065687
+0.029335836658061488,expressions,train,0.38720829732065687
+0.029335836658061488,expressions,train,0.38764044943820225
+0.02957052335132598,expressions,train,0.38764044943820225
+0.02957052335132598,expressions,train,0.388504753673293
+0.029805210044590472,expressions,train,0.388504753673293
+0.029805210044590472,expressions,train,0.4044943820224719
+0.030039896737854965,expressions,train,0.4044943820224719
+0.030039896737854965,expressions,train,0.4049265341400173
+0.030274583431119457,expressions,train,0.4049265341400173
+0.030274583431119457,expressions,train,0.4079515989628349
+0.03050927012438395,expressions,train,0.4079515989628349
+0.03050927012438395,expressions,train,0.4083837510803803
+0.03097864351091293,expressions,train,0.4083837510803803
+0.03097864351091293,expressions,train,0.4187554019014693
+0.031213330204177422,expressions,train,0.4187554019014693
+0.031213330204177422,expressions,train,0.4196197061365601
+0.03168270359070641,expressions,train,0.4196197061365601
+0.03168270359070641,expressions,train,0.4222126188418323
+0.0319173902839709,expressions,train,0.4222126188418323
+0.0319173902839709,expressions,train,0.4248055315471046
+0.03215207697723539,expressions,train,0.4248055315471046
+0.03215207697723539,expressions,train,0.42523768366465
+0.032386763670499884,expressions,train,0.42523768366465
+0.032386763670499884,expressions,train,0.4261019878997407
+0.032621450363764376,expressions,train,0.4261019878997407
+0.032621450363764376,expressions,train,0.428694900605013
+0.03309082375029336,expressions,train,0.428694900605013
+0.03309082375029336,expressions,train,0.4299913569576491
+0.03332551044355785,expressions,train,0.4299913569576491
+0.03332551044355785,expressions,train,0.4308556611927398
+0.033560197136822345,expressions,train,0.4308556611927398
+0.033560197136822345,expressions,train,0.4312878133102852
+0.03379488383008684,expressions,train,0.4312878133102852
+0.03379488383008684,expressions,train,0.43258426966292135
+0.034264257216615815,expressions,train,0.43258426966292135
+0.034264257216615815,expressions,train,0.43301642178046673
+0.03449894390988031,expressions,train,0.43301642178046673
+0.03449894390988031,expressions,train,0.43863439930855663
+0.0347336306031448,expressions,train,0.43863439930855663
+0.0347336306031448,expressions,train,0.43949870354364734
+0.03496831729640929,expressions,train,0.43949870354364734
+0.03496831729640929,expressions,train,0.44338807260155577
+0.035203003989673784,expressions,train,0.44338807260155577
+0.035203003989673784,expressions,train,0.4438202247191011
+0.035437690682938276,expressions,train,0.4438202247191011
+0.035437690682938276,expressions,train,0.445980985306828
+0.03567237737620277,expressions,train,0.445980985306828
+0.03567237737620277,expressions,train,0.44727744165946415
+0.03590706406946726,expressions,train,0.44727744165946415
+0.03590706406946726,expressions,train,0.4498703543647364
+0.03614175076273175,expressions,train,0.4498703543647364
+0.03614175076273175,expressions,train,0.45073465859982714
+0.036376437455996245,expressions,train,0.45073465859982714
+0.036376437455996245,expressions,train,0.4511668107173725
+0.03661112414926074,expressions,train,0.4511668107173725
+0.03661112414926074,expressions,train,0.45419187554019014
+0.03684581084252523,expressions,train,0.45419187554019014
+0.03684581084252523,expressions,train,0.4589455488331893
+0.037315184229054214,expressions,train,0.4589455488331893
+0.037315184229054214,expressions,train,0.45980985306828004
+0.03754987092231871,expressions,train,0.45980985306828004
+0.03754987092231871,expressions,train,0.4611063094209162
+0.0377845576155832,expressions,train,0.4611063094209162
+0.0377845576155832,expressions,train,0.46153846153846156
+0.03825393100211218,expressions,train,0.46153846153846156
+0.03825393100211218,expressions,train,0.46326707000864303
+0.03872330438864116,expressions,train,0.46326707000864303
+0.03872330438864116,expressions,train,0.4641313742437338
+0.03895799108190565,expressions,train,0.4641313742437338
+0.03895799108190565,expressions,train,0.46499567847882456
+0.039192677775170146,expressions,train,0.46499567847882456
+0.039192677775170146,expressions,train,0.46672428694900603
+0.03942736446843464,expressions,train,0.46672428694900603
+0.03942736446843464,expressions,train,0.4693171996542783
+0.03966205116169913,expressions,train,0.4693171996542783
+0.03966205116169913,expressions,train,0.4701815038893691
+0.040131424548228115,expressions,train,0.4701815038893691
+0.040131424548228115,expressions,train,0.4736387208297321
+0.04036611124149261,expressions,train,0.4736387208297321
+0.04036611124149261,expressions,train,0.47450302506482284
+0.0406007979347571,expressions,train,0.47450302506482284
+0.0406007979347571,expressions,train,0.4801210025929127
+0.04083548462802159,expressions,train,0.4801210025929127
+0.04083548462802159,expressions,train,0.4857389801210026
+0.041070171321286084,expressions,train,0.4857389801210026
+0.041070171321286084,expressions,train,0.48617113223854796
+0.041304858014550576,expressions,train,0.48617113223854796
+0.041304858014550576,expressions,train,0.4870354364736387
+0.04153954470781507,expressions,train,0.4870354364736387
+0.04153954470781507,expressions,train,0.4913569576490925
+0.04177423140107956,expressions,train,0.4913569576490925
+0.04177423140107956,expressions,train,0.49351771823681934
+0.04200891809434405,expressions,train,0.49351771823681934
+0.04200891809434405,expressions,train,0.4948141745894555
+0.042243604787608545,expressions,train,0.4948141745894555
+0.042243604787608545,expressions,train,0.49567847882454624
+0.04247829148087304,expressions,train,0.49567847882454624
+0.04247829148087304,expressions,train,0.5012964563526361
+0.04271297817413753,expressions,train,0.5012964563526361
+0.04271297817413753,expressions,train,0.503457216940363
+0.04294766486740202,expressions,train,0.503457216940363
+0.04294766486740202,expressions,train,0.5038893690579084
+0.043417038253931,expressions,train,0.5038893690579084
+0.043417038253931,expressions,train,0.5090751944684528
+0.043886411640459984,expressions,train,0.5090751944684528
+0.043886411640459984,expressions,train,0.5095073465859983
+0.044121098333724476,expressions,train,0.5095073465859983
+0.044121098333724476,expressions,train,0.510371650821089
+0.04435578502698897,expressions,train,0.510371650821089
+0.04435578502698897,expressions,train,0.5121002592912706
+0.04482515841351795,expressions,train,0.5121002592912706
+0.04482515841351795,expressions,train,0.513828867761452
+0.045059845106782445,expressions,train,0.513828867761452
+0.045059845106782445,expressions,train,0.5185825410544511
+0.04529453180004694,expressions,train,0.5185825410544511
+0.04529453180004694,expressions,train,0.5207433016421781
+0.04552921849331143,expressions,train,0.5207433016421781
+0.04552921849331143,expressions,train,0.5211754537597234
+0.04576390518657592,expressions,train,0.5211754537597234
+0.04576390518657592,expressions,train,0.5233362143474503
+0.045998591879840414,expressions,train,0.5233362143474503
+0.045998591879840414,expressions,train,0.526361279170268
+0.046233278573104906,expressions,train,0.526361279170268
+0.046233278573104906,expressions,train,0.5272255834053586
+0.0464679652663694,expressions,train,0.5272255834053586
+0.0464679652663694,expressions,train,0.533275713050994
+0.04670265195963389,expressions,train,0.533275713050994
+0.04670265195963389,expressions,train,0.5350043215211755
+0.04693733865289838,expressions,train,0.5350043215211755
+0.04693733865289838,expressions,train,0.5375972342264477
+0.047172025346162876,expressions,train,0.5375972342264477
+0.047172025346162876,expressions,train,0.5380293863439931
+0.04740671203942737,expressions,train,0.5380293863439931
+0.04740671203942737,expressions,train,0.54019014693172
+0.04764139873269185,expressions,train,0.54019014693172
+0.04764139873269185,expressions,train,0.5410544511668107
+0.047876085425956345,expressions,train,0.5410544511668107
+0.047876085425956345,expressions,train,0.5419187554019015
+0.04811077211922084,expressions,train,0.5419187554019015
+0.04811077211922084,expressions,train,0.5423509075194468
+0.048814832199014314,expressions,train,0.5423509075194468
+0.048814832199014314,expressions,train,0.5432152117545376
+0.04904951889227881,expressions,train,0.5432152117545376
+0.04904951889227881,expressions,train,0.5458081244598099
+0.0492842055855433,expressions,train,0.5458081244598099
+0.0492842055855433,expressions,train,0.5462402765773552
+0.04951889227880779,expressions,train,0.5462402765773552
+0.04951889227880779,expressions,train,0.5484010371650822
+0.049753578972072283,expressions,train,0.5484010371650822
+0.049753578972072283,expressions,train,0.5566119273984442
+0.049988265665336776,expressions,train,0.5566119273984442
+0.049988265665336776,expressions,train,0.5600691443388073
+0.05069232574513025,expressions,train,0.5600691443388073
+0.05069232574513025,expressions,train,0.5630942091616249
+0.050927012438394745,expressions,train,0.5630942091616249
+0.050927012438394745,expressions,train,0.5691443388072601
+0.05116169913165924,expressions,train,0.5691443388072601
+0.05116169913165924,expressions,train,0.5708729472774416
+0.05139638582492373,expressions,train,0.5708729472774416
+0.05139638582492373,expressions,train,0.5743301642178047
+0.05163107251818822,expressions,train,0.5743301642178047
+0.05163107251818822,expressions,train,0.5751944684528955
+0.0521004459047172,expressions,train,0.5751944684528955
+0.0521004459047172,expressions,train,0.5782195332757131
+0.052569819291246184,expressions,train,0.5782195332757131
+0.052569819291246184,expressions,train,0.5786516853932584
+0.052804505984510676,expressions,train,0.5786516853932584
+0.052804505984510676,expressions,train,0.5790838375108038
+0.05327387937103966,expressions,train,0.5790838375108038
+0.05327387937103966,expressions,train,0.5799481417458946
+0.05350856606430415,expressions,train,0.5799481417458946
+0.05350856606430415,expressions,train,0.5808124459809854
+0.05397793945083314,expressions,train,0.5808124459809854
+0.05397793945083314,expressions,train,0.5855661192739845
+0.05421262614409763,expressions,train,0.5855661192739845
+0.05421262614409763,expressions,train,0.5864304235090751
+0.05444731283736212,expressions,train,0.5864304235090751
+0.05444731283736212,expressions,train,0.5872947277441659
+0.054681999530626614,expressions,train,0.5872947277441659
+0.054681999530626614,expressions,train,0.5881590319792567
+0.0551513729171556,expressions,train,0.5881590319792567
+0.0551513729171556,expressions,train,0.5885911840968021
+0.05538605961042009,expressions,train,0.5885911840968021
+0.05538605961042009,expressions,train,0.5890233362143474
+0.05562074630368458,expressions,train,0.5890233362143474
+0.05562074630368458,expressions,train,0.5898876404494382
+0.055855432996949075,expressions,train,0.5898876404494382
+0.055855432996949075,expressions,train,0.590751944684529
+0.05632480638347806,expressions,train,0.590751944684529
+0.05632480638347806,expressions,train,0.592048401037165
+0.05655949307674255,expressions,train,0.592048401037165
+0.05655949307674255,expressions,train,0.5929127052722558
+0.05702886646327153,expressions,train,0.5929127052722558
+0.05702886646327153,expressions,train,0.5968020743301642
+0.057498239849800514,expressions,train,0.5968020743301642
+0.057498239849800514,expressions,train,0.5972342264477096
+0.05773292654306501,expressions,train,0.5972342264477096
+0.05773292654306501,expressions,train,0.6028522039757995
+0.0579676132363295,expressions,train,0.6028522039757995
+0.0579676132363295,expressions,train,0.6032843560933449
+0.05820229992959399,expressions,train,0.6032843560933449
+0.05820229992959399,expressions,train,0.6037165082108902
+0.05843698662285848,expressions,train,0.6037165082108902
+0.05843698662285848,expressions,train,0.6063094209161625
+0.058671673316122976,expressions,train,0.6063094209161625
+0.058671673316122976,expressions,train,0.6067415730337079
+0.05890636000938747,expressions,train,0.6067415730337079
+0.05890636000938747,expressions,train,0.6076058772687987
+0.05914104670265196,expressions,train,0.6076058772687987
+0.05914104670265196,expressions,train,0.6084701815038893
+0.059610420089180945,expressions,train,0.6084701815038893
+0.059610420089180945,expressions,train,0.6089023336214348
+0.05984510678244544,expressions,train,0.6089023336214348
+0.05984510678244544,expressions,train,0.611495246326707
+0.06007979347570993,expressions,train,0.611495246326707
+0.06007979347570993,expressions,train,0.6140881590319792
+0.06031448016897442,expressions,train,0.6140881590319792
+0.06031448016897442,expressions,train,0.6153846153846154
+0.060549166862238914,expressions,train,0.6153846153846154
+0.060549166862238914,expressions,train,0.6175453759723423
+0.060783853555503406,expressions,train,0.6175453759723423
+0.060783853555503406,expressions,train,0.618409680207433
+0.061253226942032384,expressions,train,0.618409680207433
+0.061253226942032384,expressions,train,0.6192739844425238
+0.061487913635296876,expressions,train,0.6192739844425238
+0.061487913635296876,expressions,train,0.6214347450302506
+0.06172260032856137,expressions,train,0.6214347450302506
+0.06172260032856137,expressions,train,0.6231633535004322
+0.062426660408354845,expressions,train,0.6231633535004322
+0.062426660408354845,expressions,train,0.6240276577355229
+0.06266134710161934,expressions,train,0.6240276577355229
+0.06266134710161934,expressions,train,0.6257562662057045
+0.06313072048814833,expressions,train,0.6257562662057045
+0.06313072048814833,expressions,train,0.6270527225583405
+0.0636000938746773,expressions,train,0.6270527225583405
+0.0636000938746773,expressions,train,0.6274848746758859
+0.0638347805679418,expressions,train,0.6274848746758859
+0.0638347805679418,expressions,train,0.6331028522039758
+0.06406946726120628,expressions,train,0.6331028522039758
+0.06406946726120628,expressions,train,0.634399308556612
+0.06430415395447078,expressions,train,0.634399308556612
+0.06430415395447078,expressions,train,0.6348314606741573
+0.06453884064773527,expressions,train,0.6348314606741573
+0.06453884064773527,expressions,train,0.6361279170267934
+0.06477352734099977,expressions,train,0.6361279170267934
+0.06477352734099977,expressions,train,0.6365600691443388
+0.06500821403426425,expressions,train,0.6365600691443388
+0.06500821403426425,expressions,train,0.6400172860847018
+0.06524290072752875,expressions,train,0.6400172860847018
+0.06524290072752875,expressions,train,0.6404494382022472
+0.06547758742079324,expressions,train,0.6404494382022472
+0.06547758742079324,expressions,train,0.6443388072601556
+0.06571227411405774,expressions,train,0.6443388072601556
+0.06571227411405774,expressions,train,0.6447709593777009
+0.06594696080732222,expressions,train,0.6447709593777009
+0.06594696080732222,expressions,train,0.6486603284356093
+0.06618164750058672,expressions,train,0.6486603284356093
+0.06618164750058672,expressions,train,0.6503889369057908
+0.0664163341938512,expressions,train,0.6503889369057908
+0.0664163341938512,expressions,train,0.6508210890233362
+0.0666510208871157,expressions,train,0.6508210890233362
+0.0666510208871157,expressions,train,0.6542783059636992
+0.06688570758038019,expressions,train,0.6542783059636992
+0.06688570758038019,expressions,train,0.6568712186689715
+0.06712039427364469,expressions,train,0.6568712186689715
+0.06712039427364469,expressions,train,0.6590319792566983
+0.06735508096690918,expressions,train,0.6590319792566983
+0.06735508096690918,expressions,train,0.6594641313742438
+0.06758976766017367,expressions,train,0.6594641313742438
+0.06758976766017367,expressions,train,0.6629213483146067
+0.06782445435343816,expressions,train,0.6629213483146067
+0.06782445435343816,expressions,train,0.6642178046672429
+0.06805914104670265,expressions,train,0.6642178046672429
+0.06805914104670265,expressions,train,0.6659464131374244
+0.06829382773996714,expressions,train,0.6659464131374244
+0.06829382773996714,expressions,train,0.6672428694900605
+0.06852851443323163,expressions,train,0.6672428694900605
+0.06852851443323163,expressions,train,0.6715643906655142
+0.06876320112649613,expressions,train,0.6715643906655142
+0.06876320112649613,expressions,train,0.6732929991356957
+0.06923257451302511,expressions,train,0.6732929991356957
+0.06923257451302511,expressions,train,0.6750216076058773
+0.0697019478995541,expressions,train,0.6750216076058773
+0.0697019478995541,expressions,train,0.6776145203111495
+0.06993663459281858,expressions,train,0.6776145203111495
+0.06993663459281858,expressions,train,0.6793431287813311
+0.07017132128608308,expressions,train,0.6793431287813311
+0.07017132128608308,expressions,train,0.6836646499567848
+0.07040600797934757,expressions,train,0.6836646499567848
+0.07040600797934757,expressions,train,0.6849611063094209
+0.07111006805914105,expressions,train,0.6849611063094209
+0.07111006805914105,expressions,train,0.6866897147796024
+0.07134475475240554,expressions,train,0.6866897147796024
+0.07134475475240554,expressions,train,0.6884183232497839
+0.07181412813893452,expressions,train,0.6884183232497839
+0.07181412813893452,expressions,train,0.6892826274848747
+0.0722835015254635,expressions,train,0.6892826274848747
+0.0722835015254635,expressions,train,0.68971477960242
+0.07322224829852148,expressions,train,0.68971477960242
+0.07322224829852148,expressions,train,0.693171996542783
+0.07345693499178596,expressions,train,0.693171996542783
+0.07345693499178596,expressions,train,0.6944684528954191
+0.07369162168505046,expressions,train,0.6944684528954191
+0.07369162168505046,expressions,train,0.6961970613656007
+0.07392630837831494,expressions,train,0.6961970613656007
+0.07392630837831494,expressions,train,0.6992221261884183
+0.07416099507157944,expressions,train,0.6992221261884183
+0.07416099507157944,expressions,train,0.7009507346585998
+0.07439568176484393,expressions,train,0.7009507346585998
+0.07439568176484393,expressions,train,0.702247191011236
+0.07463036845810843,expressions,train,0.702247191011236
+0.07463036845810843,expressions,train,0.7039757994814174
+0.07486505515137291,expressions,train,0.7039757994814174
+0.07486505515137291,expressions,train,0.7052722558340536
+0.07509974184463741,expressions,train,0.7052722558340536
+0.07509974184463741,expressions,train,0.7065687121866897
+0.0753344285379019,expressions,train,0.7065687121866897
+0.0753344285379019,expressions,train,0.7087294727744166
+0.07580380192443088,expressions,train,0.7087294727744166
+0.07580380192443088,expressions,train,0.709161624891962
+0.07603848861769538,expressions,train,0.709161624891962
+0.07603848861769538,expressions,train,0.7095937770095073
+0.07627317531095987,expressions,train,0.7095937770095073
+0.07627317531095987,expressions,train,0.7104580812445981
+0.07650786200422437,expressions,train,0.7104580812445981
+0.07650786200422437,expressions,train,0.7130509939498704
+0.07674254869748885,expressions,train,0.7130509939498704
+0.07674254869748885,expressions,train,0.7134831460674157
+0.07697723539075334,expressions,train,0.7134831460674157
+0.07697723539075334,expressions,train,0.7139152981849611
+0.07721192208401784,expressions,train,0.7139152981849611
+0.07721192208401784,expressions,train,0.7152117545375972
+0.0779159821638113,expressions,train,0.7152117545375972
+0.0779159821638113,expressions,train,0.7165082108902333
+0.0781506688570758,expressions,train,0.7165082108902333
+0.0781506688570758,expressions,train,0.7191011235955056
+0.07838535555034029,expressions,train,0.7191011235955056
+0.07838535555034029,expressions,train,0.7199654278305964
+0.07885472893686928,expressions,train,0.7199654278305964
+0.07885472893686928,expressions,train,0.7208297320656871
+0.07908941563013377,expressions,train,0.7208297320656871
+0.07908941563013377,expressions,train,0.7216940363007779
+0.07932410232339826,expressions,train,0.7216940363007779
+0.07932410232339826,expressions,train,0.7251512532411409
+0.07955878901666276,expressions,train,0.7251512532411409
+0.07955878901666276,expressions,train,0.7255834053586863
+0.07979347570992724,expressions,train,0.7255834053586863
+0.07979347570992724,expressions,train,0.7281763180639585
+0.08002816240319174,expressions,train,0.7281763180639585
+0.08002816240319174,expressions,train,0.7286084701815039
+0.08049753578972073,expressions,train,0.7286084701815039
+0.08049753578972073,expressions,train,0.72990492653414
+0.08073222248298521,expressions,train,0.72990492653414
+0.08073222248298521,expressions,train,0.7320656871218669
+0.08096690917624971,expressions,train,0.7320656871218669
+0.08096690917624971,expressions,train,0.7324978392394123
+0.0812015958695142,expressions,train,0.7324978392394123
+0.0812015958695142,expressions,train,0.733362143474503
+0.0814362825627787,expressions,train,0.733362143474503
+0.0814362825627787,expressions,train,0.7342264477095938
+0.08237502933583665,expressions,train,0.7342264477095938
+0.08237502933583665,expressions,train,0.7359550561797753
+0.08260971602910115,expressions,train,0.7359550561797753
+0.08260971602910115,expressions,train,0.7381158167675022
+0.08284440272236564,expressions,train,0.7381158167675022
+0.08284440272236564,expressions,train,0.7385479688850476
+0.08354846280215912,expressions,train,0.7385479688850476
+0.08354846280215912,expressions,train,0.7389801210025929
+0.08425252288195259,expressions,train,0.7389801210025929
+0.08425252288195259,expressions,train,0.7398444252376837
+0.08472189626848158,expressions,train,0.7398444252376837
+0.08472189626848158,expressions,train,0.740276577355229
+0.08495658296174607,expressions,train,0.740276577355229
+0.08495658296174607,expressions,train,0.7411408815903198
+0.08566064304153954,expressions,train,0.7411408815903198
+0.08566064304153954,expressions,train,0.7415730337078652
+0.08613001642806853,expressions,train,0.7415730337078652
+0.08613001642806853,expressions,train,0.7420051858254105
+0.08636470312133301,expressions,train,0.7420051858254105
+0.08636470312133301,expressions,train,0.7428694900605013
+0.08659938981459751,expressions,train,0.7428694900605013
+0.08659938981459751,expressions,train,0.7441659464131374
+0.086834076507862,expressions,train,0.7441659464131374
+0.086834076507862,expressions,train,0.7450302506482281
+0.0870687632011265,expressions,train,0.7450302506482281
+0.0870687632011265,expressions,train,0.7471910112359551
+0.08777282328091997,expressions,train,0.7471910112359551
+0.08777282328091997,expressions,train,0.7489196197061365
+0.08824219666744895,expressions,train,0.7489196197061365
+0.08824219666744895,expressions,train,0.7502160760587727
+0.08847688336071345,expressions,train,0.7502160760587727
+0.08847688336071345,expressions,train,0.7515125324114088
+0.08871157005397794,expressions,train,0.7515125324114088
+0.08871157005397794,expressions,train,0.7541054451166811
+0.08894625674724244,expressions,train,0.7541054451166811
+0.08894625674724244,expressions,train,0.7549697493517719
+0.08941563013377142,expressions,train,0.7549697493517719
+0.08941563013377142,expressions,train,0.7554019014693172
+0.0896503168270359,expressions,train,0.7554019014693172
+0.0896503168270359,expressions,train,0.7566983578219534
+0.09011969021356489,expressions,train,0.7566983578219534
+0.09011969021356489,expressions,train,0.7571305099394987
+0.09035437690682939,expressions,train,0.7571305099394987
+0.09035437690682939,expressions,train,0.7584269662921348
+0.09058906360009387,expressions,train,0.7584269662921348
+0.09058906360009387,expressions,train,0.7588591184096802
+0.09105843698662286,expressions,train,0.7588591184096802
+0.09105843698662286,expressions,train,0.7592912705272256
+0.09129312367988734,expressions,train,0.7592912705272256
+0.09129312367988734,expressions,train,0.759723422644771
+0.09152781037315184,expressions,train,0.759723422644771
+0.09152781037315184,expressions,train,0.7623163353500432
+0.09176249706641633,expressions,train,0.7623163353500432
+0.09176249706641633,expressions,train,0.7627484874675886
+0.09223187045294531,expressions,train,0.7627484874675886
+0.09223187045294531,expressions,train,0.7644770959377701
+0.0929359305327388,expressions,train,0.7644770959377701
+0.0929359305327388,expressions,train,0.766637856525497
+0.09340530391926778,expressions,train,0.766637856525497
+0.09340530391926778,expressions,train,0.7679343128781331
+0.09363999061253227,expressions,train,0.7679343128781331
+0.09363999061253227,expressions,train,0.7696629213483146
+0.09434405069232575,expressions,train,0.7696629213483146
+0.09434405069232575,expressions,train,0.7713915298184961
+0.09457873738559024,expressions,train,0.7713915298184961
+0.09457873738559024,expressions,train,0.7722558340535869
+0.09504811077211922,expressions,train,0.7722558340535869
+0.09504811077211922,expressions,train,0.7726879861711322
+0.0952827974653837,expressions,train,0.7726879861711322
+0.0952827974653837,expressions,train,0.7731201382886776
+0.09598685754517719,expressions,train,0.7731201382886776
+0.09598685754517719,expressions,train,0.7739844425237684
+0.09622154423844168,expressions,train,0.7739844425237684
+0.09622154423844168,expressions,train,0.7744165946413137
+0.09645623093170617,expressions,train,0.7744165946413137
+0.09645623093170617,expressions,train,0.7757130509939498
+0.09669091762497066,expressions,train,0.7757130509939498
+0.09669091762497066,expressions,train,0.7774416594641314
+0.09692560431823516,expressions,train,0.7774416594641314
+0.09692560431823516,expressions,train,0.7787381158167676
+0.09739497770476414,expressions,train,0.7787381158167676
+0.09739497770476414,expressions,train,0.7808988764044944
+0.09762966439802863,expressions,train,0.7808988764044944
+0.09762966439802863,expressions,train,0.7826274848746759
+0.09809903778455761,expressions,train,0.7826274848746759
+0.09809903778455761,expressions,train,0.7847882454624028
+0.0985684111710866,expressions,train,0.7847882454624028
+0.0985684111710866,expressions,train,0.7873811581676751
+0.09927247125088008,expressions,train,0.7873811581676751
+0.09927247125088008,expressions,train,0.7878133102852204
+0.09950715794414457,expressions,train,0.7878133102852204
+0.09950715794414457,expressions,train,0.7904062229904927
+0.09974184463740905,expressions,train,0.7904062229904927
+0.09974184463740905,expressions,train,0.7912705272255834
+0.09997653133067355,expressions,train,0.7912705272255834
+0.09997653133067355,expressions,train,0.7925669835782195
+0.10044590471720254,expressions,train,0.7925669835782195
+0.10044590471720254,expressions,train,0.7929991356957649
+0.10068059141046702,expressions,train,0.7929991356957649
+0.10068059141046702,expressions,train,0.7938634399308556
+0.10232339826331847,expressions,train,0.7938634399308556
+0.10232339826331847,expressions,train,0.7942955920484011
+0.10255808495658296,expressions,train,0.7942955920484011
+0.10255808495658296,expressions,train,0.7955920484010371
+0.10302745834311194,expressions,train,0.7955920484010371
+0.10302745834311194,expressions,train,0.7960242005185826
+0.10326214503637644,expressions,train,0.7960242005185826
+0.10326214503637644,expressions,train,0.7973206568712187
+0.10349683172964093,expressions,train,0.7973206568712187
+0.10349683172964093,expressions,train,0.797752808988764
+0.10373151842290543,expressions,train,0.797752808988764
+0.10373151842290543,expressions,train,0.7990492653414002
+0.1042008918094344,expressions,train,0.7990492653414002
+0.1042008918094344,expressions,train,0.8003457216940363
+0.10467026519596338,expressions,train,0.8003457216940363
+0.10467026519596338,expressions,train,0.801210025929127
+0.10560901196902135,expressions,train,0.801210025929127
+0.10560901196902135,expressions,train,0.8025064822817631
+0.10584369866228585,expressions,train,0.8025064822817631
+0.10584369866228585,expressions,train,0.8042350907519447
+0.10607838535555034,expressions,train,0.8042350907519447
+0.10607838535555034,expressions,train,0.8063958513396715
+0.10631307204881484,expressions,train,0.8063958513396715
+0.10631307204881484,expressions,train,0.8072601555747623
+0.10654775874207932,expressions,train,0.8072601555747623
+0.10654775874207932,expressions,train,0.808124459809853
+0.1072518188218728,expressions,train,0.808124459809853
+0.1072518188218728,expressions,train,0.8089887640449438
+0.10748650551513729,expressions,train,0.8089887640449438
+0.10748650551513729,expressions,train,0.8094209161624892
+0.10772119220840179,expressions,train,0.8094209161624892
+0.10772119220840179,expressions,train,0.8098530682800346
+0.10819056559493077,expressions,train,0.8098530682800346
+0.10819056559493077,expressions,train,0.8107173725151253
+0.10842525228819526,expressions,train,0.8107173725151253
+0.10842525228819526,expressions,train,0.8111495246326706
+0.10912931236798873,expressions,train,0.8111495246326706
+0.10912931236798873,expressions,train,0.8120138288677614
+0.10936399906125323,expressions,train,0.8120138288677614
+0.10936399906125323,expressions,train,0.8128781331028522
+0.10983337244778221,expressions,train,0.8128781331028522
+0.10983337244778221,expressions,train,0.8133102852203976
+0.1100680591410467,expressions,train,0.8133102852203976
+0.1100680591410467,expressions,train,0.8137424373379429
+0.1103027458343112,expressions,train,0.8137424373379429
+0.1103027458343112,expressions,train,0.8150388936905791
+0.11077211922084018,expressions,train,0.8150388936905791
+0.11077211922084018,expressions,train,0.8176318063958513
+0.11124149260736917,expressions,train,0.8176318063958513
+0.11124149260736917,expressions,train,0.8180639585133967
+0.11147617930063365,expressions,train,0.8180639585133967
+0.11147617930063365,expressions,train,0.8184961106309421
+0.11171086599389815,expressions,train,0.8184961106309421
+0.11171086599389815,expressions,train,0.8206568712186689
+0.11194555268716264,expressions,train,0.8206568712186689
+0.11194555268716264,expressions,train,0.8210890233362144
+0.11218023938042714,expressions,train,0.8210890233362144
+0.11218023938042714,expressions,train,0.8219533275713051
+0.1131189861534851,expressions,train,0.8219533275713051
+0.1131189861534851,expressions,train,0.8223854796888505
+0.11335367284674959,expressions,train,0.8223854796888505
+0.11335367284674959,expressions,train,0.8228176318063959
+0.11429241961980756,expressions,train,0.8228176318063959
+0.11429241961980756,expressions,train,0.8236819360414867
+0.11546585308613001,expressions,train,0.8236819360414867
+0.11546585308613001,expressions,train,0.824114088159032
+0.11640459985918798,expressions,train,0.824114088159032
+0.11640459985918798,expressions,train,0.8245462402765773
+0.11710865993898147,expressions,train,0.8245462402765773
+0.11710865993898147,expressions,train,0.8258426966292135
+0.11734334663224595,expressions,train,0.8258426966292135
+0.11734334663224595,expressions,train,0.8262748487467588
+0.11757803332551045,expressions,train,0.8262748487467588
+0.11757803332551045,expressions,train,0.8271391529818496
+0.11898615348509739,expressions,train,0.8271391529818496
+0.11898615348509739,expressions,train,0.827571305099395
+0.11945552687162637,expressions,train,0.827571305099395
+0.11945552687162637,expressions,train,0.8284356093344858
+0.11992490025815536,expressions,train,0.8284356093344858
+0.11992490025815536,expressions,train,0.8288677614520311
+0.12156770711100681,expressions,train,0.8288677614520311
+0.12156770711100681,expressions,train,0.8301642178046672
+0.1220370804975358,expressions,train,0.8301642178046672
+0.1220370804975358,expressions,train,0.8305963699222126
+0.12250645388406477,expressions,train,0.8305963699222126
+0.12250645388406477,expressions,train,0.831028522039758
+0.12344520065712274,expressions,train,0.831028522039758
+0.12344520065712274,expressions,train,0.8314606741573034
+0.12391457404365172,expressions,train,0.8314606741573034
+0.12391457404365172,expressions,train,0.8331892826274849
+0.1246186341234452,expressions,train,0.8331892826274849
+0.1246186341234452,expressions,train,0.8353500432152118
+0.12485332081670969,expressions,train,0.8353500432152118
+0.12485332081670969,expressions,train,0.8362143474503025
+0.12508800750997418,expressions,train,0.8362143474503025
+0.12508800750997418,expressions,train,0.8370786516853933
+0.1272001877493546,expressions,train,0.8370786516853933
+0.1272001877493546,expressions,train,0.8383751080380294
+0.12790424782914808,expressions,train,0.8383751080380294
+0.12790424782914808,expressions,train,0.8388072601555747
+0.12837362121567708,expressions,train,0.8388072601555747
+0.12837362121567708,expressions,train,0.8396715643906655
+0.12954705468199953,expressions,train,0.8396715643906655
+0.12954705468199953,expressions,train,0.8409680207433017
+0.1300164280685285,expressions,train,0.8409680207433017
+0.1300164280685285,expressions,train,0.8418323249783924
+0.13025111476179302,expressions,train,0.8418323249783924
+0.13025111476179302,expressions,train,0.8431287813310285
+0.1304858014550575,expressions,train,0.8431287813310285
+0.1304858014550575,expressions,train,0.8448573898012101
+0.13095517484158647,expressions,train,0.8448573898012101
+0.13095517484158647,expressions,train,0.8457216940363008
+0.13212860830790893,expressions,train,0.8457216940363008
+0.13212860830790893,expressions,train,0.8461538461538461
+0.13236329500117344,expressions,train,0.8461538461538461
+0.13236329500117344,expressions,train,0.8470181503889369
+0.13259798169443793,expressions,train,0.8470181503889369
+0.13259798169443793,expressions,train,0.8474503025064822
+0.1328326683877024,expressions,train,0.8474503025064822
+0.1328326683877024,expressions,train,0.8478824546240277
+0.1330673550809669,expressions,train,0.8478824546240277
+0.1330673550809669,expressions,train,0.8491789109766638
+0.1333020417742314,expressions,train,0.8491789109766638
+0.1333020417742314,expressions,train,0.8504753673293
+0.13377141516076038,expressions,train,0.8504753673293
+0.13377141516076038,expressions,train,0.851771823681936
+0.13400610185402487,expressions,train,0.851771823681936
+0.13400610185402487,expressions,train,0.8522039757994814
+0.13424078854728938,expressions,train,0.8522039757994814
+0.13424078854728938,expressions,train,0.8526361279170268
+0.13471016193381835,expressions,train,0.8526361279170268
+0.13471016193381835,expressions,train,0.8543647363872083
+0.13494484862708284,expressions,train,0.8543647363872083
+0.13494484862708284,expressions,train,0.8556611927398444
+0.13564890870687632,expressions,train,0.8556611927398444
+0.13564890870687632,expressions,train,0.8560933448573897
+0.1361182820934053,expressions,train,0.8560933448573897
+0.1361182820934053,expressions,train,0.8569576490924805
+0.1365876554799343,expressions,train,0.8569576490924805
+0.1365876554799343,expressions,train,0.857389801210026
+0.13776108894625674,expressions,train,0.857389801210026
+0.13776108894625674,expressions,train,0.8582541054451167
+0.13823046233278574,expressions,train,0.8582541054451167
+0.13823046233278574,expressions,train,0.858686257562662
+0.1389345224125792,expressions,train,0.858686257562662
+0.1389345224125792,expressions,train,0.8591184096802075
+0.1391692091058437,expressions,train,0.8591184096802075
+0.1391692091058437,expressions,train,0.8599827139152982
+0.13963858249237268,expressions,train,0.8599827139152982
+0.13963858249237268,expressions,train,0.8604148660328436
+0.13987326918563717,expressions,train,0.8604148660328436
+0.13987326918563717,expressions,train,0.8612791702679343
+0.14104670265195962,expressions,train,0.8612791702679343
+0.14104670265195962,expressions,train,0.8617113223854796
+0.14268950950481107,expressions,train,0.8617113223854796
+0.14268950950481107,expressions,train,0.8621434745030251
+0.14339356958460456,expressions,train,0.8621434745030251
+0.14339356958460456,expressions,train,0.8625756266205704
+0.14386294297113353,expressions,train,0.8625756266205704
+0.14386294297113353,expressions,train,0.8630077787381158
+0.1452710631307205,expressions,train,0.8630077787381158
+0.1452710631307205,expressions,train,0.8634399308556612
+0.14550574982398498,expressions,train,0.8634399308556612
+0.14550574982398498,expressions,train,0.8638720829732066
+0.14574043651724947,expressions,train,0.8638720829732066
+0.14574043651724947,expressions,train,0.8660328435609335
+0.14644449659704295,expressions,train,0.8660328435609335
+0.14644449659704295,expressions,train,0.8664649956784788
+0.14667918329030744,expressions,train,0.8664649956784788
+0.14667918329030744,expressions,train,0.8668971477960242
+0.14691386998357192,expressions,train,0.8668971477960242
+0.14691386998357192,expressions,train,0.8673292999135696
+0.14738324337010092,expressions,train,0.8673292999135696
+0.14738324337010092,expressions,train,0.867761452031115
+0.1480873034498944,expressions,train,0.867761452031115
+0.1480873034498944,expressions,train,0.8681936041486603
+0.14902605022295237,expressions,train,0.8681936041486603
+0.14902605022295237,expressions,train,0.8686257562662058
+0.14926073691621686,expressions,train,0.8686257562662058
+0.14926073691621686,expressions,train,0.8690579083837511
+0.1511382304623328,expressions,train,0.8690579083837511
+0.1511382304623328,expressions,train,0.8694900605012964
+0.15184229054212625,expressions,train,0.8694900605012964
+0.15184229054212625,expressions,train,0.8699222126188418
+0.15301572400844873,expressions,train,0.8699222126188418
+0.15301572400844873,expressions,train,0.8707865168539326
+0.1534850973949777,expressions,train,0.8707865168539326
+0.1534850973949777,expressions,train,0.8712186689714779
+0.15536259094109364,expressions,train,0.8712186689714779
+0.15536259094109364,expressions,train,0.8729472774416595
+0.15559727763435813,expressions,train,0.8729472774416595
+0.15559727763435813,expressions,train,0.8733794295592049
+0.1558319643276226,expressions,train,0.8733794295592049
+0.1558319643276226,expressions,train,0.8742437337942955
+0.15606665102088713,expressions,train,0.8742437337942955
+0.15606665102088713,expressions,train,0.874675885911841
+0.15747477118047407,expressions,train,0.874675885911841
+0.15747477118047407,expressions,train,0.8751080380293863
+0.15841351795353203,expressions,train,0.8751080380293863
+0.15841351795353203,expressions,train,0.8755401901469317
+0.15935226472659,expressions,train,0.8755401901469317
+0.15935226472659,expressions,train,0.8759723422644771
+0.16076038488617694,expressions,train,0.8759723422644771
+0.16076038488617694,expressions,train,0.8764044943820225
+0.16099507157944146,expressions,train,0.8764044943820225
+0.16099507157944146,expressions,train,0.8768366464995678
+0.16122975827270594,expressions,train,0.8768366464995678
+0.16122975827270594,expressions,train,0.8772687986171133
+0.16263787843229288,expressions,train,0.8772687986171133
+0.16263787843229288,expressions,train,0.8777009507346586
+0.16357662520535085,expressions,train,0.8777009507346586
+0.16357662520535085,expressions,train,0.8789974070872947
+0.16428068528514433,expressions,train,0.8789974070872947
+0.16428068528514433,expressions,train,0.8802938634399309
+0.1652194320582023,expressions,train,0.8802938634399309
+0.1652194320582023,expressions,train,0.8820224719101124
+0.1654541187514668,expressions,train,0.8820224719101124
+0.1654541187514668,expressions,train,0.8841832324978393
+0.16615817883126027,expressions,train,0.8841832324978393
+0.16615817883126027,expressions,train,0.8876404494382022
+0.16686223891105376,expressions,train,0.8876404494382022
+0.16686223891105376,expressions,train,0.8880726015557476
+0.16733161229758273,expressions,train,0.8880726015557476
+0.16733161229758273,expressions,train,0.8898012100259292
+0.16850504576390518,expressions,train,0.8898012100259292
+0.16850504576390518,expressions,train,0.8902333621434745
+0.16991316592349215,expressions,train,0.8902333621434745
+0.16991316592349215,expressions,train,0.8906655142610199
+0.17085191269655012,expressions,train,0.8906655142610199
+0.17085191269655012,expressions,train,0.8910976663785652
+0.1713212860830791,expressions,train,0.8910976663785652
+0.1713212860830791,expressions,train,0.891961970613656
+0.17155597277634357,expressions,train,0.891961970613656
+0.17155597277634357,expressions,train,0.8923941227312013
+0.173668153015724,expressions,train,0.8923941227312013
+0.173668153015724,expressions,train,0.8928262748487468
+0.17507627317531096,expressions,train,0.8928262748487468
+0.17507627317531096,expressions,train,0.8932584269662921
+0.17531095986857545,expressions,train,0.8932584269662921
+0.17531095986857545,expressions,train,0.8936905790838375
+0.17578033325510445,expressions,train,0.8936905790838375
+0.17578033325510445,expressions,train,0.8941227312013829
+0.17624970664163342,expressions,train,0.8941227312013829
+0.17624970664163342,expressions,train,0.8945548833189283
+0.1764843933348979,expressions,train,0.8945548833189283
+0.1764843933348979,expressions,train,0.8949870354364736
+0.17883126026754284,expressions,train,0.8949870354364736
+0.17883126026754284,expressions,train,0.8958513396715644
+0.1793006336540718,expressions,train,0.8958513396715644
+0.1793006336540718,expressions,train,0.8962834917891098
+0.18070875381365878,expressions,train,0.8962834917891098
+0.18070875381365878,expressions,train,0.8967156439066551
+0.18117812720018775,expressions,train,0.8967156439066551
+0.18117812720018775,expressions,train,0.8971477960242005
+0.18188218727998123,expressions,train,0.8971477960242005
+0.18188218727998123,expressions,train,0.8984442523768367
+0.1830556207463037,expressions,train,0.8984442523768367
+0.1830556207463037,expressions,train,0.8997407087294728
+0.18329030743956817,expressions,train,0.8997407087294728
+0.18329030743956817,expressions,train,0.9006050129645635
+0.18352499413283266,expressions,train,0.9006050129645635
+0.18352499413283266,expressions,train,0.9014693171996543
+0.18399436751936166,expressions,train,0.9014693171996543
+0.18399436751936166,expressions,train,0.9027657735522904
+0.18493311429241963,expressions,train,0.9027657735522904
+0.18493311429241963,expressions,train,0.9031979256698358
+0.1858718610654776,expressions,train,0.9031979256698358
+0.1858718610654776,expressions,train,0.9044943820224719
+0.18657592114527105,expressions,train,0.9044943820224719
+0.18657592114527105,expressions,train,0.9053586862575627
+0.18774935461159353,expressions,train,0.9053586862575627
+0.18774935461159353,expressions,train,0.905790838375108
+0.18798404130485802,expressions,train,0.905790838375108
+0.18798404130485802,expressions,train,0.9062229904926534
+0.188453414691387,expressions,train,0.9062229904926534
+0.188453414691387,expressions,train,0.9066551426101987
+0.188922788077916,expressions,train,0.9066551426101987
+0.188922788077916,expressions,train,0.9070872947277442
+0.18915747477118047,expressions,train,0.9070872947277442
+0.18915747477118047,expressions,train,0.9075194468452895
+0.18962684815770947,expressions,train,0.9075194468452895
+0.18962684815770947,expressions,train,0.907951598962835
+0.18986153485097396,expressions,train,0.907951598962835
+0.18986153485097396,expressions,train,0.9083837510803803
+0.1905655949307674,expressions,train,0.9083837510803803
+0.1905655949307674,expressions,train,0.9088159031979257
+0.19080028162403193,expressions,train,0.9088159031979257
+0.19080028162403193,expressions,train,0.9096802074330165
+0.19150434170382538,expressions,train,0.9096802074330165
+0.19150434170382538,expressions,train,0.9101123595505618
+0.1917390283970899,expressions,train,0.9101123595505618
+0.1917390283970899,expressions,train,0.9105445116681071
+0.19197371509035438,expressions,train,0.9105445116681071
+0.19197371509035438,expressions,train,0.9109766637856526
+0.19291246186341235,expressions,train,0.9109766637856526
+0.19291246186341235,expressions,train,0.9114088159031979
+0.19338183524994132,expressions,train,0.9114088159031979
+0.19338183524994132,expressions,train,0.9118409680207433
+0.19385120863647032,expressions,train,0.9118409680207433
+0.19385120863647032,expressions,train,0.9131374243733794
+0.1943205820229993,expressions,train,0.9131374243733794
+0.1943205820229993,expressions,train,0.9135695764909249
+0.19737150903543768,expressions,train,0.9135695764909249
+0.19737150903543768,expressions,train,0.9140017286084702
+0.19831025580849565,expressions,train,0.9140017286084702
+0.19831025580849565,expressions,train,0.9144338807260155
+0.1994836892748181,expressions,train,0.9144338807260155
+0.1994836892748181,expressions,train,0.9148660328435609
+0.20112649612766956,expressions,train,0.9148660328435609
+0.20112649612766956,expressions,train,0.9152981849611063
+0.20394273644684346,expressions,train,0.9152981849611063
+0.20394273644684346,expressions,train,0.9157303370786517
+0.20441210983337244,expressions,train,0.9157303370786517
+0.20441210983337244,expressions,train,0.916162489196197
+0.20511616991316592,expressions,train,0.916162489196197
+0.20511616991316592,expressions,train,0.9165946413137425
+0.20558554329969492,expressions,train,0.9165946413137425
+0.20558554329969492,expressions,train,0.9170267934312878
+0.20628960337948837,expressions,train,0.9170267934312878
+0.20628960337948837,expressions,train,0.9178910976663786
+0.20675897676601737,expressions,train,0.9178910976663786
+0.20675897676601737,expressions,train,0.9187554019014693
+0.20699366345928186,expressions,train,0.9187554019014693
+0.20699366345928186,expressions,train,0.9191875540190146
+0.20722835015254634,expressions,train,0.9191875540190146
+0.20722835015254634,expressions,train,0.9196197061365601
+0.2088711570053978,expressions,train,0.9196197061365601
+0.2088711570053978,expressions,train,0.9204840103716508
+0.21239145740436519,expressions,train,0.9204840103716508
+0.21239145740436519,expressions,train,0.9209161624891962
+0.21262614409762967,expressions,train,0.9209161624891962
+0.21262614409762967,expressions,train,0.9213483146067416
+0.21286083079089416,expressions,train,0.9213483146067416
+0.21286083079089416,expressions,train,0.9217804667242869
+0.21309551748415864,expressions,train,0.9217804667242869
+0.21309551748415864,expressions,train,0.9226447709593777
+0.21356489087068764,expressions,train,0.9226447709593777
+0.21356489087068764,expressions,train,0.9230769230769231
+0.21379957756395213,expressions,train,0.9230769230769231
+0.21379957756395213,expressions,train,0.9235090751944685
+0.21685050457639052,expressions,train,0.9235090751944685
+0.21685050457639052,expressions,train,0.9239412273120138
+0.217085191269655,expressions,train,0.9239412273120138
+0.217085191269655,expressions,train,0.9243733794295592
+0.21966674489556443,expressions,train,0.9243733794295592
+0.21966674489556443,expressions,train,0.9248055315471045
+0.22154423844168036,expressions,train,0.9248055315471045
+0.22154423844168036,expressions,train,0.92523768366465
+0.22248298521473833,expressions,train,0.92523768366465
+0.22248298521473833,expressions,train,0.9256698357821953
+0.22271767190800282,expressions,train,0.9256698357821953
+0.22271767190800282,expressions,train,0.9261019878997407
+0.22459516545411876,expressions,train,0.9261019878997407
+0.22459516545411876,expressions,train,0.9273984442523768
+0.22553391222717672,expressions,train,0.9273984442523768
+0.22553391222717672,expressions,train,0.9282627484874676
+0.2257685989204412,expressions,train,0.9282627484874676
+0.2257685989204412,expressions,train,0.9286949006050129
+0.2264726590002347,expressions,train,0.9286949006050129
+0.2264726590002347,expressions,train,0.9295592048401037
+0.22694203238676366,expressions,train,0.9295592048401037
+0.22694203238676366,expressions,train,0.9299913569576491
+0.22788077915982163,expressions,train,0.9299913569576491
+0.22788077915982163,expressions,train,0.9304235090751944
+0.22858483923961512,expressions,train,0.9304235090751944
+0.22858483923961512,expressions,train,0.9317199654278306
+0.2295235860126731,expressions,train,0.9317199654278306
+0.2295235860126731,expressions,train,0.932152117545376
+0.22999295939920206,expressions,train,0.932152117545376
+0.22999295939920206,expressions,train,0.9325842696629213
+0.23046233278573106,expressions,train,0.9325842696629213
+0.23046233278573106,expressions,train,0.9330164217804667
+0.23093170617226003,expressions,train,0.9330164217804667
+0.23093170617226003,expressions,train,0.9338807260155575
+0.23210513963858248,expressions,train,0.9338807260155575
+0.23210513963858248,expressions,train,0.9343128781331028
+0.23257451302511148,expressions,train,0.9343128781331028
+0.23257451302511148,expressions,train,0.9347450302506483
+0.23351325979816945,expressions,train,0.9347450302506483
+0.23351325979816945,expressions,train,0.9351771823681936
+0.23398263318469842,expressions,train,0.9351771823681936
+0.23398263318469842,expressions,train,0.935609334485739
+0.2351560666510209,expressions,train,0.935609334485739
+0.2351560666510209,expressions,train,0.9364736387208298
+0.23632950011734336,expressions,train,0.9364736387208298
+0.23632950011734336,expressions,train,0.9369057908383751
+0.2375029335836658,expressions,train,0.9369057908383751
+0.2375029335836658,expressions,train,0.9373379429559204
+0.23844168035672378,expressions,train,0.9373379429559204
+0.23844168035672378,expressions,train,0.9382022471910112
+0.23891105374325275,expressions,train,0.9382022471910112
+0.23891105374325275,expressions,train,0.9386343993085566
+0.23961511382304623,expressions,train,0.9386343993085566
+0.23961511382304623,expressions,train,0.939066551426102
+0.2405538605961042,expressions,train,0.939066551426102
+0.2405538605961042,expressions,train,0.9403630077787382
+0.2407885472893687,expressions,train,0.9403630077787382
+0.2407885472893687,expressions,train,0.9407951598962835
+0.24172729406242666,expressions,train,0.9407951598962835
+0.24172729406242666,expressions,train,0.9412273120138289
+0.24383947430180708,expressions,train,0.9412273120138289
+0.24383947430180708,expressions,train,0.942523768366465
+0.24618634123445202,expressions,train,0.942523768366465
+0.24618634123445202,expressions,train,0.9429559204840103
+0.246655714620981,expressions,train,0.9429559204840103
+0.246655714620981,expressions,train,0.9433880726015558
+0.2487678948603614,expressions,train,0.9433880726015558
+0.2487678948603614,expressions,train,0.9438202247191011
+0.2515841351795353,expressions,train,0.9438202247191011
+0.2515841351795353,expressions,train,0.9446845289541919
+0.2527575686458578,expressions,train,0.9446845289541919
+0.2527575686458578,expressions,train,0.9451166810717373
+0.25369631541891574,expressions,train,0.9451166810717373
+0.25369631541891574,expressions,train,0.9455488331892826
+0.25932879605726356,expressions,train,0.9455488331892826
+0.25932879605726356,expressions,train,0.945980985306828
+0.26261440976296646,expressions,train,0.945980985306828
+0.26261440976296646,expressions,train,0.9464131374243734
+0.2635531565360244,expressions,train,0.9464131374243734
+0.2635531565360244,expressions,train,0.9472774416594641
+0.2640225299225534,expressions,train,0.9472774416594641
+0.2640225299225534,expressions,train,0.9477095937770095
+0.26636939685519834,expressions,train,0.9477095937770095
+0.26636939685519834,expressions,train,0.9481417458945549
+0.2670734569349918,expressions,train,0.9481417458945549
+0.2670734569349918,expressions,train,0.9485738980121002
+0.2694203238676367,expressions,train,0.9485738980121002
+0.2694203238676367,expressions,train,0.949438202247191
+0.27106313072048815,expressions,train,0.949438202247191
+0.27106313072048815,expressions,train,0.9498703543647364
+0.2715325041070171,expressions,train,0.9498703543647364
+0.2715325041070171,expressions,train,0.9507346585998271
+0.27434874442619106,expressions,train,0.9507346585998271
+0.27434874442619106,expressions,train,0.9515989628349178
+0.2750528045059845,expressions,train,0.9515989628349178
+0.2750528045059845,expressions,train,0.9524632670700086
+0.2799812250645388,expressions,train,0.9524632670700086
+0.2799812250645388,expressions,train,0.952895419187554
+0.28021591175780336,expressions,train,0.952895419187554
+0.28021591175780336,expressions,train,0.9533275713050994
+0.2809199718375968,expressions,train,0.9533275713050994
+0.2809199718375968,expressions,train,0.9541918755401901
+0.28209340530391924,expressions,train,0.9541918755401901
+0.28209340530391924,expressions,train,0.9546240276577356
+0.2832668387702417,expressions,train,0.9546240276577356
+0.2832668387702417,expressions,train,0.9550561797752809
+0.28514433231635766,expressions,train,0.9550561797752809
+0.28514433231635766,expressions,train,0.9554883318928262
+0.2867871391692091,expressions,train,0.9554883318928262
+0.2867871391692091,expressions,train,0.9559204840103717
+0.28866463271532505,expressions,train,0.9559204840103717
+0.28866463271532505,expressions,train,0.956352636127917
+0.289134006101854,expressions,train,0.956352636127917
+0.289134006101854,expressions,train,0.9567847882454624
+0.29007275287491197,expressions,train,0.9567847882454624
+0.29007275287491197,expressions,train,0.9572169403630078
+0.2917155597277634,expressions,train,0.9572169403630078
+0.2917155597277634,expressions,train,0.9576490924805532
+0.2928889931940859,expressions,train,0.9576490924805532
+0.2928889931940859,expressions,train,0.9580812445980985
+0.2952358601267308,expressions,train,0.9580812445980985
+0.2952358601267308,expressions,train,0.958513396715644
+0.29593992020652427,expressions,train,0.958513396715644
+0.29593992020652427,expressions,train,0.9589455488331893
+0.29946022060549166,expressions,train,0.9589455488331893
+0.29946022060549166,expressions,train,0.9593777009507347
+0.3013377141516076,expressions,train,0.9593777009507347
+0.3013377141516076,expressions,train,0.95980985306828
+0.3025111476179301,expressions,train,0.95980985306828
+0.3025111476179301,expressions,train,0.9602420051858254
+0.3036845810842525,expressions,train,0.9602420051858254
+0.3036845810842525,expressions,train,0.9606741573033708
+0.304858014550575,expressions,train,0.9606741573033708
+0.304858014550575,expressions,train,0.9611063094209161
+0.30556207463036844,expressions,train,0.9611063094209161
+0.30556207463036844,expressions,train,0.9615384615384616
+0.3069701947899554,expressions,train,0.9615384615384616
+0.3069701947899554,expressions,train,0.9619706136560069
+0.3081436282562779,expressions,train,0.9619706136560069
+0.3081436282562779,expressions,train,0.9624027657735523
+0.30861300164280686,expressions,train,0.9624027657735523
+0.30861300164280686,expressions,train,0.9628349178910977
+0.3095517484158648,expressions,train,0.9628349178910977
+0.3095517484158648,expressions,train,0.9632670700086431
+0.31002112180239383,expressions,train,0.9632670700086431
+0.31002112180239383,expressions,train,0.9636992221261884
+0.31119455526871626,expressions,train,0.9636992221261884
+0.31119455526871626,expressions,train,0.9641313742437337
+0.3142454822811547,expressions,train,0.9641313742437337
+0.3142454822811547,expressions,train,0.9645635263612792
+0.32034733630603146,expressions,train,0.9645635263612792
+0.32034733630603146,expressions,train,0.9654278305963699
+0.3243370100915278,expressions,train,0.9654278305963699
+0.3243370100915278,expressions,train,0.9662921348314607
+0.32762262379723067,expressions,train,0.9662921348314607
+0.32762262379723067,expressions,train,0.966724286949006
+0.32903074395681764,expressions,train,0.966724286949006
+0.32903074395681764,expressions,train,0.9675885911840968
+0.33231635766252055,expressions,train,0.9675885911840968
+0.33231635766252055,expressions,train,0.9680207433016422
+0.333020417742314,expressions,train,0.9680207433016422
+0.333020417742314,expressions,train,0.9684528954191876
+0.3360713447547524,expressions,train,0.9684528954191876
+0.3360713447547524,expressions,train,0.9688850475367329
+0.3391222717671908,expressions,train,0.9688850475367329
+0.3391222717671908,expressions,train,0.9693171996542783
+0.3426425721661582,expressions,train,0.9693171996542783
+0.3426425721661582,expressions,train,0.9697493517718236
+0.34405069232574514,expressions,train,0.9697493517718236
+0.34405069232574514,expressions,train,0.9701815038893691
+0.3445200657122741,expressions,train,0.9701815038893691
+0.3445200657122741,expressions,train,0.9706136560069144
+0.3447547524055386,expressions,train,0.9706136560069144
+0.3447547524055386,expressions,train,0.9710458081244598
+0.34545881248533206,expressions,train,0.9710458081244598
+0.34545881248533206,expressions,train,0.9719101123595506
+0.35789720722835017,expressions,train,0.9719101123595506
+0.35789720722835017,expressions,train,0.9723422644770959
+0.36634592818587186,expressions,train,0.9723422644770959
+0.36634592818587186,expressions,train,0.9727744165946414
+0.36751936165219434,expressions,train,0.9727744165946414
+0.36751936165219434,expressions,train,0.9732065687121867
+0.36775404834545883,expressions,train,0.9732065687121867
+0.36775404834545883,expressions,train,0.9740708729472775
+0.3679887350387233,expressions,train,0.9740708729472775
+0.3679887350387233,expressions,train,0.9745030250648228
+0.36986622858483925,expressions,train,0.9745030250648228
+0.36986622858483925,expressions,train,0.9749351771823682
+0.3710396620511617,expressions,train,0.9749351771823682
+0.3710396620511617,expressions,train,0.9753673292999135
+0.3719784088242197,expressions,train,0.9753673292999135
+0.3719784088242197,expressions,train,0.975799481417459
+0.3731518422905421,expressions,train,0.975799481417459
+0.3731518422905421,expressions,train,0.9762316335350043
+0.37479464914339355,expressions,train,0.9762316335350043
+0.37479464914339355,expressions,train,0.9766637856525497
+0.37502933583665804,expressions,train,0.9766637856525497
+0.37502933583665804,expressions,train,0.9770959377700951
+0.3790190096221544,expressions,train,0.9770959377700951
+0.3790190096221544,expressions,train,0.9775280898876404
+0.3827739967143863,expressions,train,0.9775280898876404
+0.3827739967143863,expressions,train,0.9779602420051858
+0.38676367049988264,expressions,train,0.9779602420051858
+0.38676367049988264,expressions,train,0.9783923941227312
+0.3938042712978174,expressions,train,0.9783923941227312
+0.3938042712978174,expressions,train,0.9788245462402766
+0.39591645153719784,expressions,train,0.9788245462402766
+0.39591645153719784,expressions,train,0.9792566983578219
+0.3989673785496362,expressions,train,0.9792566983578219
+0.3989673785496362,expressions,train,0.9796888504753674
+0.4081201595869514,expressions,train,0.9796888504753674
+0.4081201595869514,expressions,train,0.9801210025929127
+0.4121098333724478,expressions,train,0.9801210025929127
+0.4121098333724478,expressions,train,0.9805531547104581
+0.4149260736916217,expressions,train,0.9805531547104581
+0.4149260736916217,expressions,train,0.9809853068280034
+0.41961980755691153,expressions,train,0.9809853068280034
+0.41961980755691153,expressions,train,0.9814174589455489
+0.42055855432996947,expressions,train,0.9814174589455489
+0.42055855432996947,expressions,train,0.9818496110630942
+0.42454822811546583,expressions,train,0.9818496110630942
+0.42454822811546583,expressions,train,0.9822817631806395
+0.4294766486740202,expressions,train,0.9822817631806395
+0.4294766486740202,expressions,train,0.982713915298185
+0.4297113353672847,expressions,train,0.982713915298185
+0.4297113353672847,expressions,train,0.9831460674157303
+0.4348744426191035,expressions,train,0.9831460674157303
+0.4348744426191035,expressions,train,0.9835782195332757
+0.435578502698897,expressions,train,0.9835782195332757
+0.435578502698897,expressions,train,0.9840103716508211
+0.4388641164045999,expressions,train,0.9840103716508211
+0.4388641164045999,expressions,train,0.9844425237683665
+0.44426191034968315,expressions,train,0.9844425237683665
+0.44426191034968315,expressions,train,0.9853068280034573
+0.4482515841351795,expressions,train,0.9853068280034573
+0.4482515841351795,expressions,train,0.9857389801210026
+0.4505984510678245,expressions,train,0.9857389801210026
+0.4505984510678245,expressions,train,0.986171132238548
+0.4524759446139404,expressions,train,0.986171132238548
+0.4524759446139404,expressions,train,0.9866032843560933
+0.4602206054916686,expressions,train,0.9866032843560933
+0.4602206054916686,expressions,train,0.9870354364736387
+0.4698427599155128,expressions,train,0.9870354364736387
+0.4698427599155128,expressions,train,0.9874675885911841
+0.4719549401548932,expressions,train,0.9874675885911841
+0.4719549401548932,expressions,train,0.9878997407087294
+0.4843933348979113,expressions,train,0.9878997407087294
+0.4843933348979113,expressions,train,0.9883318928262749
+0.48556676836423374,expressions,train,0.9883318928262749
+0.48556676836423374,expressions,train,0.9887640449438202
+0.5005867167331612,expressions,train,0.9887640449438202
+0.5005867167331612,expressions,train,0.9891961970613656
+0.5012907768129548,expressions,train,0.9891961970613656
+0.5012907768129548,expressions,train,0.989628349178911
+0.5052804505984511,expressions,train,0.989628349178911
+0.5052804505984511,expressions,train,0.9900605012964564
+0.5130251114761794,expressions,train,0.9900605012964564
+0.5130251114761794,expressions,train,0.9904926534140017
+0.5181882187279981,expressions,train,0.9904926534140017
+0.5181882187279981,expressions,train,0.9909248055315472
+0.5282797465383713,expressions,train,0.9909248055315472
+0.5282797465383713,expressions,train,0.9913569576490925
+0.5285144332316357,expressions,train,0.9913569576490925
+0.5285144332316357,expressions,train,0.9917891097666378
+0.5461159352264726,expressions,train,0.9917891097666378
+0.5461159352264726,expressions,train,0.9922212618841832
+0.5714620980990378,expressions,train,0.9922212618841832
+0.5714620980990378,expressions,train,0.9926534140017286
+0.6061957287021826,expressions,train,0.9926534140017286
+0.6061957287021826,expressions,train,0.993085566119274
+0.6108894625674725,expressions,train,0.993085566119274
+0.6108894625674725,expressions,train,0.9935177182368193
+0.6207463036845811,expressions,train,0.9935177182368193
+0.6207463036845811,expressions,train,0.9939498703543648
+0.6629899084721896,expressions,train,0.9939498703543648
+0.6629899084721896,expressions,train,0.9943820224719101
+0.6784792302276461,expressions,train,0.9943820224719101
+0.6784792302276461,expressions,train,0.9948141745894555
+0.6996010326214503,expressions,train,0.9948141745894555
+0.6996010326214503,expressions,train,0.9952463267070009
+0.7265900023468669,expressions,train,0.9952463267070009
+0.7265900023468669,expressions,train,0.9956784788245462
+0.7862004224360479,expressions,train,0.9956784788245462
+0.7862004224360479,expressions,train,0.9961106309420916
+0.7998122506453884,expressions,train,0.9961106309420916
+0.7998122506453884,expressions,train,0.996542783059637
+0.8246890401314245,expressions,train,0.996542783059637
+0.8246890401314245,expressions,train,0.9969749351771824
+0.8338418211687397,expressions,train,0.9969749351771824
+0.8338418211687397,expressions,train,0.9974070872947277
+0.8352499413283266,expressions,train,0.9974070872947277
+0.8352499413283266,expressions,train,0.9978392394122731
+0.8392396151138231,expressions,train,0.9978392394122731
+0.8392396151138231,expressions,train,0.9982713915298185
+0.8530861300164281,expressions,train,0.9982713915298185
+0.8530861300164281,expressions,train,0.9987035436473639
+0.8819525932879606,expressions,train,0.9987035436473639
+0.8819525932879606,expressions,train,0.9991356957649092
+0.8842994602206055,expressions,train,0.9991356957649092
+0.8842994602206055,expressions,train,0.9995678478824547
+0.8878197606195729,expressions,train,0.9995678478824547
+0.8878197606195729,expressions,train,1.0
+1.0,expressions,train,1.0
+0.0,covariates,test,0.0
+0.002183406113537118,covariates,test,0.0
+0.004366812227074236,covariates,test,0.0
+0.004366812227074236,covariates,test,0.007326007326007326
+0.006550218340611353,covariates,test,0.007326007326007326
+0.006550218340611353,covariates,test,0.02197802197802198
+0.008733624454148471,covariates,test,0.02197802197802198
+0.008733624454148471,covariates,test,0.029304029304029304
+0.010917030567685589,covariates,test,0.029304029304029304
+0.010917030567685589,covariates,test,0.047619047619047616
+0.010917030567685589,covariates,test,0.054945054945054944
+0.013100436681222707,covariates,test,0.054945054945054944
+0.013100436681222707,covariates,test,0.06593406593406594
+0.015283842794759825,covariates,test,0.06593406593406594
+0.015283842794759825,covariates,test,0.09157509157509157
+0.017467248908296942,covariates,test,0.09157509157509157
+0.017467248908296942,covariates,test,0.10622710622710622
+0.017467248908296942,covariates,test,0.11355311355311355
+0.017467248908296942,covariates,test,0.1391941391941392
+0.019650655021834062,covariates,test,0.1391941391941392
+0.019650655021834062,covariates,test,0.15384615384615385
+0.024017467248908297,covariates,test,0.15384615384615385
+0.026200873362445413,covariates,test,0.15384615384615385
+0.026200873362445413,covariates,test,0.18315018315018314
+0.028384279475982533,covariates,test,0.18315018315018314
+0.028384279475982533,covariates,test,0.18681318681318682
+0.03275109170305677,covariates,test,0.18681318681318682
+0.03275109170305677,covariates,test,0.19413919413919414
+0.03711790393013101,covariates,test,0.19413919413919414
+0.03711790393013101,covariates,test,0.21245421245421245
+0.039301310043668124,covariates,test,0.21245421245421245
+0.039301310043668124,covariates,test,0.21978021978021978
+0.039301310043668124,covariates,test,0.2271062271062271
+0.04148471615720524,covariates,test,0.2271062271062271
+0.04148471615720524,covariates,test,0.23443223443223443
+0.043668122270742356,covariates,test,0.23443223443223443
+0.043668122270742356,covariates,test,0.23809523809523808
+0.04585152838427948,covariates,test,0.23809523809523808
+0.04585152838427948,covariates,test,0.24175824175824176
+0.048034934497816595,covariates,test,0.24175824175824176
+0.048034934497816595,covariates,test,0.2600732600732601
+0.05021834061135371,covariates,test,0.2600732600732601
+0.05021834061135371,covariates,test,0.2783882783882784
+0.05240174672489083,covariates,test,0.2783882783882784
+0.05240174672489083,covariates,test,0.2857142857142857
+0.05458515283842795,covariates,test,0.2857142857142857
+0.05458515283842795,covariates,test,0.29304029304029305
+0.05458515283842795,covariates,test,0.30036630036630035
+0.05458515283842795,covariates,test,0.37362637362637363
+0.056768558951965066,covariates,test,0.37362637362637363
+0.056768558951965066,covariates,test,0.42124542124542125
+0.0611353711790393,covariates,test,0.42124542124542125
+0.0611353711790393,covariates,test,0.42857142857142855
+0.06550218340611354,covariates,test,0.42857142857142855
+0.06768558951965066,covariates,test,0.43223443223443225
+0.06768558951965066,covariates,test,0.45054945054945056
+0.06986899563318777,covariates,test,0.4542124542124542
+0.06986899563318777,covariates,test,0.46153846153846156
+0.06986899563318777,covariates,test,0.4652014652014652
+0.07423580786026202,covariates,test,0.4652014652014652
+0.07423580786026202,covariates,test,0.47985347985347987
+0.07860262008733625,covariates,test,0.47985347985347987
+0.07860262008733625,covariates,test,0.4835164835164835
+0.08078602620087336,covariates,test,0.4835164835164835
+0.08078602620087336,covariates,test,0.4908424908424908
+0.0851528384279476,covariates,test,0.4908424908424908
+0.0851528384279476,covariates,test,0.5091575091575091
+0.08733624454148471,covariates,test,0.5091575091575091
+0.08951965065502183,covariates,test,0.5128205128205128
+0.08951965065502183,covariates,test,0.5201465201465202
+0.09388646288209607,covariates,test,0.5201465201465202
+0.09388646288209607,covariates,test,0.5311355311355311
+0.09606986899563319,covariates,test,0.5311355311355311
+0.09606986899563319,covariates,test,0.5347985347985348
+0.0982532751091703,covariates,test,0.5347985347985348
+0.0982532751091703,covariates,test,0.5384615384615384
+0.10043668122270742,covariates,test,0.5384615384615384
+0.10043668122270742,covariates,test,0.5457875457875457
+0.10698689956331878,covariates,test,0.5457875457875457
+0.10698689956331878,covariates,test,0.5494505494505495
+0.10698689956331878,covariates,test,0.5567765567765568
+0.10698689956331878,covariates,test,0.5604395604395604
+0.1091703056768559,covariates,test,0.5604395604395604
+0.1091703056768559,covariates,test,0.5677655677655677
+0.11353711790393013,covariates,test,0.5677655677655677
+0.11353711790393013,covariates,test,0.5934065934065934
+0.11572052401746726,covariates,test,0.5934065934065934
+0.11572052401746726,covariates,test,0.5970695970695971
+0.11790393013100436,covariates,test,0.6007326007326007
+0.12008733624454149,covariates,test,0.6007326007326007
+0.12008733624454149,covariates,test,0.608058608058608
+0.12663755458515283,covariates,test,0.608058608058608
+0.12663755458515283,covariates,test,0.6117216117216118
+0.13100436681222707,covariates,test,0.6117216117216118
+0.13100436681222707,covariates,test,0.6153846153846154
+0.1331877729257642,covariates,test,0.6153846153846154
+0.1331877729257642,covariates,test,0.6190476190476191
+0.13537117903930132,covariates,test,0.6190476190476191
+0.13537117903930132,covariates,test,0.6263736263736264
+0.13973799126637554,covariates,test,0.6263736263736264
+0.13973799126637554,covariates,test,0.63003663003663
+0.1462882096069869,covariates,test,0.63003663003663
+0.1462882096069869,covariates,test,0.6336996336996337
+0.14847161572052403,covariates,test,0.6336996336996337
+0.14847161572052403,covariates,test,0.6410256410256411
+0.1615720524017467,covariates,test,0.6410256410256411
+0.1615720524017467,covariates,test,0.652014652014652
+0.16375545851528384,covariates,test,0.652014652014652
+0.16375545851528384,covariates,test,0.6556776556776557
+0.16593886462882096,covariates,test,0.6556776556776557
+0.16593886462882096,covariates,test,0.663003663003663
+0.16812227074235808,covariates,test,0.663003663003663
+0.16812227074235808,covariates,test,0.6703296703296703
+0.1703056768558952,covariates,test,0.6703296703296703
+0.1703056768558952,covariates,test,0.6776556776556777
+0.17248908296943233,covariates,test,0.6776556776556777
+0.17248908296943233,covariates,test,0.684981684981685
+0.17467248908296942,covariates,test,0.684981684981685
+0.17467248908296942,covariates,test,0.6886446886446886
+0.17685589519650655,covariates,test,0.6886446886446886
+0.17685589519650655,covariates,test,0.6923076923076923
+0.17903930131004367,covariates,test,0.6923076923076923
+0.17903930131004367,covariates,test,0.6959706959706959
+0.1812227074235808,covariates,test,0.6959706959706959
+0.1812227074235808,covariates,test,0.6996336996336996
+0.18340611353711792,covariates,test,0.6996336996336996
+0.185589519650655,covariates,test,0.7032967032967034
+0.18777292576419213,covariates,test,0.7032967032967034
+0.18777292576419213,covariates,test,0.7216117216117216
+0.19213973799126638,covariates,test,0.7216117216117216
+0.19213973799126638,covariates,test,0.7252747252747253
+0.1943231441048035,covariates,test,0.7252747252747253
+0.1943231441048035,covariates,test,0.7289377289377289
+0.1965065502183406,covariates,test,0.7326007326007326
+0.19868995633187772,covariates,test,0.7326007326007326
+0.19868995633187772,covariates,test,0.7362637362637363
+0.20087336244541484,covariates,test,0.73992673992674
+0.2052401746724891,covariates,test,0.73992673992674
+0.2052401746724891,covariates,test,0.7472527472527473
+0.2096069868995633,covariates,test,0.7472527472527473
+0.2096069868995633,covariates,test,0.7545787545787546
+0.2096069868995633,covariates,test,0.7619047619047619
+0.2183406113537118,covariates,test,0.7619047619047619
+0.2183406113537118,covariates,test,0.7692307692307693
+0.2205240174672489,covariates,test,0.7728937728937729
+0.2292576419213974,covariates,test,0.7728937728937729
+0.2292576419213974,covariates,test,0.7765567765567766
+0.23580786026200873,covariates,test,0.7765567765567766
+0.23580786026200873,covariates,test,0.7838827838827839
+0.25327510917030566,covariates,test,0.7838827838827839
+0.259825327510917,covariates,test,0.7838827838827839
+0.259825327510917,covariates,test,0.7912087912087912
+0.27074235807860264,covariates,test,0.7912087912087912
+0.27074235807860264,covariates,test,0.7948717948717948
+0.27292576419213976,covariates,test,0.7948717948717948
+0.27292576419213976,covariates,test,0.7985347985347986
+0.27292576419213976,covariates,test,0.8058608058608059
+0.27510917030567683,covariates,test,0.8058608058608059
+0.27510917030567683,covariates,test,0.8095238095238095
+0.27729257641921395,covariates,test,0.8095238095238095
+0.2794759825327511,covariates,test,0.8168498168498168
+0.2794759825327511,covariates,test,0.8205128205128205
+0.2838427947598253,covariates,test,0.8205128205128205
+0.28820960698689957,covariates,test,0.8205128205128205
+0.2903930131004367,covariates,test,0.8205128205128205
+0.29475982532751094,covariates,test,0.8205128205128205
+0.29912663755458513,covariates,test,0.8278388278388278
+0.29912663755458513,covariates,test,0.8315018315018315
+0.3034934497816594,covariates,test,0.8315018315018315
+0.3056768558951965,covariates,test,0.8424908424908425
+0.3078602620087336,covariates,test,0.8424908424908425
+0.3078602620087336,covariates,test,0.8461538461538461
+0.3165938864628821,covariates,test,0.8461538461538461
+0.3165938864628821,covariates,test,0.8534798534798534
+0.31877729257641924,covariates,test,0.8534798534798534
+0.32096069868995636,covariates,test,0.8644688644688645
+0.3231441048034934,covariates,test,0.8717948717948718
+0.3231441048034934,covariates,test,0.8791208791208791
+0.32751091703056767,covariates,test,0.8791208791208791
+0.3296943231441048,covariates,test,0.8827838827838828
+0.3406113537117904,covariates,test,0.8827838827838828
+0.3406113537117904,covariates,test,0.8864468864468864
+0.34497816593886466,covariates,test,0.8901098901098901
+0.3471615720524017,covariates,test,0.8901098901098901
+0.3537117903930131,covariates,test,0.8937728937728938
+0.3558951965065502,covariates,test,0.8937728937728938
+0.36026200873362446,covariates,test,0.8937728937728938
+0.3624454148471616,covariates,test,0.8974358974358975
+0.3646288209606987,covariates,test,0.8974358974358975
+0.36681222707423583,covariates,test,0.9010989010989011
+0.37336244541484714,covariates,test,0.9010989010989011
+0.37554585152838427,covariates,test,0.9010989010989011
+0.3799126637554585,covariates,test,0.9084249084249084
+0.3799126637554585,covariates,test,0.9157509157509157
+0.38209606986899564,covariates,test,0.9157509157509157
+0.38427947598253276,covariates,test,0.9194139194139194
+0.3864628820960699,covariates,test,0.9194139194139194
+0.39082969432314413,covariates,test,0.9194139194139194
+0.3930131004366812,covariates,test,0.9194139194139194
+0.3930131004366812,covariates,test,0.9230769230769231
+0.39737991266375544,covariates,test,0.9230769230769231
+0.39956331877729256,covariates,test,0.9267399267399268
+0.4017467248908297,covariates,test,0.9267399267399268
+0.4017467248908297,covariates,test,0.9304029304029304
+0.4039301310043668,covariates,test,0.9304029304029304
+0.40611353711790393,covariates,test,0.9340659340659341
+0.40829694323144106,covariates,test,0.9340659340659341
+0.4126637554585153,covariates,test,0.9340659340659341
+0.4192139737991266,covariates,test,0.9340659340659341
+0.425764192139738,covariates,test,0.9377289377289377
+0.43231441048034935,covariates,test,0.9377289377289377
+0.4366812227074236,covariates,test,0.9377289377289377
+0.4388646288209607,covariates,test,0.9377289377289377
+0.4388646288209607,covariates,test,0.9413919413919414
+0.4432314410480349,covariates,test,0.9413919413919414
+0.4497816593886463,covariates,test,0.945054945054945
+0.45414847161572053,covariates,test,0.945054945054945
+0.4585152838427948,covariates,test,0.945054945054945
+0.4585152838427948,covariates,test,0.9487179487179487
+0.4650655021834061,covariates,test,0.9487179487179487
+0.4672489082969432,covariates,test,0.9560439560439561
+0.47161572052401746,covariates,test,0.9560439560439561
+0.4759825327510917,covariates,test,0.9560439560439561
+0.48034934497816595,covariates,test,0.9633699633699634
+0.4868995633187773,covariates,test,0.9633699633699634
+0.4912663755458515,covariates,test,0.9633699633699634
+0.49563318777292575,covariates,test,0.9633699633699634
+0.5,covariates,test,0.9633699633699634
+0.5065502183406113,covariates,test,0.9633699633699634
+0.5131004366812227,covariates,test,0.9633699633699634
+0.5152838427947598,covariates,test,0.9633699633699634
+0.5152838427947598,covariates,test,0.967032967032967
+0.519650655021834,covariates,test,0.967032967032967
+0.5218340611353712,covariates,test,0.967032967032967
+0.5218340611353712,covariates,test,0.9706959706959707
+0.5240174672489083,covariates,test,0.9706959706959707
+0.5262008733624454,covariates,test,0.9743589743589743
+0.537117903930131,covariates,test,0.9743589743589743
+0.537117903930131,covariates,test,0.978021978021978
+0.5545851528384279,covariates,test,0.978021978021978
+0.5545851528384279,covariates,test,0.9816849816849816
+0.5589519650655022,covariates,test,0.9816849816849816
+0.5589519650655022,covariates,test,0.9853479853479854
+0.5633187772925764,covariates,test,0.9853479853479854
+0.5633187772925764,covariates,test,0.989010989010989
+0.5676855895196506,covariates,test,0.989010989010989
+0.5676855895196506,covariates,test,0.9926739926739927
+0.6091703056768559,covariates,test,0.9926739926739927
+0.6091703056768559,covariates,test,1.0
+0.611353711790393,covariates,test,1.0
+0.6157205240174672,covariates,test,1.0
+0.6179039301310044,covariates,test,1.0
+0.6222707423580786,covariates,test,1.0
+0.6441048034934498,covariates,test,1.0
+0.6528384279475983,covariates,test,1.0
+0.6550218340611353,covariates,test,1.0
+0.6615720524017468,covariates,test,1.0
+0.665938864628821,covariates,test,1.0
+0.6703056768558951,covariates,test,1.0
+0.6724890829694323,covariates,test,1.0
+0.6790393013100436,covariates,test,1.0
+0.6834061135371179,covariates,test,1.0
+0.7052401746724891,covariates,test,1.0
+0.7096069868995634,covariates,test,1.0
+0.7183406113537117,covariates,test,1.0
+0.722707423580786,covariates,test,1.0
+0.7292576419213974,covariates,test,1.0
+0.7336244541484717,covariates,test,1.0
+0.740174672489083,covariates,test,1.0
+0.74235807860262,covariates,test,1.0
+0.7467248908296943,covariates,test,1.0
+0.7532751091703057,covariates,test,1.0
+0.75764192139738,covariates,test,1.0
+0.7641921397379913,covariates,test,1.0
+0.8165938864628821,covariates,test,1.0
+0.8209606986899564,covariates,test,1.0
+0.8406113537117904,covariates,test,1.0
+0.8449781659388647,covariates,test,1.0
+0.8537117903930131,covariates,test,1.0
+0.8580786026200873,covariates,test,1.0
+0.8646288209606987,covariates,test,1.0
+0.8668122270742358,covariates,test,1.0
+0.87117903930131,covariates,test,1.0
+0.8755458515283843,covariates,test,1.0
+0.8799126637554585,covariates,test,1.0
+0.8820960698689956,covariates,test,1.0
+0.8908296943231441,covariates,test,1.0
+0.8973799126637555,covariates,test,1.0
+0.9039301310043668,covariates,test,1.0
+0.9082969432314411,covariates,test,1.0
+0.9104803493449781,covariates,test,1.0
+0.9235807860262009,covariates,test,1.0
+0.925764192139738,covariates,test,1.0
+0.9388646288209607,covariates,test,1.0
+0.9432314410480349,covariates,test,1.0
+0.9475982532751092,covariates,test,1.0
+0.9519650655021834,covariates,test,1.0
+0.9563318777292577,covariates,test,1.0
+0.9585152838427947,covariates,test,1.0
+0.9672489082969432,covariates,test,1.0
+0.9694323144104804,covariates,test,1.0
+0.9781659388646288,covariates,test,1.0
+1.0,covariates,test,1.0
+0.0,covariates,train,0.000432152117545376
+0.0002346866932644919,covariates,train,0.000432152117545376
+0.0002346866932644919,covariates,train,0.0012964563526361278
+0.0007040600797934757,covariates,train,0.0012964563526361278
+0.0007040600797934757,covariates,train,0.006914433880726016
+0.0009387467730579676,covariates,train,0.006914433880726016
+0.0009387467730579676,covariates,train,0.009075194468452896
+0.0011734334663224596,covariates,train,0.009075194468452896
+0.0011734334663224596,covariates,train,0.013828867761452032
+0.0014081201595869514,covariates,train,0.014261019878997408
+0.0014081201595869514,covariates,train,0.022039757994814176
+0.0016428068528514432,covariates,train,0.022039757994814176
+0.0016428068528514432,covariates,train,0.02247191011235955
+0.0018774935461159353,covariates,train,0.02247191011235955
+0.0018774935461159353,covariates,train,0.024200518582541054
+0.0021121802393804273,covariates,train,0.024200518582541054
+0.0021121802393804273,covariates,train,0.025064822817631807
+0.002346866932644919,covariates,train,0.025064822817631807
+0.002346866932644919,covariates,train,0.027225583405358685
+0.002581553625909411,covariates,train,0.027225583405358685
+0.002581553625909411,covariates,train,0.028089887640449437
+0.002581553625909411,covariates,train,0.02895419187554019
+0.002581553625909411,covariates,train,0.030682800345721694
+0.002816240319173903,covariates,train,0.030682800345721694
+0.002816240319173903,covariates,train,0.03111495246326707
+0.002816240319173903,covariates,train,0.03197925669835782
+0.002816240319173903,covariates,train,0.03327571305099395
+0.0030509270124383947,covariates,train,0.03327571305099395
+0.0030509270124383947,covariates,train,0.033707865168539325
+0.0032856137057028865,covariates,train,0.033707865168539325
+0.0032856137057028865,covariates,train,0.035004321521175455
+0.0035203003989673787,covariates,train,0.035004321521175455
+0.0035203003989673787,covariates,train,0.035868625756266204
+0.0035203003989673787,covariates,train,0.03673292999135696
+0.0035203003989673787,covariates,train,0.037165082108902334
+0.0037549870922318706,covariates,train,0.037165082108902334
+0.0037549870922318706,covariates,train,0.038461538461538464
+0.0037549870922318706,covariates,train,0.03932584269662921
+0.0037549870922318706,covariates,train,0.03975799481417459
+0.003989673785496362,covariates,train,0.03975799481417459
+0.003989673785496362,covariates,train,0.044511668107173726
+0.004224360478760855,covariates,train,0.044511668107173726
+0.004224360478760855,covariates,train,0.04710458081244598
+0.004693733865289838,covariates,train,0.04710458081244598
+0.004693733865289838,covariates,train,0.04753673292999136
+0.00492842055855433,covariates,train,0.04753673292999136
+0.005163107251818822,covariates,train,0.04840103716508211
+0.005163107251818822,covariates,train,0.04883318928262748
+0.005163107251818822,covariates,train,0.04969749351771824
+0.005163107251818822,covariates,train,0.05012964563526361
+0.005397793945083313,covariates,train,0.05012964563526361
+0.005397793945083313,covariates,train,0.05056179775280899
+0.005632480638347806,covariates,train,0.05099394987035436
+0.005632480638347806,covariates,train,0.05142610198789974
+0.005632480638347806,covariates,train,0.05315471045808125
+0.005632480638347806,covariates,train,0.05445116681071737
+0.005632480638347806,covariates,train,0.0557476231633535
+0.005632480638347806,covariates,train,0.056179775280898875
+0.005632480638347806,covariates,train,0.057476231633535005
+0.005632480638347806,covariates,train,0.05790838375108038
+0.005632480638347806,covariates,train,0.058772687986171135
+0.005867167331612298,covariates,train,0.05920484010371651
+0.005867167331612298,covariates,train,0.06050129645635264
+0.005867167331612298,covariates,train,0.06352636127917027
+0.006101854024876789,covariates,train,0.06352636127917027
+0.006101854024876789,covariates,train,0.06395851339671564
+0.006101854024876789,covariates,train,0.06482281763180639
+0.006101854024876789,covariates,train,0.06568712186689715
+0.0063365407181412816,covariates,train,0.06568712186689715
+0.0063365407181412816,covariates,train,0.06611927398444252
+0.006571227411405773,covariates,train,0.06611927398444252
+0.006571227411405773,covariates,train,0.0665514261019879
+0.006805914104670265,covariates,train,0.0665514261019879
+0.006805914104670265,covariates,train,0.06741573033707865
+0.006805914104670265,covariates,train,0.0682800345721694
+0.0070406007979347575,covariates,train,0.0682800345721694
+0.007275287491199249,covariates,train,0.06871218668971478
+0.007275287491199249,covariates,train,0.06914433880726016
+0.007509974184463741,covariates,train,0.06957649092480553
+0.007509974184463741,covariates,train,0.07044079515989628
+0.007509974184463741,covariates,train,0.07173725151253241
+0.0077446608777282325,covariates,train,0.07173725151253241
+0.0077446608777282325,covariates,train,0.07216940363007779
+0.007979347570992725,covariates,train,0.07216940363007779
+0.008214034264257217,covariates,train,0.07389801210025929
+0.008214034264257217,covariates,train,0.07519446845289542
+0.008214034264257217,covariates,train,0.0756266205704408
+0.00844872095752171,covariates,train,0.07649092480553155
+0.00844872095752171,covariates,train,0.07692307692307693
+0.0086834076507862,covariates,train,0.07692307692307693
+0.0086834076507862,covariates,train,0.07821953327571306
+0.008918094344050692,covariates,train,0.07865168539325842
+0.009152781037315184,covariates,train,0.07865168539325842
+0.009387467730579677,covariates,train,0.0790838375108038
+0.009387467730579677,covariates,train,0.07951598962834917
+0.009387467730579677,covariates,train,0.08038029386343994
+0.009387467730579677,covariates,train,0.0808124459809853
+0.009387467730579677,covariates,train,0.08254105445116681
+0.009387467730579677,covariates,train,0.08556611927398444
+0.009387467730579677,covariates,train,0.08686257562662057
+0.009387467730579677,covariates,train,0.08772687986171132
+0.009622154423844167,covariates,train,0.08772687986171132
+0.00985684111710866,covariates,train,0.08945548833189283
+0.00985684111710866,covariates,train,0.09075194468452895
+0.010091527810373152,covariates,train,0.09075194468452895
+0.010091527810373152,covariates,train,0.09204840103716508
+0.010091527810373152,covariates,train,0.09248055315471046
+0.010326214503637644,covariates,train,0.09291270527225583
+0.010326214503637644,covariates,train,0.09377700950734659
+0.010326214503637644,covariates,train,0.09507346585998272
+0.010326214503637644,covariates,train,0.09593777009507347
+0.010326214503637644,covariates,train,0.09680207433016422
+0.010326214503637644,covariates,train,0.09766637856525497
+0.010326214503637644,covariates,train,0.09939498703543648
+0.010326214503637644,covariates,train,0.09982713915298184
+0.010326214503637644,covariates,train,0.10069144338807261
+0.010326214503637644,covariates,train,0.10112359550561797
+0.010326214503637644,covariates,train,0.10198789974070872
+0.010326214503637644,covariates,train,0.10328435609334485
+0.010326214503637644,covariates,train,0.10371650821089023
+0.010326214503637644,covariates,train,0.10458081244598098
+0.010326214503637644,covariates,train,0.10587726879861711
+0.010560901196902136,covariates,train,0.10587726879861711
+0.010795587890166627,covariates,train,0.1063094209161625
+0.010795587890166627,covariates,train,0.10717372515125324
+0.010795587890166627,covariates,train,0.10803802938634399
+0.011264961276695611,covariates,train,0.10803802938634399
+0.011264961276695611,covariates,train,0.10890233362143474
+0.011264961276695611,covariates,train,0.111495246326707
+0.011264961276695611,covariates,train,0.11192739844425238
+0.011264961276695611,covariates,train,0.11279170267934313
+0.011264961276695611,covariates,train,0.1132238547968885
+0.011264961276695611,covariates,train,0.11408815903197926
+0.011499647969960104,covariates,train,0.11408815903197926
+0.011734334663224596,covariates,train,0.11452031114952463
+0.011734334663224596,covariates,train,0.11495246326707001
+0.011734334663224596,covariates,train,0.11624891961970614
+0.011734334663224596,covariates,train,0.11797752808988764
+0.011969021356489086,covariates,train,0.11884183232497839
+0.012203708049753579,covariates,train,0.11884183232497839
+0.012203708049753579,covariates,train,0.11927398444252377
+0.012203708049753579,covariates,train,0.1205704407951599
+0.012203708049753579,covariates,train,0.12143474503025065
+0.012438394743018071,covariates,train,0.12186689714779603
+0.012438394743018071,covariates,train,0.1240276577355229
+0.012438394743018071,covariates,train,0.12489196197061365
+0.012673081436282563,covariates,train,0.12489196197061365
+0.012673081436282563,covariates,train,0.12662057044079517
+0.012907768129547055,covariates,train,0.12662057044079517
+0.012907768129547055,covariates,train,0.12791702679343128
+0.012907768129547055,covariates,train,0.12964563526361278
+0.013142454822811546,covariates,train,0.12964563526361278
+0.013142454822811546,covariates,train,0.13050993949870354
+0.013142454822811546,covariates,train,0.13180639585133966
+0.013377141516076038,covariates,train,0.13180639585133966
+0.013377141516076038,covariates,train,0.13267070008643042
+0.01361182820934053,covariates,train,0.1331028522039758
+0.013846514902605023,covariates,train,0.13396715643906656
+0.014081201595869515,covariates,train,0.13612791702679344
+0.014081201595869515,covariates,train,0.13742437337942956
+0.014315888289134006,covariates,train,0.13742437337942956
+0.014315888289134006,covariates,train,0.13785652549697494
+0.014550574982398498,covariates,train,0.13785652549697494
+0.014550574982398498,covariates,train,0.13958513396715644
+0.014550574982398498,covariates,train,0.14131374243733794
+0.014550574982398498,covariates,train,0.1421780466724287
+0.014550574982398498,covariates,train,0.14304235090751943
+0.01478526167566299,covariates,train,0.14347450302506481
+0.01478526167566299,covariates,train,0.14433880726015558
+0.01478526167566299,covariates,train,0.14520311149524634
+0.01478526167566299,covariates,train,0.1456352636127917
+0.01478526167566299,covariates,train,0.14693171996542784
+0.015019948368927482,covariates,train,0.14693171996542784
+0.015254635062191975,covariates,train,0.14736387208297322
+0.015254635062191975,covariates,train,0.14822817631806395
+0.015254635062191975,covariates,train,0.1495246326707001
+0.015254635062191975,covariates,train,0.1508210890233362
+0.015489321755456465,covariates,train,0.1525496974935177
+0.01595869514198545,covariates,train,0.1525496974935177
+0.01595869514198545,covariates,train,0.1529818496110631
+0.016193381835249942,covariates,train,0.1529818496110631
+0.016428068528514434,covariates,train,0.15427830596369924
+0.016428068528514434,covariates,train,0.15600691443388073
+0.016662755221778926,covariates,train,0.15600691443388073
+0.016662755221778926,covariates,train,0.15643906655142611
+0.016662755221778926,covariates,train,0.1581676750216076
+0.016662755221778926,covariates,train,0.158599827139153
+0.016662755221778926,covariates,train,0.1598962834917891
+0.016662755221778926,covariates,train,0.16076058772687987
+0.01689744191504342,covariates,train,0.16076058772687987
+0.01689744191504342,covariates,train,0.16119273984442523
+0.017132128608307907,covariates,train,0.16119273984442523
+0.0173668153015724,covariates,train,0.1616248919619706
+0.0173668153015724,covariates,train,0.162057044079516
+0.0173668153015724,covariates,train,0.16292134831460675
+0.0173668153015724,covariates,train,0.16378565254969749
+0.0173668153015724,covariates,train,0.16464995678478825
+0.0173668153015724,covariates,train,0.16637856525496975
+0.017601501994836892,covariates,train,0.16681071737251513
+0.017836188688101384,covariates,train,0.16681071737251513
+0.017836188688101384,covariates,train,0.1676750216076059
+0.017836188688101384,covariates,train,0.168971477960242
+0.017836188688101384,covariates,train,0.1694036300777874
+0.018070875381365877,covariates,train,0.1694036300777874
+0.018070875381365877,covariates,train,0.17156439066551427
+0.01854024876789486,covariates,train,0.17156439066551427
+0.018774935461159353,covariates,train,0.17199654278305965
+0.018774935461159353,covariates,train,0.17286084701815038
+0.019009622154423846,covariates,train,0.17286084701815038
+0.019244308847688334,covariates,train,0.17415730337078653
+0.019244308847688334,covariates,train,0.17718236819360414
+0.019244308847688334,covariates,train,0.1780466724286949
+0.019244308847688334,covariates,train,0.1797752808988764
+0.01971368223421732,covariates,train,0.1797752808988764
+0.01971368223421732,covariates,train,0.18020743301642178
+0.01994836892748181,covariates,train,0.18020743301642178
+0.01994836892748181,covariates,train,0.18193604148660328
+0.020183055620746303,covariates,train,0.18236819360414866
+0.020417742314010796,covariates,train,0.18236819360414866
+0.020652429007275288,covariates,train,0.18280034572169404
+0.020652429007275288,covariates,train,0.18323249783923942
+0.02088711570053978,covariates,train,0.18366464995678478
+0.02088711570053978,covariates,train,0.18409680207433016
+0.02088711570053978,covariates,train,0.18496110630942092
+0.021121802393804272,covariates,train,0.1853932584269663
+0.021121802393804272,covariates,train,0.18582541054451165
+0.021121802393804272,covariates,train,0.18668971477960242
+0.021121802393804272,covariates,train,0.1871218668971478
+0.021356489087068765,covariates,train,0.1871218668971478
+0.021825862473597746,covariates,train,0.1871218668971478
+0.022060549166862238,covariates,train,0.1871218668971478
+0.022060549166862238,covariates,train,0.18798617113223856
+0.02229523586012673,covariates,train,0.18798617113223856
+0.02229523586012673,covariates,train,0.18971477960242006
+0.02229523586012673,covariates,train,0.1905790838375108
+0.022529922553391223,covariates,train,0.1905790838375108
+0.022529922553391223,covariates,train,0.19101123595505617
+0.022764609246655715,covariates,train,0.19187554019014694
+0.022764609246655715,covariates,train,0.19230769230769232
+0.022764609246655715,covariates,train,0.19317199654278305
+0.022764609246655715,covariates,train,0.19403630077787382
+0.022999295939920207,covariates,train,0.1944684528954192
+0.022999295939920207,covariates,train,0.1961970613656007
+0.022999295939920207,covariates,train,0.19706136560069146
+0.0232339826331847,covariates,train,0.1979256698357822
+0.0232339826331847,covariates,train,0.19922212618841834
+0.02346866932644919,covariates,train,0.20138288677614521
+0.02346866932644919,covariates,train,0.20440795159896283
+0.023703356019713684,covariates,train,0.20440795159896283
+0.023703356019713684,covariates,train,0.2048401037165082
+0.023938042712978173,covariates,train,0.2048401037165082
+0.024172729406242665,covariates,train,0.2052722558340536
+0.024172729406242665,covariates,train,0.20570440795159897
+0.024407416099507157,covariates,train,0.20570440795159897
+0.024407416099507157,covariates,train,0.20613656006914433
+0.02464210279277165,covariates,train,0.20613656006914433
+0.024876789486036142,covariates,train,0.20872947277441659
+0.024876789486036142,covariates,train,0.20916162489196197
+0.024876789486036142,covariates,train,0.21002592912705273
+0.024876789486036142,covariates,train,0.212618841832325
+0.025111476179300634,covariates,train,0.212618841832325
+0.025111476179300634,covariates,train,0.2139152981849611
+0.025111476179300634,covariates,train,0.21521175453759722
+0.025111476179300634,covariates,train,0.21607605877268798
+0.025346162872565126,covariates,train,0.2173725151253241
+0.02558084956582962,covariates,train,0.21910112359550563
+0.02558084956582962,covariates,train,0.219533275713051
+0.02581553625909411,covariates,train,0.219533275713051
+0.02581553625909411,covariates,train,0.22082973206568712
+0.0260502229523586,covariates,train,0.22082973206568712
+0.0260502229523586,covariates,train,0.22169403630077789
+0.0260502229523586,covariates,train,0.22212618841832324
+0.026284909645623092,covariates,train,0.22212618841832324
+0.026284909645623092,covariates,train,0.22342264477095938
+0.026519596338887584,covariates,train,0.22342264477095938
+0.026519596338887584,covariates,train,0.22385479688850476
+0.026519596338887584,covariates,train,0.22515125324114088
+0.026519596338887584,covariates,train,0.22558340535868626
+0.02698896972541657,covariates,train,0.22558340535868626
+0.02698896972541657,covariates,train,0.226447709593777
+0.027927716498474538,covariates,train,0.226447709593777
+0.027927716498474538,covariates,train,0.22687986171132238
+0.027927716498474538,covariates,train,0.22774416594641314
+0.027927716498474538,covariates,train,0.22860847018150388
+0.027927716498474538,covariates,train,0.22947277441659464
+0.02839708988500352,covariates,train,0.22947277441659464
+0.02839708988500352,covariates,train,0.23076923076923078
+0.02863177657826801,covariates,train,0.23120138288677614
+0.02863177657826801,covariates,train,0.2320656871218669
+0.02863177657826801,covariates,train,0.23336214347450301
+0.02863177657826801,covariates,train,0.2337942955920484
+0.02863177657826801,covariates,train,0.23465859982713916
+0.02863177657826801,covariates,train,0.23509075194468454
+0.02863177657826801,covariates,train,0.23595505617977527
+0.02863177657826801,covariates,train,0.23768366464995677
+0.02863177657826801,covariates,train,0.23854796888504753
+0.02863177657826801,covariates,train,0.23898012100259292
+0.028866463271532503,covariates,train,0.23898012100259292
+0.029101149964796996,covariates,train,0.2394122731201383
+0.02957052335132598,covariates,train,0.2394122731201383
+0.029805210044590472,covariates,train,0.24027657735522903
+0.029805210044590472,covariates,train,0.2407087294727744
+0.030039896737854965,covariates,train,0.2407087294727744
+0.030039896737854965,covariates,train,0.24157303370786518
+0.030274583431119457,covariates,train,0.24157303370786518
+0.030274583431119457,covariates,train,0.24200518582541056
+0.03050927012438395,covariates,train,0.2424373379429559
+0.03097864351091293,covariates,train,0.2424373379429559
+0.03097864351091293,covariates,train,0.2428694900605013
+0.031213330204177422,covariates,train,0.24330164217804667
+0.031448016897441915,covariates,train,0.24330164217804667
+0.031448016897441915,covariates,train,0.24373379429559205
+0.03168270359070641,covariates,train,0.24373379429559205
+0.0319173902839709,covariates,train,0.24416594641313744
+0.0319173902839709,covariates,train,0.2445980985306828
+0.03215207697723539,covariates,train,0.2445980985306828
+0.03215207697723539,covariates,train,0.24546240276577355
+0.032621450363764376,covariates,train,0.24546240276577355
+0.032621450363764376,covariates,train,0.24632670700086431
+0.032621450363764376,covariates,train,0.24675885911840967
+0.03285613705702887,covariates,train,0.24675885911840967
+0.03285613705702887,covariates,train,0.24762316335350043
+0.03285613705702887,covariates,train,0.2480553154710458
+0.03332551044355785,covariates,train,0.2480553154710458
+0.03332551044355785,covariates,train,0.24891961970613655
+0.033560197136822345,covariates,train,0.24891961970613655
+0.033560197136822345,covariates,train,0.24935177182368193
+0.03379488383008684,covariates,train,0.24935177182368193
+0.03379488383008684,covariates,train,0.2497839239412273
+0.03379488383008684,covariates,train,0.25064822817631804
+0.03402957052335132,covariates,train,0.2510803802938634
+0.03402957052335132,covariates,train,0.25280898876404495
+0.034264257216615815,covariates,train,0.2536732929991357
+0.034264257216615815,covariates,train,0.2545375972342264
+0.03449894390988031,covariates,train,0.2545375972342264
+0.03449894390988031,covariates,train,0.2554019014693172
+0.0347336306031448,covariates,train,0.2554019014693172
+0.0347336306031448,covariates,train,0.25583405358686256
+0.03496831729640929,covariates,train,0.25583405358686256
+0.03496831729640929,covariates,train,0.2575626620570441
+0.035203003989673784,covariates,train,0.25842696629213485
+0.035203003989673784,covariates,train,0.25972342264477094
+0.035437690682938276,covariates,train,0.25972342264477094
+0.03590706406946726,covariates,train,0.2601555747623163
+0.03590706406946726,covariates,train,0.2610198789974071
+0.03590706406946726,covariates,train,0.26188418323249785
+0.03590706406946726,covariates,train,0.2627484874675886
+0.03614175076273175,covariates,train,0.2636127917026793
+0.03614175076273175,covariates,train,0.2640449438202247
+0.03661112414926074,covariates,train,0.2640449438202247
+0.03661112414926074,covariates,train,0.26490924805531546
+0.03708049753578972,covariates,train,0.26490924805531546
+0.03708049753578972,covariates,train,0.26534140017286084
+0.03708049753578972,covariates,train,0.26707000864304237
+0.037315184229054214,covariates,train,0.26707000864304237
+0.03754987092231871,covariates,train,0.26793431287813313
+0.0377845576155832,covariates,train,0.26836646499567846
+0.0377845576155832,covariates,train,0.27052722558340536
+0.03801924430884769,covariates,train,0.27095937770095074
+0.03801924430884769,covariates,train,0.2713915298184961
+0.03848861769537667,covariates,train,0.2718236819360415
+0.03872330438864116,covariates,train,0.2726879861711322
+0.03895799108190565,covariates,train,0.2726879861711322
+0.03895799108190565,covariates,train,0.27398444252376836
+0.039192677775170146,covariates,train,0.27398444252376836
+0.03942736446843464,covariates,train,0.27441659464131374
+0.03966205116169913,covariates,train,0.27441659464131374
+0.03989673785496362,covariates,train,0.27614520311149526
+0.03989673785496362,covariates,train,0.27657735522904064
+0.040131424548228115,covariates,train,0.277009507346586
+0.04036611124149261,covariates,train,0.2783059636992221
+0.04036611124149261,covariates,train,0.2787381158167675
+0.04036611124149261,covariates,train,0.27960242005185826
+0.04036611124149261,covariates,train,0.2808988764044944
+0.04036611124149261,covariates,train,0.2817631806395851
+0.0406007979347571,covariates,train,0.2821953327571305
+0.0406007979347571,covariates,train,0.283923941227312
+0.0406007979347571,covariates,train,0.28522039757994816
+0.04083548462802159,covariates,train,0.28522039757994816
+0.04083548462802159,covariates,train,0.28608470181503887
+0.041070171321286084,covariates,train,0.28608470181503887
+0.041070171321286084,covariates,train,0.28651685393258425
+0.04153954470781507,covariates,train,0.28651685393258425
+0.04153954470781507,covariates,train,0.28910976663785654
+0.04177423140107956,covariates,train,0.2895419187554019
+0.04200891809434405,covariates,train,0.2895419187554019
+0.04200891809434405,covariates,train,0.2904062229904927
+0.042243604787608545,covariates,train,0.290838375108038
+0.042243604787608545,covariates,train,0.29213483146067415
+0.04247829148087304,covariates,train,0.29213483146067415
+0.04247829148087304,covariates,train,0.2929991356957649
+0.04271297817413753,covariates,train,0.2929991356957649
+0.04271297817413753,covariates,train,0.2960242005185825
+0.04271297817413753,covariates,train,0.29732065687121867
+0.04294766486740202,covariates,train,0.29732065687121867
+0.043417038253931,covariates,train,0.29818496110630943
+0.043886411640459984,covariates,train,0.3003457216940363
+0.04435578502698897,covariates,train,0.3003457216940363
+0.04435578502698897,covariates,train,0.30077787381158166
+0.04435578502698897,covariates,train,0.3016421780466724
+0.04459047172025346,covariates,train,0.3025064822817632
+0.04459047172025346,covariates,train,0.30293863439930857
+0.04482515841351795,covariates,train,0.30337078651685395
+0.04482515841351795,covariates,train,0.30466724286949004
+0.045059845106782445,covariates,train,0.3050993949870354
+0.045059845106782445,covariates,train,0.3059636992221262
+0.04529453180004694,covariates,train,0.3059636992221262
+0.04529453180004694,covariates,train,0.30639585133967157
+0.04552921849331143,covariates,train,0.30639585133967157
+0.045998591879840414,covariates,train,0.30726015557476233
+0.045998591879840414,covariates,train,0.3076923076923077
+0.046233278573104906,covariates,train,0.3081244598098531
+0.046233278573104906,covariates,train,0.30985306828003456
+0.046233278573104906,covariates,train,0.3111495246326707
+0.046233278573104906,covariates,train,0.31201382886776147
+0.04670265195963389,covariates,train,0.31201382886776147
+0.04670265195963389,covariates,train,0.31244598098530685
+0.04670265195963389,covariates,train,0.3141745894554883
+0.04670265195963389,covariates,train,0.3150388936905791
+0.047172025346162876,covariates,train,0.3163353500432152
+0.04740671203942737,covariates,train,0.3163353500432152
+0.04740671203942737,covariates,train,0.3167675021607606
+0.04740671203942737,covariates,train,0.31892826274848746
+0.04740671203942737,covariates,train,0.31936041486603284
+0.04764139873269185,covariates,train,0.31936041486603284
+0.04764139873269185,covariates,train,0.3197925669835782
+0.04764139873269185,covariates,train,0.32108902333621436
+0.047876085425956345,covariates,train,0.32108902333621436
+0.047876085425956345,covariates,train,0.3219533275713051
+0.047876085425956345,covariates,train,0.32454624027657736
+0.04811077211922084,covariates,train,0.32497839239412274
+0.04811077211922084,covariates,train,0.3254105445116681
+0.04858014550574982,covariates,train,0.3262748487467589
+0.048814832199014314,covariates,train,0.3267070008643042
+0.048814832199014314,covariates,train,0.3271391529818496
+0.0492842055855433,covariates,train,0.32757130509939497
+0.0492842055855433,covariates,train,0.32800345721694035
+0.0492842055855433,covariates,train,0.33016421780466726
+0.04951889227880779,covariates,train,0.33016421780466726
+0.04951889227880779,covariates,train,0.331028522039758
+0.04951889227880779,covariates,train,0.33146067415730335
+0.049753578972072283,covariates,train,0.33146067415730335
+0.05045763905186576,covariates,train,0.33146067415730335
+0.05045763905186576,covariates,train,0.3323249783923941
+0.05069232574513025,covariates,train,0.3327571305099395
+0.05069232574513025,covariates,train,0.3331892826274849
+0.05069232574513025,covariates,train,0.3349178910976664
+0.050927012438394745,covariates,train,0.3349178910976664
+0.05116169913165924,covariates,train,0.3362143474503025
+0.05116169913165924,covariates,train,0.33664649956784787
+0.05163107251818822,covariates,train,0.33707865168539325
+0.05163107251818822,covariates,train,0.33751080380293863
+0.05163107251818822,covariates,train,0.33967156439066554
+0.05163107251818822,covariates,train,0.3418323249783924
+0.051865759211452714,covariates,train,0.34269662921348315
+0.051865759211452714,covariates,train,0.34485738980121
+0.051865759211452714,covariates,train,0.3452895419187554
+0.0521004459047172,covariates,train,0.3452895419187554
+0.0521004459047172,covariates,train,0.34572169403630076
+0.0521004459047172,covariates,train,0.3465859982713915
+0.05233513259798169,covariates,train,0.3465859982713915
+0.05233513259798169,covariates,train,0.34788245462402767
+0.05233513259798169,covariates,train,0.34831460674157305
+0.052569819291246184,covariates,train,0.34831460674157305
+0.052569819291246184,covariates,train,0.34874675885911843
+0.052804505984510676,covariates,train,0.34874675885911843
+0.05327387937103966,covariates,train,0.34917891097666376
+0.05327387937103966,covariates,train,0.3500432152117545
+0.05327387937103966,covariates,train,0.35177182368193605
+0.05327387937103966,covariates,train,0.35350043215211757
+0.05350856606430415,covariates,train,0.35350043215211757
+0.05350856606430415,covariates,train,0.3543647363872083
+0.053743252757568645,covariates,train,0.3543647363872083
+0.053743252757568645,covariates,train,0.35522904062229904
+0.053743252757568645,covariates,train,0.3556611927398444
+0.053743252757568645,covariates,train,0.3565254969749352
+0.05421262614409763,covariates,train,0.3565254969749352
+0.05421262614409763,covariates,train,0.35695764909248057
+0.05444731283736212,covariates,train,0.35695764909248057
+0.054916686223891106,covariates,train,0.35738980121002595
+0.054916686223891106,covariates,train,0.35825410544511666
+0.0551513729171556,covariates,train,0.35825410544511666
+0.0551513729171556,covariates,train,0.3599827139152982
+0.0551513729171556,covariates,train,0.36041486603284356
+0.05538605961042009,covariates,train,0.36041486603284356
+0.05538605961042009,covariates,train,0.3617113223854797
+0.05538605961042009,covariates,train,0.36257562662057047
+0.05538605961042009,covariates,train,0.3630077787381158
+0.055855432996949075,covariates,train,0.3630077787381158
+0.055855432996949075,covariates,train,0.3647363872082973
+0.05609011969021357,covariates,train,0.36603284356093346
+0.05632480638347806,covariates,train,0.36603284356093346
+0.05632480638347806,covariates,train,0.36732929991356955
+0.05655949307674255,covariates,train,0.3686257562662057
+0.05655949307674255,covariates,train,0.36992221261884184
+0.05679417977000704,covariates,train,0.36992221261884184
+0.05702886646327153,covariates,train,0.3703543647363872
+0.05702886646327153,covariates,train,0.3716508210890233
+0.05702886646327153,covariates,train,0.37251512532411407
+0.05702886646327153,covariates,train,0.37294727744165945
+0.05726355315653602,covariates,train,0.37294727744165945
+0.05726355315653602,covariates,train,0.37337942955920483
+0.05726355315653602,covariates,train,0.3742437337942956
+0.057498239849800514,covariates,train,0.3742437337942956
+0.057498239849800514,covariates,train,0.37510803802938636
+0.05773292654306501,covariates,train,0.37510803802938636
+0.05773292654306501,covariates,train,0.37554019014693174
+0.0579676132363295,covariates,train,0.37554019014693174
+0.0579676132363295,covariates,train,0.3759723422644771
+0.05820229992959399,covariates,train,0.3759723422644771
+0.05820229992959399,covariates,train,0.37640449438202245
+0.05820229992959399,covariates,train,0.3772687986171132
+0.05820229992959399,covariates,train,0.3777009507346586
+0.05843698662285848,covariates,train,0.3777009507346586
+0.05843698662285848,covariates,train,0.378133102852204
+0.058671673316122976,covariates,train,0.37899740708729474
+0.05890636000938747,covariates,train,0.37899740708729474
+0.05890636000938747,covariates,train,0.3798617113223855
+0.059610420089180945,covariates,train,0.3807260155574762
+0.059610420089180945,covariates,train,0.38159031979256697
+0.059610420089180945,covariates,train,0.3828867761452031
+0.059610420089180945,covariates,train,0.3833189282627485
+0.06031448016897442,covariates,train,0.38504753673293
+0.06031448016897442,covariates,train,0.3867761452031115
+0.060549166862238914,covariates,train,0.38720829732065687
+0.060783853555503406,covariates,train,0.38807260155574763
+0.060783853555503406,covariates,train,0.388504753673293
+0.060783853555503406,covariates,train,0.3898012100259291
+0.060783853555503406,covariates,train,0.3902333621434745
+0.0610185402487679,covariates,train,0.3902333621434745
+0.0610185402487679,covariates,train,0.39109766637856525
+0.061253226942032384,covariates,train,0.3915298184961106
+0.061253226942032384,covariates,train,0.39369057908383753
+0.061487913635296876,covariates,train,0.39455488331892824
+0.061487913635296876,covariates,train,0.395419187554019
+0.061487913635296876,covariates,train,0.39714779602420053
+0.06195728702182586,covariates,train,0.3980121002592913
+0.06195728702182586,covariates,train,0.39844425237683667
+0.06195728702182586,covariates,train,0.3993085566119274
+0.06195728702182586,covariates,train,0.39974070872947276
+0.06219197371509035,covariates,train,0.39974070872947276
+0.06289603379488383,covariates,train,0.39974070872947276
+0.06313072048814833,covariates,train,0.39974070872947276
+0.06313072048814833,covariates,train,0.40017286084701814
+0.06313072048814833,covariates,train,0.4014693171996543
+0.06313072048814833,covariates,train,0.40233362143474505
+0.06313072048814833,covariates,train,0.40319792566983575
+0.06336540718141281,covariates,train,0.40319792566983575
+0.0636000938746773,covariates,train,0.40363007778738114
+0.0638347805679418,covariates,train,0.40363007778738114
+0.0638347805679418,covariates,train,0.4040622299049265
+0.06406946726120628,covariates,train,0.40579083837510804
+0.06477352734099977,covariates,train,0.40579083837510804
+0.06477352734099977,covariates,train,0.4062229904926534
+0.06477352734099977,covariates,train,0.4079515989628349
+0.06477352734099977,covariates,train,0.40924805531547104
+0.06477352734099977,covariates,train,0.4096802074330164
+0.06500821403426425,covariates,train,0.4096802074330164
+0.06500821403426425,covariates,train,0.4101123595505618
+0.06524290072752875,covariates,train,0.4101123595505618
+0.06524290072752875,covariates,train,0.4105445116681072
+0.06524290072752875,covariates,train,0.41140881590319794
+0.06524290072752875,covariates,train,0.41270527225583403
+0.06547758742079324,covariates,train,0.41270527225583403
+0.06594696080732222,covariates,train,0.41270527225583403
+0.06594696080732222,covariates,train,0.4131374243733794
+0.0664163341938512,covariates,train,0.4135695764909248
+0.0664163341938512,covariates,train,0.41443388072601556
+0.0666510208871157,covariates,train,0.4152981849611063
+0.0666510208871157,covariates,train,0.4157303370786517
+0.06688570758038019,covariates,train,0.4157303370786517
+0.06688570758038019,covariates,train,0.4161624891961971
+0.06712039427364469,covariates,train,0.4170267934312878
+0.06712039427364469,covariates,train,0.41745894554883317
+0.06735508096690918,covariates,train,0.41745894554883317
+0.06735508096690918,covariates,train,0.4191875540190147
+0.06758976766017367,covariates,train,0.42134831460674155
+0.06805914104670265,covariates,train,0.42134831460674155
+0.06829382773996714,covariates,train,0.42178046672428693
+0.06876320112649613,covariates,train,0.42178046672428693
+0.06876320112649613,covariates,train,0.4222126188418323
+0.06876320112649613,covariates,train,0.4230769230769231
+0.06899788781976061,covariates,train,0.4243733794295592
+0.06899788781976061,covariates,train,0.42523768366465
+0.06899788781976061,covariates,train,0.42566983578219536
+0.06923257451302511,covariates,train,0.42566983578219536
+0.0694672612062896,covariates,train,0.42653414001728607
+0.0697019478995541,covariates,train,0.42696629213483145
+0.07017132128608308,covariates,train,0.42696629213483145
+0.07017132128608308,covariates,train,0.428694900605013
+0.07087538136587655,covariates,train,0.42955920484010374
+0.07134475475240554,covariates,train,0.42955920484010374
+0.07134475475240554,covariates,train,0.4308556611927398
+0.07134475475240554,covariates,train,0.4312878133102852
+0.07181412813893452,covariates,train,0.43301642178046673
+0.07204881483219902,covariates,train,0.4334485738980121
+0.0722835015254635,covariates,train,0.4334485738980121
+0.0722835015254635,covariates,train,0.4338807260155575
+0.07275287491199249,covariates,train,0.4338807260155575
+0.07275287491199249,covariates,train,0.4351771823681936
+0.07275287491199249,covariates,train,0.43604148660328435
+0.07298756160525698,covariates,train,0.43604148660328435
+0.07298756160525698,covariates,train,0.4373379429559205
+0.07322224829852148,covariates,train,0.43820224719101125
+0.07322224829852148,covariates,train,0.439066551426102
+0.07322224829852148,covariates,train,0.43949870354364734
+0.07345693499178596,covariates,train,0.43949870354364734
+0.07345693499178596,covariates,train,0.4420916162489196
+0.07392630837831494,covariates,train,0.4420916162489196
+0.07439568176484393,covariates,train,0.442523768366465
+0.07439568176484393,covariates,train,0.44338807260155577
+0.07486505515137291,covariates,train,0.44338807260155577
+0.07486505515137291,covariates,train,0.4438202247191011
+0.07486505515137291,covariates,train,0.44468452895419186
+0.07509974184463741,covariates,train,0.4464131374243734
+0.07509974184463741,covariates,train,0.44684528954191877
+0.0753344285379019,covariates,train,0.44684528954191877
+0.0753344285379019,covariates,train,0.44770959377700953
+0.0755691152311664,covariates,train,0.44857389801210024
+0.0755691152311664,covariates,train,0.4490060501296456
+0.07603848861769538,covariates,train,0.4490060501296456
+0.07627317531095987,covariates,train,0.4490060501296456
+0.07674254869748885,covariates,train,0.45030250648228176
+0.07674254869748885,covariates,train,0.45073465859982714
+0.07697723539075334,covariates,train,0.45073465859982714
+0.07697723539075334,covariates,train,0.4511668107173725
+0.07697723539075334,covariates,train,0.45246326707000867
+0.07721192208401784,covariates,train,0.45246326707000867
+0.07721192208401784,covariates,train,0.4550561797752809
+0.07768129547054682,covariates,train,0.4567847882454624
+0.07768129547054682,covariates,train,0.45721694036300775
+0.0779159821638113,covariates,train,0.45764909248055313
+0.0779159821638113,covariates,train,0.4580812445980985
+0.0781506688570758,covariates,train,0.4585133967156439
+0.07838535555034029,covariates,train,0.4585133967156439
+0.07838535555034029,covariates,train,0.4602420051858254
+0.07885472893686928,covariates,train,0.4606741573033708
+0.07908941563013377,covariates,train,0.4611063094209162
+0.07908941563013377,covariates,train,0.4619706136560069
+0.07932410232339826,covariates,train,0.4619706136560069
+0.07932410232339826,covariates,train,0.46240276577355227
+0.07955878901666276,covariates,train,0.46283491789109765
+0.07955878901666276,covariates,train,0.46326707000864303
+0.08002816240319174,covariates,train,0.4641313742437338
+0.08002816240319174,covariates,train,0.46499567847882456
+0.08026284909645623,covariates,train,0.46499567847882456
+0.08026284909645623,covariates,train,0.4658599827139153
+0.08026284909645623,covariates,train,0.46629213483146065
+0.08049753578972073,covariates,train,0.46629213483146065
+0.08049753578972073,covariates,train,0.46672428694900603
+0.08073222248298521,covariates,train,0.46672428694900603
+0.08096690917624971,covariates,train,0.4671564390665514
+0.0812015958695142,covariates,train,0.4671564390665514
+0.0812015958695142,covariates,train,0.4675885911840968
+0.0812015958695142,covariates,train,0.4693171996542783
+0.0812015958695142,covariates,train,0.4701815038893691
+0.0814362825627787,covariates,train,0.4701815038893691
+0.08167096925604318,covariates,train,0.4710458081244598
+0.08190565594930767,covariates,train,0.4710458081244598
+0.08237502933583665,covariates,train,0.4710458081244598
+0.08284440272236564,covariates,train,0.4710458081244598
+0.08284440272236564,covariates,train,0.47147796024200517
+0.08307908941563014,covariates,train,0.47147796024200517
+0.08307908941563014,covariates,train,0.47191011235955055
+0.08307908941563014,covariates,train,0.4727744165946413
+0.08331377610889462,covariates,train,0.4727744165946413
+0.0837831494954236,covariates,train,0.4732065687121867
+0.0840178361886881,covariates,train,0.4732065687121867
+0.0840178361886881,covariates,train,0.4736387208297321
+0.0840178361886881,covariates,train,0.47450302506482284
+0.08448720957521709,covariates,train,0.4757994814174589
+0.08448720957521709,covariates,train,0.4762316335350043
+0.08495658296174607,covariates,train,0.4762316335350043
+0.08495658296174607,covariates,train,0.4766637856525497
+0.08495658296174607,covariates,train,0.47752808988764045
+0.08495658296174607,covariates,train,0.4783923941227312
+0.08495658296174607,covariates,train,0.47968885047536736
+0.08566064304153954,covariates,train,0.47968885047536736
+0.08589532973480404,covariates,train,0.47968885047536736
+0.08589532973480404,covariates,train,0.4801210025929127
+0.08589532973480404,covariates,train,0.48098530682800344
+0.08613001642806853,covariates,train,0.4814174589455488
+0.08636470312133301,covariates,train,0.4814174589455488
+0.08636470312133301,covariates,train,0.4818496110630942
+0.08659938981459751,covariates,train,0.4818496110630942
+0.08659938981459751,covariates,train,0.48271391529818497
+0.0870687632011265,covariates,train,0.48357821953327573
+0.08800750997418447,covariates,train,0.4840103716508211
+0.08800750997418447,covariates,train,0.4857389801210026
+0.08847688336071345,covariates,train,0.4857389801210026
+0.08847688336071345,covariates,train,0.48660328435609335
+0.08871157005397794,covariates,train,0.48660328435609335
+0.08871157005397794,covariates,train,0.4870354364736387
+0.08871157005397794,covariates,train,0.4878997407087295
+0.08871157005397794,covariates,train,0.48833189282627487
+0.08918094344050692,covariates,train,0.48833189282627487
+0.08918094344050692,covariates,train,0.4887640449438202
+0.08918094344050692,covariates,train,0.4904926534140017
+0.08918094344050692,covariates,train,0.4913569576490925
+0.08941563013377142,covariates,train,0.49178910976663787
+0.08941563013377142,covariates,train,0.49222126188418325
+0.09011969021356489,covariates,train,0.49265341400172863
+0.09011969021356489,covariates,train,0.493085566119274
+0.09035437690682939,covariates,train,0.49351771823681934
+0.09058906360009387,covariates,train,0.49351771823681934
+0.09058906360009387,covariates,train,0.4939498703543647
+0.09082375029335836,covariates,train,0.4939498703543647
+0.09129312367988734,covariates,train,0.4943820224719101
+0.09129312367988734,covariates,train,0.4948141745894555
+0.09176249706641633,covariates,train,0.4948141745894555
+0.09223187045294531,covariates,train,0.4961106309420916
+0.09246655714620981,covariates,train,0.496542783059637
+0.09246655714620981,covariates,train,0.4969749351771824
+0.09317061722600328,covariates,train,0.4969749351771824
+0.09340530391926778,covariates,train,0.4969749351771824
+0.09340530391926778,covariates,train,0.49740708729472777
+0.09410936399906125,covariates,train,0.49740708729472777
+0.09410936399906125,covariates,train,0.4978392394122731
+0.09434405069232575,covariates,train,0.4978392394122731
+0.09457873738559024,covariates,train,0.4982713915298185
+0.09504811077211922,covariates,train,0.4982713915298185
+0.0952827974653837,covariates,train,0.49870354364736386
+0.0952827974653837,covariates,train,0.4995678478824546
+0.0952827974653837,covariates,train,0.5004321521175453
+0.09575217085191269,covariates,train,0.5004321521175453
+0.09598685754517719,covariates,train,0.5017286084701815
+0.09598685754517719,covariates,train,0.5021607605877269
+0.09622154423844168,covariates,train,0.5021607605877269
+0.09622154423844168,covariates,train,0.5030250648228176
+0.09669091762497066,covariates,train,0.5030250648228176
+0.09669091762497066,covariates,train,0.503457216940363
+0.09669091762497066,covariates,train,0.5043215211754538
+0.09739497770476414,covariates,train,0.5051858254105445
+0.09762966439802863,covariates,train,0.5051858254105445
+0.09762966439802863,covariates,train,0.5056179775280899
+0.09786435109129313,covariates,train,0.5056179775280899
+0.09809903778455761,covariates,train,0.5064822817631807
+0.0988030978643511,covariates,train,0.5064822817631807
+0.0988030978643511,covariates,train,0.5073465859982714
+0.0988030978643511,covariates,train,0.5082108902333622
+0.09903778455761558,covariates,train,0.5082108902333622
+0.09950715794414457,covariates,train,0.5095073465859983
+0.09950715794414457,covariates,train,0.5099394987035436
+0.09997653133067355,covariates,train,0.5099394987035436
+0.09997653133067355,covariates,train,0.510371650821089
+0.10068059141046702,covariates,train,0.510371650821089
+0.101149964796996,covariates,train,0.5108038029386344
+0.101149964796996,covariates,train,0.5125324114088159
+0.10161933818352499,covariates,train,0.5125324114088159
+0.10185402487678949,covariates,train,0.5129645635263613
+0.10208871157005397,covariates,train,0.5129645635263613
+0.10208871157005397,covariates,train,0.5133967156439067
+0.10232339826331847,covariates,train,0.5133967156439067
+0.10232339826331847,covariates,train,0.513828867761452
+0.10232339826331847,covariates,train,0.5146931719965427
+0.10232339826331847,covariates,train,0.5155574762316335
+0.10232339826331847,covariates,train,0.5164217804667243
+0.10279277164984746,covariates,train,0.5164217804667243
+0.10279277164984746,covariates,train,0.517286084701815
+0.10302745834311194,covariates,train,0.5181503889369058
+0.10326214503637644,covariates,train,0.5181503889369058
+0.10326214503637644,covariates,train,0.5190146931719966
+0.10349683172964093,covariates,train,0.5194468452895419
+0.10349683172964093,covariates,train,0.5203111495246326
+0.10349683172964093,covariates,train,0.5207433016421781
+0.1042008918094344,covariates,train,0.5207433016421781
+0.1044355785026989,covariates,train,0.5211754537597234
+0.10490495188922788,covariates,train,0.5211754537597234
+0.10490495188922788,covariates,train,0.5216076058772688
+0.10513963858249237,covariates,train,0.5216076058772688
+0.10513963858249237,covariates,train,0.5237683664649957
+0.10513963858249237,covariates,train,0.5246326707000865
+0.10513963858249237,covariates,train,0.5254969749351772
+0.10560901196902135,covariates,train,0.5254969749351772
+0.10560901196902135,covariates,train,0.5259291270527225
+0.10607838535555034,covariates,train,0.5259291270527225
+0.10607838535555034,covariates,train,0.5267934312878133
+0.10631307204881484,covariates,train,0.5272255834053586
+0.10654775874207932,covariates,train,0.5272255834053586
+0.10654775874207932,covariates,train,0.5276577355229041
+0.10654775874207932,covariates,train,0.5285220397579948
+0.10654775874207932,covariates,train,0.5289541918755402
+0.10678244543534382,covariates,train,0.5289541918755402
+0.10678244543534382,covariates,train,0.5293863439930856
+0.1070171321286083,covariates,train,0.5298184961106309
+0.10748650551513729,covariates,train,0.5298184961106309
+0.10748650551513729,covariates,train,0.5302506482281764
+0.10772119220840179,covariates,train,0.5311149524632671
+0.10795587890166627,covariates,train,0.5311149524632671
+0.10795587890166627,covariates,train,0.5315471045808124
+0.10842525228819526,covariates,train,0.5315471045808124
+0.10865993898145974,covariates,train,0.5315471045808124
+0.10865993898145974,covariates,train,0.5324114088159032
+0.10912931236798873,covariates,train,0.5324114088159032
+0.10912931236798873,covariates,train,0.5328435609334485
+0.10936399906125323,covariates,train,0.5337078651685393
+0.10936399906125323,covariates,train,0.5345721694036301
+0.1100680591410467,covariates,train,0.5345721694036301
+0.1100680591410467,covariates,train,0.5354364736387208
+0.1103027458343112,covariates,train,0.5363007778738116
+0.11053743252757568,covariates,train,0.5367329299913569
+0.11100680591410467,covariates,train,0.5371650821089023
+0.11124149260736917,covariates,train,0.5371650821089023
+0.11124149260736917,covariates,train,0.5380293863439931
+0.11147617930063365,covariates,train,0.5384615384615384
+0.11147617930063365,covariates,train,0.5388936905790839
+0.11171086599389815,covariates,train,0.5388936905790839
+0.11194555268716264,covariates,train,0.5393258426966292
+0.11194555268716264,covariates,train,0.54019014693172
+0.11218023938042714,covariates,train,0.54019014693172
+0.11218023938042714,covariates,train,0.5410544511668107
+0.11218023938042714,covariates,train,0.5427830596369922
+0.11218023938042714,covariates,train,0.5449438202247191
+0.11218023938042714,covariates,train,0.5458081244598099
+0.11218023938042714,covariates,train,0.5466724286949006
+0.11264961276695612,covariates,train,0.5466724286949006
+0.11264961276695612,covariates,train,0.547104580812446
+0.11335367284674959,covariates,train,0.547104580812446
+0.11358835954001407,covariates,train,0.5479688850475367
+0.11382304623327857,covariates,train,0.5479688850475367
+0.11382304623327857,covariates,train,0.5496974935177182
+0.11405773292654306,covariates,train,0.5496974935177182
+0.11405773292654306,covariates,train,0.5501296456352636
+0.11429241961980756,covariates,train,0.550561797752809
+0.11429241961980756,covariates,train,0.5509939498703543
+0.11476179300633654,covariates,train,0.5518582541054451
+0.11499647969960103,covariates,train,0.5518582541054451
+0.11499647969960103,covariates,train,0.5527225583405359
+0.11499647969960103,covariates,train,0.554019014693172
+0.11499647969960103,covariates,train,0.5544511668107174
+0.11523116639286553,covariates,train,0.5544511668107174
+0.11523116639286553,covariates,train,0.5553154710458081
+0.115935226472659,covariates,train,0.5553154710458081
+0.1161699131659235,covariates,train,0.5553154710458081
+0.1161699131659235,covariates,train,0.5557476231633535
+0.11640459985918798,covariates,train,0.5557476231633535
+0.11640459985918798,covariates,train,0.5561797752808989
+0.11640459985918798,covariates,train,0.557476231633535
+0.11663928655245248,covariates,train,0.557476231633535
+0.11663928655245248,covariates,train,0.5587726879861711
+0.11663928655245248,covariates,train,0.5592048401037165
+0.11710865993898147,covariates,train,0.5592048401037165
+0.11734334663224595,covariates,train,0.5600691443388073
+0.11757803332551045,covariates,train,0.5600691443388073
+0.11757803332551045,covariates,train,0.5605012964563526
+0.11804740671203942,covariates,train,0.5605012964563526
+0.1185167800985684,covariates,train,0.5613656006914434
+0.1187514667918329,covariates,train,0.5613656006914434
+0.1187514667918329,covariates,train,0.5617977528089888
+0.11898615348509739,covariates,train,0.5617977528089888
+0.11922084017836189,covariates,train,0.5622299049265341
+0.11945552687162637,covariates,train,0.5622299049265341
+0.11945552687162637,covariates,train,0.5626620570440796
+0.11992490025815536,covariates,train,0.5626620570440796
+0.12015958695141986,covariates,train,0.5635263612791702
+0.12015958695141986,covariates,train,0.5639585133967157
+0.12062896033794884,covariates,train,0.5652549697493517
+0.12086364703121333,covariates,train,0.5652549697493517
+0.12086364703121333,covariates,train,0.5656871218668972
+0.12109833372447783,covariates,train,0.5665514261019879
+0.12109833372447783,covariates,train,0.5669835782195333
+0.12156770711100681,covariates,train,0.5674157303370787
+0.1220370804975358,covariates,train,0.5674157303370787
+0.1220370804975358,covariates,train,0.5687121866897148
+0.1220370804975358,covariates,train,0.5691443388072601
+0.12274114057732927,covariates,train,0.5704407951598963
+0.12274114057732927,covariates,train,0.5713050993949871
+0.12321051396385825,covariates,train,0.5713050993949871
+0.12321051396385825,covariates,train,0.5721694036300777
+0.12344520065712274,covariates,train,0.5721694036300777
+0.12344520065712274,covariates,train,0.5730337078651685
+0.12367988735038724,covariates,train,0.5734658599827139
+0.12367988735038724,covariates,train,0.5738980121002593
+0.12391457404365172,covariates,train,0.5743301642178047
+0.12391457404365172,covariates,train,0.5756266205704408
+0.1243839474301807,covariates,train,0.5756266205704408
+0.1243839474301807,covariates,train,0.5760587726879862
+0.1246186341234452,covariates,train,0.5760587726879862
+0.1246186341234452,covariates,train,0.5773552290406223
+0.12485332081670969,covariates,train,0.5773552290406223
+0.12508800750997418,covariates,train,0.5777873811581676
+0.12508800750997418,covariates,train,0.5782195332757131
+0.12555738089650317,covariates,train,0.5782195332757131
+0.12602675428303214,covariates,train,0.5786516853932584
+0.12626144097629666,covariates,train,0.5786516853932584
+0.12626144097629666,covariates,train,0.5795159896283492
+0.1269655010560901,covariates,train,0.5808124459809854
+0.1272001877493546,covariates,train,0.5808124459809854
+0.1272001877493546,covariates,train,0.5812445980985307
+0.1274348744426191,covariates,train,0.581676750216076
+0.1276695611358836,covariates,train,0.5825410544511668
+0.1276695611358836,covariates,train,0.5834053586862575
+0.12790424782914808,covariates,train,0.5834053586862575
+0.12790424782914808,covariates,train,0.583837510803803
+0.12790424782914808,covariates,train,0.5847018150388937
+0.12813893452241257,covariates,train,0.5851339671564391
+0.12837362121567708,covariates,train,0.5851339671564391
+0.12884299460220605,covariates,train,0.5855661192739845
+0.12884299460220605,covariates,train,0.5864304235090751
+0.12907768129547054,covariates,train,0.5864304235090751
+0.12907768129547054,covariates,train,0.5868625756266206
+0.12954705468199953,covariates,train,0.5877268798617113
+0.12978174137526402,covariates,train,0.5877268798617113
+0.13025111476179302,covariates,train,0.5881590319792567
+0.1304858014550575,covariates,train,0.5881590319792567
+0.1304858014550575,covariates,train,0.5890233362143474
+0.130720488148322,covariates,train,0.5890233362143474
+0.130720488148322,covariates,train,0.5894554883318929
+0.13095517484158647,covariates,train,0.5894554883318929
+0.13095517484158647,covariates,train,0.5898876404494382
+0.13095517484158647,covariates,train,0.590751944684529
+0.13095517484158647,covariates,train,0.5916162489196197
+0.131189861534851,covariates,train,0.5916162489196197
+0.13165923492137996,covariates,train,0.5916162489196197
+0.13212860830790893,covariates,train,0.5916162489196197
+0.13212860830790893,covariates,train,0.5929127052722558
+0.13212860830790893,covariates,train,0.5933448573898013
+0.1328326683877024,covariates,train,0.5937770095073466
+0.1328326683877024,covariates,train,0.5946413137424373
+0.1335367284674959,covariates,train,0.5946413137424373
+0.13377141516076038,covariates,train,0.5946413137424373
+0.13471016193381835,covariates,train,0.5946413137424373
+0.13494484862708284,covariates,train,0.5946413137424373
+0.13494484862708284,covariates,train,0.5955056179775281
+0.13517953532034735,covariates,train,0.5959377700950734
+0.13541422201361183,covariates,train,0.5968020743301642
+0.13541422201361183,covariates,train,0.597666378565255
+0.13564890870687632,covariates,train,0.5985306828003457
+0.1358835954001408,covariates,train,0.5989628349178912
+0.1358835954001408,covariates,train,0.5993949870354365
+0.1361182820934053,covariates,train,0.6002592912705272
+0.1365876554799343,covariates,train,0.6002592912705272
+0.13682234217319877,covariates,train,0.6006914433880726
+0.13729171555972777,covariates,train,0.6006914433880726
+0.13752640225299226,covariates,train,0.601123595505618
+0.13752640225299226,covariates,train,0.6019878997407088
+0.13752640225299226,covariates,train,0.6024200518582541
+0.13799577563952123,covariates,train,0.6032843560933449
+0.1386998357193147,covariates,train,0.6032843560933449
+0.1386998357193147,covariates,train,0.6037165082108902
+0.1391692091058437,covariates,train,0.6037165082108902
+0.13963858249237268,covariates,train,0.6041486603284356
+0.13987326918563717,covariates,train,0.6041486603284356
+0.13987326918563717,covariates,train,0.6045808124459809
+0.14010795587890168,covariates,train,0.6045808124459809
+0.14034264257216617,covariates,train,0.6050129645635264
+0.14057732926543065,covariates,train,0.6050129645635264
+0.1417507627317531,covariates,train,0.6050129645635264
+0.1422201361182821,covariates,train,0.6050129645635264
+0.1422201361182821,covariates,train,0.6058772687986171
+0.14268950950481107,covariates,train,0.6058772687986171
+0.14315888289134007,covariates,train,0.6058772687986171
+0.14339356958460456,covariates,train,0.6063094209161625
+0.14362825627786904,covariates,train,0.6063094209161625
+0.14386294297113353,covariates,train,0.6067415730337079
+0.14409762966439804,covariates,train,0.6067415730337079
+0.14409762966439804,covariates,train,0.6071737251512532
+0.14433231635766253,covariates,train,0.6071737251512532
+0.1448016897441915,covariates,train,0.6071737251512532
+0.14503637643745598,covariates,train,0.6071737251512532
+0.14503637643745598,covariates,train,0.6076058772687987
+0.14550574982398498,covariates,train,0.6076058772687987
+0.14550574982398498,covariates,train,0.6089023336214348
+0.14574043651724947,covariates,train,0.6089023336214348
+0.14597512321051395,covariates,train,0.6093344857389801
+0.14620980990377846,covariates,train,0.6101987899740708
+0.14667918329030744,covariates,train,0.6110630942091616
+0.14691386998357192,covariates,train,0.6110630942091616
+0.14691386998357192,covariates,train,0.6119273984442524
+0.14738324337010092,covariates,train,0.6119273984442524
+0.1478526167566299,covariates,train,0.6123595505617978
+0.1478526167566299,covariates,train,0.6140881590319792
+0.1480873034498944,covariates,train,0.6145203111495247
+0.1483219901431589,covariates,train,0.6145203111495247
+0.1483219901431589,covariates,train,0.6158167675021607
+0.14879136352968786,covariates,train,0.6162489196197062
+0.14879136352968786,covariates,train,0.6166810717372515
+0.14902605022295237,covariates,train,0.6166810717372515
+0.14902605022295237,covariates,train,0.6171132238547969
+0.14926073691621686,covariates,train,0.6171132238547969
+0.14973011030274583,covariates,train,0.6171132238547969
+0.14973011030274583,covariates,train,0.6175453759723423
+0.1504341703825393,covariates,train,0.6179775280898876
+0.1504341703825393,covariates,train,0.6188418323249784
+0.15090354376906828,covariates,train,0.6188418323249784
+0.15137291715559728,covariates,train,0.6188418323249784
+0.15160760384886177,covariates,train,0.6188418323249784
+0.15160760384886177,covariates,train,0.6197061365600691
+0.15207697723539076,covariates,train,0.6197061365600691
+0.15207697723539076,covariates,train,0.6205704407951599
+0.15231166392865525,covariates,train,0.6205704407951599
+0.15231166392865525,covariates,train,0.6214347450302506
+0.15254635062191974,covariates,train,0.621866897147796
+0.15325041070171322,covariates,train,0.621866897147796
+0.15325041070171322,covariates,train,0.6222990492653414
+0.1534850973949777,covariates,train,0.6222990492653414
+0.15395447078150667,covariates,train,0.6231633535004322
+0.1541891574747712,covariates,train,0.6231633535004322
+0.15489321755456464,covariates,train,0.6240276577355229
+0.15489321755456464,covariates,train,0.6244598098530683
+0.15512790424782916,covariates,train,0.6248919619706137
+0.15512790424782916,covariates,train,0.625324114088159
+0.15559727763435813,covariates,train,0.625324114088159
+0.15559727763435813,covariates,train,0.6261884183232498
+0.15559727763435813,covariates,train,0.6266205704407951
+0.15559727763435813,covariates,train,0.6274848746758859
+0.1558319643276226,covariates,train,0.6283491789109766
+0.1558319643276226,covariates,train,0.6287813310285221
+0.1563013377141516,covariates,train,0.6287813310285221
+0.1563013377141516,covariates,train,0.6296456352636128
+0.15677071110068058,covariates,train,0.6296456352636128
+0.15677071110068058,covariates,train,0.6300777873811582
+0.15724008448720958,covariates,train,0.6300777873811582
+0.15770945787373855,covariates,train,0.6305099394987036
+0.15770945787373855,covariates,train,0.6309420916162489
+0.15794414456700306,covariates,train,0.6313742437337942
+0.15794414456700306,covariates,train,0.632238547968885
+0.15841351795353203,covariates,train,0.632238547968885
+0.15864820464679652,covariates,train,0.632238547968885
+0.15911757803332552,covariates,train,0.632238547968885
+0.15911757803332552,covariates,train,0.6326707000864304
+0.1595869514198545,covariates,train,0.6326707000864304
+0.15982163811311897,covariates,train,0.6331028522039758
+0.15982163811311897,covariates,train,0.6335350043215212
+0.1600563248063835,covariates,train,0.634399308556612
+0.1600563248063835,covariates,train,0.6352636127917026
+0.16029101149964797,covariates,train,0.6352636127917026
+0.16029101149964797,covariates,train,0.6361279170267934
+0.16052569819291246,covariates,train,0.6361279170267934
+0.16052569819291246,covariates,train,0.6365600691443388
+0.16122975827270594,covariates,train,0.6365600691443388
+0.16146444496597043,covariates,train,0.6374243733794296
+0.1616991316592349,covariates,train,0.6374243733794296
+0.1621685050457639,covariates,train,0.6378565254969749
+0.1624031917390284,covariates,train,0.6382886776145204
+0.1624031917390284,covariates,train,0.6391529818496111
+0.16310725181882188,covariates,train,0.6391529818496111
+0.16357662520535085,covariates,train,0.6391529818496111
+0.16404599859187985,covariates,train,0.6391529818496111
+0.16404599859187985,covariates,train,0.6408815903197925
+0.16428068528514433,covariates,train,0.6408815903197925
+0.1647500586716733,covariates,train,0.6408815903197925
+0.16498474536493782,covariates,train,0.641313742437338
+0.16568880544473127,covariates,train,0.641313742437338
+0.16568880544473127,covariates,train,0.6417458945548833
+0.16615817883126027,covariates,train,0.6421780466724287
+0.16639286552452476,covariates,train,0.6430423509075195
+0.16662755221778924,covariates,train,0.6430423509075195
+0.16709692560431824,covariates,train,0.6439066551426103
+0.16709692560431824,covariates,train,0.6447709593777009
+0.1678009856841117,covariates,train,0.6447709593777009
+0.16850504576390518,covariates,train,0.6447709593777009
+0.16944379253696315,covariates,train,0.6447709593777009
+0.16967847923022764,covariates,train,0.6447709593777009
+0.16967847923022764,covariates,train,0.6456352636127917
+0.16967847923022764,covariates,train,0.6460674157303371
+0.17038253931002112,covariates,train,0.6460674157303371
+0.17038253931002112,covariates,train,0.6464995678478824
+0.1706172260032856,covariates,train,0.6473638720829732
+0.17085191269655012,covariates,train,0.6477960242005186
+0.1713212860830791,covariates,train,0.6477960242005186
+0.1717906594696081,covariates,train,0.6486603284356093
+0.17202534616287257,covariates,train,0.6486603284356093
+0.17202534616287257,covariates,train,0.6490924805531547
+0.17226003285613706,covariates,train,0.6499567847882455
+0.17226003285613706,covariates,train,0.651685393258427
+0.17249471954940154,covariates,train,0.6521175453759723
+0.17249471954940154,covariates,train,0.6525496974935178
+0.17296409293593054,covariates,train,0.6525496974935178
+0.17319877962919503,covariates,train,0.6525496974935178
+0.17319877962919503,covariates,train,0.6529818496110631
+0.173668153015724,covariates,train,0.6529818496110631
+0.1739028397089885,covariates,train,0.6534140017286084
+0.174137526402253,covariates,train,0.6534140017286084
+0.17437221309551748,covariates,train,0.6542783059636992
+0.17460689978878197,covariates,train,0.6542783059636992
+0.17460689978878197,covariates,train,0.6547104580812446
+0.17460689978878197,covariates,train,0.6560069144338807
+0.17460689978878197,covariates,train,0.6564390665514261
+0.17507627317531096,covariates,train,0.6568712186689715
+0.17507627317531096,covariates,train,0.6577355229040622
+0.17578033325510445,covariates,train,0.6577355229040622
+0.1764843933348979,covariates,train,0.6577355229040622
+0.1771884534146914,covariates,train,0.6577355229040622
+0.17742314010795587,covariates,train,0.658599827139153
+0.17742314010795587,covariates,train,0.6590319792566983
+0.17742314010795587,covariates,train,0.6598962834917891
+0.17765782680122036,covariates,train,0.6598962834917891
+0.17812720018774936,covariates,train,0.6603284356093345
+0.17836188688101384,covariates,train,0.6611927398444253
+0.17883126026754284,covariates,train,0.6616248919619706
+0.17883126026754284,covariates,train,0.662057044079516
+0.17906594696080733,covariates,train,0.6624891961970614
+0.1793006336540718,covariates,train,0.6624891961970614
+0.1795353203473363,covariates,train,0.6629213483146067
+0.1800046937338653,covariates,train,0.6629213483146067
+0.1800046937338653,covariates,train,0.6633535004321521
+0.18047406712039427,covariates,train,0.6637856525496975
+0.18070875381365878,covariates,train,0.6637856525496975
+0.18141281389345223,covariates,train,0.6637856525496975
+0.18188218727998123,covariates,train,0.6646499567847882
+0.18188218727998123,covariates,train,0.6650821089023337
+0.18211687397324572,covariates,train,0.665514261019879
+0.18211687397324572,covariates,train,0.6659464131374244
+0.1825862473597747,covariates,train,0.6659464131374244
+0.1830556207463037,covariates,train,0.6663785652549697
+0.1830556207463037,covariates,train,0.6668107173725151
+0.1830556207463037,covariates,train,0.6676750216076058
+0.18375968082609717,covariates,train,0.6681071737251513
+0.18422905421262614,covariates,train,0.6681071737251513
+0.18493311429241963,covariates,train,0.6685393258426966
+0.1854024876789486,covariates,train,0.6685393258426966
+0.1854024876789486,covariates,train,0.6694036300777874
+0.18563717437221308,covariates,train,0.6698357821953328
+0.18563717437221308,covariates,train,0.6702679343128781
+0.1858718610654776,covariates,train,0.6702679343128781
+0.1858718610654776,covariates,train,0.6707000864304236
+0.18610654775874208,covariates,train,0.6711322385479689
+0.18657592114527105,covariates,train,0.6711322385479689
+0.18657592114527105,covariates,train,0.6715643906655142
+0.18681060783853556,covariates,train,0.6715643906655142
+0.18727998122506453,covariates,train,0.672428694900605
+0.18727998122506453,covariates,train,0.6732929991356957
+0.18727998122506453,covariates,train,0.6741573033707865
+0.18727998122506453,covariates,train,0.6745894554883319
+0.18727998122506453,covariates,train,0.6754537597234227
+0.18751466791832902,covariates,train,0.6754537597234227
+0.18798404130485802,covariates,train,0.6754537597234227
+0.18798404130485802,covariates,train,0.6763180639585133
+0.1882187279981225,covariates,train,0.6767502160760588
+0.188453414691387,covariates,train,0.6767502160760588
+0.18986153485097396,covariates,train,0.6767502160760588
+0.19009622154423844,covariates,train,0.6767502160760588
+0.19033090823750293,covariates,train,0.6776145203111495
+0.19033090823750293,covariates,train,0.6780466724286949
+0.1905655949307674,covariates,train,0.6780466724286949
+0.1905655949307674,covariates,train,0.6784788245462403
+0.19080028162403193,covariates,train,0.6789109766637856
+0.19080028162403193,covariates,train,0.6797752808988764
+0.19150434170382538,covariates,train,0.6797752808988764
+0.1917390283970899,covariates,train,0.6802074330164217
+0.19267777517014786,covariates,train,0.6802074330164217
+0.19267777517014786,covariates,train,0.6815038893690579
+0.19291246186341235,covariates,train,0.6815038893690579
+0.19291246186341235,covariates,train,0.6823681936041487
+0.19314714855667683,covariates,train,0.6836646499567848
+0.19361652194320583,covariates,train,0.6836646499567848
+0.19385120863647032,covariates,train,0.6836646499567848
+0.1940858953297348,covariates,train,0.6840968020743302
+0.1940858953297348,covariates,train,0.6845289541918755
+0.1947899554095283,covariates,train,0.6849611063094209
+0.19502464210279277,covariates,train,0.6849611063094209
+0.19549401548932174,covariates,train,0.6849611063094209
+0.19572870218258626,covariates,train,0.6862575626620571
+0.19572870218258626,covariates,train,0.6871218668971478
+0.19572870218258626,covariates,train,0.6879861711322386
+0.19596338887585074,covariates,train,0.6879861711322386
+0.1964327622623797,covariates,train,0.6879861711322386
+0.1964327622623797,covariates,train,0.6892826274848747
+0.19666744895564423,covariates,train,0.6901469317199654
+0.19666744895564423,covariates,train,0.6910112359550562
+0.1976061957287022,covariates,train,0.691875540190147
+0.1976061957287022,covariates,train,0.6927398444252377
+0.19784088242196668,covariates,train,0.6927398444252377
+0.19807556911523116,covariates,train,0.6936041486603285
+0.19831025580849565,covariates,train,0.6936041486603285
+0.19901431588828913,covariates,train,0.6936041486603285
+0.1994836892748181,covariates,train,0.6936041486603285
+0.1994836892748181,covariates,train,0.6944684528954191
+0.19971837596808262,covariates,train,0.6953327571305099
+0.20042243604787607,covariates,train,0.6953327571305099
+0.2006571227411406,covariates,train,0.6957649092480553
+0.2006571227411406,covariates,train,0.6961970613656007
+0.20112649612766956,covariates,train,0.6961970613656007
+0.20206524290072753,covariates,train,0.6970613656006914
+0.20253461628725652,covariates,train,0.6979256698357822
+0.20323867636704998,covariates,train,0.6979256698357822
+0.2034733630603145,covariates,train,0.6983578219533275
+0.20394273644684346,covariates,train,0.6983578219533275
+0.20394273644684346,covariates,train,0.698789974070873
+0.20464679652663695,covariates,train,0.698789974070873
+0.20488148321990143,covariates,train,0.6992221261884183
+0.20511616991316592,covariates,train,0.6992221261884183
+0.20558554329969492,covariates,train,0.6992221261884183
+0.2060549166862239,covariates,train,0.6992221261884183
+0.2065242900727529,covariates,train,0.6996542783059637
+0.20675897676601737,covariates,train,0.700086430423509
+0.20699366345928186,covariates,train,0.700086430423509
+0.20769772353907534,covariates,train,0.7005185825410545
+0.2081670969256043,covariates,train,0.7005185825410545
+0.2081670969256043,covariates,train,0.7009507346585998
+0.2084017836188688,covariates,train,0.7013828867761452
+0.2084017836188688,covariates,train,0.7018150388936906
+0.2086364703121333,covariates,train,0.7026793431287813
+0.2086364703121333,covariates,train,0.7044079515989629
+0.2088711570053978,covariates,train,0.7044079515989629
+0.20910584369866228,covariates,train,0.7052722558340536
+0.20980990377845576,covariates,train,0.7052722558340536
+0.21004459047172025,covariates,train,0.7057044079515989
+0.21051396385824925,covariates,train,0.7057044079515989
+0.21051396385824925,covariates,train,0.7061365600691444
+0.21074865055151373,covariates,train,0.7061365600691444
+0.21074865055151373,covariates,train,0.7065687121866897
+0.21098333724477822,covariates,train,0.7074330164217805
+0.21145271063130722,covariates,train,0.7074330164217805
+0.21239145740436519,covariates,train,0.7078651685393258
+0.21286083079089416,covariates,train,0.709161624891962
+0.21356489087068764,covariates,train,0.709161624891962
+0.21356489087068764,covariates,train,0.7095937770095073
+0.2140342642572166,covariates,train,0.7095937770095073
+0.2145036376437456,covariates,train,0.7104580812445981
+0.21520769772353907,covariates,train,0.7108902333621435
+0.21520769772353907,covariates,train,0.7113223854796888
+0.21544238441680358,covariates,train,0.7113223854796888
+0.21544238441680358,covariates,train,0.7117545375972342
+0.21591175780333255,covariates,train,0.7117545375972342
+0.21638113118986155,covariates,train,0.7121866897147796
+0.21685050457639052,covariates,train,0.7121866897147796
+0.217085191269655,covariates,train,0.7126188418323249
+0.217085191269655,covariates,train,0.7130509939498704
+0.217085191269655,covariates,train,0.7139152981849611
+0.217554564656184,covariates,train,0.7139152981849611
+0.2177892513494485,covariates,train,0.7139152981849611
+0.21825862473597746,covariates,train,0.7139152981849611
+0.21872799812250646,covariates,train,0.7143474503025065
+0.21872799812250646,covariates,train,0.7147796024200519
+0.21896268481577094,covariates,train,0.7147796024200519
+0.21919737150903543,covariates,train,0.7152117545375972
+0.21943205820229994,covariates,train,0.716076058772688
+0.21966674489556443,covariates,train,0.7165082108902333
+0.2199014315888289,covariates,train,0.7165082108902333
+0.2199014315888289,covariates,train,0.7169403630077787
+0.2203708049753579,covariates,train,0.7169403630077787
+0.22084017836188688,covariates,train,0.7173725151253241
+0.22107486505515136,covariates,train,0.7178046672428695
+0.22130955174841588,covariates,train,0.7178046672428695
+0.22130955174841588,covariates,train,0.7186689714779603
+0.22224829852147382,covariates,train,0.7191011235955056
+0.22248298521473833,covariates,train,0.7191011235955056
+0.22271767190800282,covariates,train,0.719533275713051
+0.2229523586012673,covariates,train,0.719533275713051
+0.2229523586012673,covariates,train,0.7199654278305964
+0.2234217319877963,covariates,train,0.7208297320656871
+0.2236564186810608,covariates,train,0.7208297320656871
+0.22482985214738324,covariates,train,0.7212618841832324
+0.22506453884064773,covariates,train,0.7221261884183232
+0.2257685989204412,covariates,train,0.7225583405358686
+0.2257685989204412,covariates,train,0.722990492653414
+0.2262379723069702,covariates,train,0.7234226447709594
+0.2262379723069702,covariates,train,0.7238547968885047
+0.2264726590002347,covariates,train,0.7238547968885047
+0.2264726590002347,covariates,train,0.7242869490060502
+0.22670734569349918,covariates,train,0.7247191011235955
+0.22694203238676366,covariates,train,0.7247191011235955
+0.22741140577329266,covariates,train,0.7247191011235955
+0.22764609246655715,covariates,train,0.7255834053586863
+0.22788077915982163,covariates,train,0.7255834053586863
+0.22999295939920206,covariates,train,0.7277441659464131
+0.23022764609246657,covariates,train,0.7277441659464131
+0.23069701947899554,covariates,train,0.7281763180639585
+0.2311663928655245,covariates,train,0.7281763180639585
+0.23140107955878902,covariates,train,0.7290406222990493
+0.23140107955878902,covariates,train,0.72990492653414
+0.2316357662520535,covariates,train,0.7303370786516854
+0.231870452945318,covariates,train,0.7316335350043215
+0.23210513963858248,covariates,train,0.7320656871218669
+0.23257451302511148,covariates,train,0.7320656871218669
+0.23304388641164045,covariates,train,0.7337942955920485
+0.23304388641164045,covariates,train,0.7342264477095938
+0.23374794649143393,covariates,train,0.7342264477095938
+0.2346866932644919,covariates,train,0.7346585998271391
+0.2346866932644919,covariates,train,0.7355229040622299
+0.2349213799577564,covariates,train,0.7355229040622299
+0.23539075334428539,covariates,train,0.7368193604148661
+0.23586012673081436,covariates,train,0.7368193604148661
+0.23632950011734336,covariates,train,0.7368193604148661
+0.23726824689040132,covariates,train,0.7394122731201382
+0.2375029335836658,covariates,train,0.7394122731201382
+0.23844168035672378,covariates,train,0.7411408815903198
+0.23844168035672378,covariates,train,0.7415730337078652
+0.23891105374325275,covariates,train,0.7415730337078652
+0.23938042712978175,covariates,train,0.7420051858254105
+0.2405538605961042,covariates,train,0.7428694900605013
+0.2405538605961042,covariates,train,0.7433016421780466
+0.24172729406242666,covariates,train,0.7450302506482281
+0.24219666744895565,covariates,train,0.7463267070008643
+0.24243135414222014,covariates,train,0.7467588591184097
+0.2429007275287491,covariates,train,0.7467588591184097
+0.24383947430180708,covariates,train,0.7476231633535004
+0.24477822107486505,covariates,train,0.7480553154710458
+0.24477822107486505,covariates,train,0.7484874675885912
+0.24501290776812953,covariates,train,0.7484874675885912
+0.24524759446139405,covariates,train,0.7489196197061365
+0.24735977470077447,covariates,train,0.7510803802938635
+0.24759446139403896,covariates,train,0.7510803802938635
+0.24806383478056795,covariates,train,0.7510803802938635
+0.24829852147383244,covariates,train,0.7515125324114088
+0.24829852147383244,covariates,train,0.7519446845289542
+0.2487678948603614,covariates,train,0.7532411408815903
+0.2490025815536259,covariates,train,0.7532411408815903
+0.2494719549401549,covariates,train,0.7532411408815903
+0.2494719549401549,covariates,train,0.7545375972342264
+0.24994132832668386,covariates,train,0.7558340535868626
+0.25017601501994835,covariates,train,0.756266205704408
+0.25017601501994835,covariates,train,0.7566983578219534
+0.25088007509974186,covariates,train,0.7571305099394987
+0.2515841351795353,covariates,train,0.7579948141745895
+0.2525228819525933,covariates,train,0.7592912705272256
+0.2527575686458578,covariates,train,0.759723422644771
+0.25369631541891574,covariates,train,0.7605877268798618
+0.2539310021121802,covariates,train,0.7605877268798618
+0.2541656888054447,covariates,train,0.7614520311149524
+0.25463506219197374,covariates,train,0.7627484874675886
+0.25463506219197374,covariates,train,0.7631806395851339
+0.2551044355785027,covariates,train,0.7631806395851339
+0.2551044355785027,covariates,train,0.7649092480553155
+0.2555738089650317,covariates,train,0.7649092480553155
+0.25604318235156065,covariates,train,0.7653414001728609
+0.25627786904482514,covariates,train,0.7670700086430423
+0.2574513025111476,covariates,train,0.7687986171132238
+0.2576859892044121,covariates,train,0.7692307692307693
+0.2581553625909411,covariates,train,0.7705272255834054
+0.2581553625909411,covariates,train,0.7709593777009507
+0.2581553625909411,covariates,train,0.7718236819360415
+0.2581553625909411,covariates,train,0.7722558340535869
+0.2586247359774701,covariates,train,0.7722558340535869
+0.25909410936399907,covariates,train,0.7731201382886776
+0.25956348275052804,covariates,train,0.7731201382886776
+0.2597981694437925,covariates,train,0.7731201382886776
+0.261440976296644,covariates,train,0.7739844425237684
+0.2633184698427599,covariates,train,0.7752808988764045
+0.2635531565360244,covariates,train,0.7757130509939498
+0.2647265900023469,covariates,train,0.7761452031114953
+0.26519596338887585,covariates,train,0.7761452031114953
+0.26543065008214034,covariates,train,0.7765773552290406
+0.2656653367754048,covariates,train,0.7765773552290406
+0.2661347101619338,covariates,train,0.7765773552290406
+0.2668387702417273,covariates,train,0.777009507346586
+0.2673081436282563,covariates,train,0.7787381158167676
+0.26754283032152076,covariates,train,0.7791702679343129
+0.2696550105609012,covariates,train,0.7821953327571305
+0.2698896972541657,covariates,train,0.7821953327571305
+0.27012438394743016,covariates,train,0.7826274848746759
+0.2705937573339592,covariates,train,0.7826274848746759
+0.27082844402722367,covariates,train,0.7834917891097667
+0.27106313072048815,covariates,train,0.7834917891097667
+0.2724712508800751,covariates,train,0.783923941227312
+0.2727059375733396,covariates,train,0.783923941227312
+0.2731753109598686,covariates,train,0.783923941227312
+0.27434874442619106,covariates,train,0.7843560933448573
+0.27575686458577797,covariates,train,0.7843560933448573
+0.27599155127904246,covariates,train,0.7843560933448573
+0.2783384182116874,covariates,train,0.7847882454624028
+0.2785731049049519,covariates,train,0.7847882454624028
+0.2799812250645388,covariates,train,0.7865168539325843
+0.28021591175780336,covariates,train,0.7865168539325843
+0.28068528514433233,covariates,train,0.7878133102852204
+0.2811546585308613,covariates,train,0.7895419187554019
+0.2811546585308613,covariates,train,0.7899740708729472
+0.28185871861065476,covariates,train,0.7899740708729472
+0.28209340530391924,covariates,train,0.7899740708729472
+0.2823280919971838,covariates,train,0.7904062229904927
+0.2823280919971838,covariates,train,0.790838375108038
+0.28279746538371275,covariates,train,0.7925669835782195
+0.28279746538371275,covariates,train,0.7929991356957649
+0.2842055855432997,covariates,train,0.7955920484010371
+0.2842055855432997,covariates,train,0.7960242005185826
+0.2849096456230932,covariates,train,0.7968885047536733
+0.28537901900962215,covariates,train,0.7968885047536733
+0.28561370570288663,covariates,train,0.799913569576491
+0.28631776578268014,covariates,train,0.8007778738115817
+0.2867871391692091,covariates,train,0.8016421780466725
+0.2870218258624736,covariates,train,0.8016421780466725
+0.28842994602206057,covariates,train,0.8025064822817631
+0.28866463271532505,covariates,train,0.8029386343993086
+0.289134006101854,covariates,train,0.8046672428694901
+0.289134006101854,covariates,train,0.8050993949870354
+0.2893686927951185,covariates,train,0.8050993949870354
+0.29148087303449893,covariates,train,0.8089887640449438
+0.2919502464210279,covariates,train,0.8094209161624892
+0.2919502464210279,covariates,train,0.8098530682800346
+0.2928889931940859,covariates,train,0.8098530682800346
+0.29382773996714384,covariates,train,0.8098530682800346
+0.29453180004693735,covariates,train,0.8115816767502161
+0.2950011734334663,covariates,train,0.8120138288677614
+0.2952358601267308,covariates,train,0.8120138288677614
+0.2961746068997888,covariates,train,0.8120138288677614
+0.29711335367284675,covariates,train,0.8124459809853068
+0.29734804036611123,covariates,train,0.8141745894554884
+0.2975827270593757,covariates,train,0.8141745894554884
+0.3011030274583431,covariates,train,0.8176318063958513
+0.3015724008448721,covariates,train,0.8176318063958513
+0.3025111476179301,covariates,train,0.8184961106309421
+0.30321520769772353,covariates,train,0.8189282627484875
+0.3036845810842525,covariates,train,0.8189282627484875
+0.303919267777517,covariates,train,0.8197925669835783
+0.304858014550575,covariates,train,0.8197925669835783
+0.30509270124383947,covariates,train,0.8197925669835783
+0.30556207463036844,covariates,train,0.8197925669835783
+0.30603144801689747,covariates,train,0.8236819360414867
+0.30626613471016195,covariates,train,0.8236819360414867
+0.3067355080966909,covariates,train,0.8236819360414867
+0.3069701947899554,covariates,train,0.824114088159032
+0.3072048814832199,covariates,train,0.824114088159032
+0.30861300164280686,covariates,train,0.824114088159032
+0.30884768833607135,covariates,train,0.824114088159032
+0.31142924196198074,covariates,train,0.8267070008643043
+0.31189861534850977,covariates,train,0.8267070008643043
+0.3128373621215677,covariates,train,0.8297320656871219
+0.3140107955878902,covariates,train,0.8297320656871219
+0.3140107955878902,covariates,train,0.8301642178046672
+0.31471485566768365,covariates,train,0.8318928262748487
+0.3151842290542126,covariates,train,0.8331892826274849
+0.3165923492137996,covariates,train,0.8331892826274849
+0.31682703590706407,covariates,train,0.8331892826274849
+0.31729640929359304,covariates,train,0.8331892826274849
+0.317765782680122,covariates,train,0.8331892826274849
+0.319173902839709,covariates,train,0.8340535868625756
+0.320112649612767,covariates,train,0.8370786516853933
+0.32081670969256043,covariates,train,0.837942955920484
+0.3236329500117343,covariates,train,0.8435609334485739
+0.3245716967847923,covariates,train,0.8439930855661193
+0.3248063834780568,covariates,train,0.8439930855661193
+0.3257451302511148,covariates,train,0.8465859982713916
+0.3259798169443793,covariates,train,0.8470181503889369
+0.32621450363764376,covariates,train,0.8478824546240277
+0.3269185637174372,covariates,train,0.848314606741573
+0.3271532504107017,covariates,train,0.8487467588591184
+0.32762262379723067,covariates,train,0.8491789109766638
+0.3278573104904952,covariates,train,0.8491789109766638
+0.32903074395681764,covariates,train,0.8504753673293
+0.3292654306500821,covariates,train,0.8504753673293
+0.32973480403661115,covariates,train,0.8504753673293
+0.32996949072987564,covariates,train,0.8509075194468453
+0.33231635766252055,covariates,train,0.8526361279170268
+0.333020417742314,covariates,train,0.8530682800345721
+0.333959164515372,covariates,train,0.8543647363872083
+0.33442853790190097,covariates,train,0.8547968885047537
+0.33489791128842994,covariates,train,0.8547968885047537
+0.33583665806148794,covariates,train,0.8552290406222991
+0.3360713447547524,covariates,train,0.8569576490924805
+0.3363060314480169,covariates,train,0.8569576490924805
+0.33747946491433933,covariates,train,0.857389801210026
+0.33841821168739733,covariates,train,0.857389801210026
+0.33841821168739733,covariates,train,0.8578219533275713
+0.3386528983806618,covariates,train,0.8578219533275713
+0.3391222717671908,covariates,train,0.8582541054451167
+0.33959164515371976,covariates,train,0.8582541054451167
+0.34076507862004224,covariates,train,0.8599827139152982
+0.34076507862004224,covariates,train,0.8604148660328436
+0.3409997653133067,covariates,train,0.8604148660328436
+0.34405069232574514,covariates,train,0.8651685393258427
+0.34428537901900963,covariates,train,0.8651685393258427
+0.34545881248533206,covariates,train,0.8651685393258427
+0.34639755925839005,covariates,train,0.8664649956784788
+0.347805679417977,covariates,train,0.8707865168539326
+0.3480403661112415,covariates,train,0.8712186689714779
+0.34874442619103496,covariates,train,0.8712186689714779
+0.34921379957756393,covariates,train,0.8712186689714779
+0.34968317296409296,covariates,train,0.8712186689714779
+0.3503872330438864,covariates,train,0.8729472774416595
+0.3506219197371509,covariates,train,0.8733794295592049
+0.35109129312367987,covariates,train,0.8738115816767502
+0.3515606665102089,covariates,train,0.874675885911841
+0.3539075334428538,covariates,train,0.8794295592048401
+0.35555034029570526,covariates,train,0.8811581676750216
+0.3564890870687632,covariates,train,0.881590319792567
+0.3574278338418212,covariates,train,0.8824546240276577
+0.35789720722835017,covariates,train,0.8824546240276577
+0.35813189392161465,covariates,train,0.8824546240276577
+0.3602440741609951,covariates,train,0.8841832324978393
+0.3602440741609951,covariates,train,0.8846153846153846
+0.361182820934053,covariates,train,0.8846153846153846
+0.36141750762731756,covariates,train,0.88504753673293
+0.36165219432058204,covariates,train,0.88504753673293
+0.36188688101384653,covariates,train,0.8872082973206569
+0.36259094109364,covariates,train,0.8872082973206569
+0.36306031448016896,covariates,train,0.8876404494382022
+0.3672846749589298,covariates,train,0.8910976663785652
+0.36775404834545883,covariates,train,0.8915298184961107
+0.3679887350387233,covariates,train,0.891961970613656
+0.3682234217319878,covariates,train,0.891961970613656
+0.3693968551983103,covariates,train,0.8936905790838375
+0.3693968551983103,covariates,train,0.8949870354364736
+0.36963154189157477,covariates,train,0.8954191875540191
+0.37010091527810374,covariates,train,0.8954191875540191
+0.3708049753578972,covariates,train,0.8958513396715644
+0.3710396620511617,covariates,train,0.8958513396715644
+0.3715090354376907,covariates,train,0.8958513396715644
+0.37362121567707113,covariates,train,0.8975799481417459
+0.3740905890636001,covariates,train,0.8975799481417459
+0.3740905890636001,covariates,train,0.8980121002592912
+0.3743252757568646,covariates,train,0.8980121002592912
+0.3743252757568646,covariates,train,0.8984442523768367
+0.37455996245012907,covariates,train,0.8997407087294728
+0.37808026284909646,covariates,train,0.9066551426101987
+0.37831494954236095,covariates,train,0.9066551426101987
+0.38183524994132834,covariates,train,0.9083837510803803
+0.3825393100211218,covariates,train,0.9088159031979257
+0.3827739967143863,covariates,train,0.9088159031979257
+0.3832433701009153,covariates,train,0.9096802074330165
+0.3837127434874443,covariates,train,0.9096802074330165
+0.3848861769537667,covariates,train,0.9096802074330165
+0.3869983571931471,covariates,train,0.9118409680207433
+0.38723304388641167,covariates,train,0.9118409680207433
+0.38723304388641167,covariates,train,0.9122731201382887
+0.3879371039662051,covariates,train,0.9127052722558341
+0.3879371039662051,covariates,train,0.9131374243733794
+0.3893452241257921,covariates,train,0.9140017286084702
+0.3895799108190566,covariates,train,0.9140017286084702
+0.39004928420558554,covariates,train,0.9144338807260155
+0.39028397089885003,covariates,train,0.9144338807260155
+0.3928655245247594,covariates,train,0.916162489196197
+0.39333489791128845,covariates,train,0.9174589455488332
+0.39356958460455294,covariates,train,0.9174589455488332
+0.3942736446843464,covariates,train,0.918323249783924
+0.39826331846984275,covariates,train,0.9196197061365601
+0.3989673785496362,covariates,train,0.9204840103716508
+0.39920206524290075,covariates,train,0.9213483146067416
+0.3996714386294297,covariates,train,0.9213483146067416
+0.4024876789486036,covariates,train,0.9222126188418324
+0.40295705233513257,covariates,train,0.9230769230769231
+0.4034264257216616,covariates,train,0.9230769230769231
+0.4057732926543065,covariates,train,0.9235090751944685
+0.406007979347571,covariates,train,0.9235090751944685
+0.40647735273409996,covariates,train,0.9239412273120138
+0.40765078620042244,covariates,train,0.9243733794295592
+0.40788547289368693,covariates,train,0.9243733794295592
+0.4116404599859188,covariates,train,0.92523768366465
+0.4118751466791833,covariates,train,0.9256698357821953
+0.4118751466791833,covariates,train,0.9261019878997407
+0.4121098333724478,covariates,train,0.9261019878997407
+0.41257920675897675,covariates,train,0.9265341400172861
+0.41257920675897675,covariates,train,0.9269662921348315
+0.41328326683877026,covariates,train,0.9278305963699223
+0.41586482046467965,covariates,train,0.9291270527225584
+0.4189157474771181,covariates,train,0.9291270527225584
+0.41961980755691153,covariates,train,0.9295592048401037
+0.419854494250176,covariates,train,0.9295592048401037
+0.420793241023234,covariates,train,0.9295592048401037
+0.421262614409763,covariates,train,0.9295592048401037
+0.42196667448955644,covariates,train,0.9295592048401037
+0.4222013611828209,covariates,train,0.9295592048401037
+0.4231401079558789,covariates,train,0.9295592048401037
+0.42759915512790425,covariates,train,0.9325842696629213
+0.42783384182116874,covariates,train,0.9325842696629213
+0.4283032152076977,covariates,train,0.9325842696629213
+0.4285379019009622,covariates,train,0.9325842696629213
+0.4290072752874912,covariates,train,0.9338807260155575
+0.4294766486740202,covariates,train,0.9338807260155575
+0.4313541422201361,covariates,train,0.9351771823681936
+0.43604787608542595,covariates,train,0.9382022471910112
+0.43628256277869043,covariates,train,0.9382022471910112
+0.43675193616521946,covariates,train,0.9382022471910112
+0.4374559962450129,covariates,train,0.9382022471910112
+0.4379253696315419,covariates,train,0.9382022471910112
+0.4409762966439803,covariates,train,0.939066551426102
+0.4412109833372448,covariates,train,0.939066551426102
+0.44168035672377376,covariates,train,0.9394987035436474
+0.44168035672377376,covariates,train,0.9399308556611927
+0.44214973011030273,covariates,train,0.9399308556611927
+0.4461394038957991,covariates,train,0.9407951598962835
+0.4463740905890636,covariates,train,0.9407951598962835
+0.4468434639755926,covariates,train,0.9407951598962835
+0.4473128373621216,covariates,train,0.9416594641313742
+0.44754752405538606,covariates,train,0.9416594641313742
+0.448486270828444,covariates,train,0.9416594641313742
+0.4529453180004694,covariates,train,0.942523768366465
+0.45364937808026284,covariates,train,0.942523768366465
+0.4541187514667918,covariates,train,0.942523768366465
+0.4543534381600563,covariates,train,0.9433880726015558
+0.4550574982398498,covariates,train,0.9438202247191011
+0.4555268716263788,covariates,train,0.9442523768366465
+0.45576155831964327,covariates,train,0.9442523768366465
+0.45716967847923023,covariates,train,0.9451166810717373
+0.4602206054916686,covariates,train,0.9472774416594641
+0.4602206054916686,covariates,train,0.9481417458945549
+0.4611593522647266,covariates,train,0.9481417458945549
+0.46209809903778454,covariates,train,0.9485738980121002
+0.46209809903778454,covariates,train,0.9490060501296457
+0.4667918329030744,covariates,train,0.9511668107173725
+0.46773057967613235,covariates,train,0.9511668107173725
+0.4681999530626613,covariates,train,0.9511668107173725
+0.4726590002346867,covariates,train,0.9520311149524633
+0.4731283736212157,covariates,train,0.9520311149524633
+0.47477118047406713,covariates,train,0.952895419187554
+0.4752405538605961,covariates,train,0.952895419187554
+0.47805679417977,covariates,train,0.9554883318928262
+0.478526167566299,covariates,train,0.956352636127917
+0.478995540952828,covariates,train,0.956352636127917
+0.478995540952828,covariates,train,0.9567847882454624
+0.47923022764609247,covariates,train,0.9567847882454624
+0.4801689744191504,covariates,train,0.9567847882454624
+0.4848627082844403,covariates,train,0.9576490924805532
+0.48556676836423374,covariates,train,0.9580812445980985
+0.48650551513729173,covariates,train,0.9580812445980985
+0.4867402018305562,covariates,train,0.958513396715644
+0.4869748885238207,covariates,train,0.958513396715644
+0.48767894860361416,covariates,train,0.9589455488331893
+0.48861769537667216,covariates,train,0.9602420051858254
+0.4930767425486975,covariates,train,0.9611063094209161
+0.49378080262849094,covariates,train,0.9611063094209161
+0.49425017601501997,covariates,train,0.9611063094209161
+0.4949542360948134,covariates,train,0.9619706136560069
+0.4956582961746069,covariates,train,0.9619706136560069
+0.49589298286787137,covariates,train,0.9619706136560069
+0.5003520300398967,covariates,train,0.9619706136560069
+0.5015254635062192,covariates,train,0.9619706136560069
+0.5064538840647735,covariates,train,0.9624027657735523
+0.5069232574513025,covariates,train,0.9624027657735523
+0.507157944144567,covariates,train,0.9624027657735523
+0.507157944144567,covariates,train,0.9632670700086431
+0.5078620042243605,covariates,train,0.9636992221261884
+0.5083313776108894,covariates,train,0.9636992221261884
+0.5130251114761794,covariates,train,0.9641313742437337
+0.5132597981694438,covariates,train,0.9641313742437337
+0.5139638582492373,covariates,train,0.9641313742437337
+0.5146679183290307,covariates,train,0.9641313742437337
+0.5167800985684111,covariates,train,0.9645635263612792
+0.5167800985684111,covariates,train,0.9649956784788245
+0.5170147852616757,covariates,train,0.9649956784788245
+0.5170147852616757,covariates,train,0.9654278305963699
+0.5177188453414692,covariates,train,0.9654278305963699
+0.5179535320347336,covariates,train,0.9654278305963699
+0.5188922788077917,covariates,train,0.9654278305963699
+0.519596338887585,covariates,train,0.9654278305963699
+0.5207697723539075,covariates,train,0.9658599827139153
+0.5249941328326684,covariates,train,0.9671564390665515
+0.5259328796057263,covariates,train,0.9671564390665515
+0.5266369396855198,covariates,train,0.9671564390665515
+0.5271063130720488,covariates,train,0.9671564390665515
+0.5306266134710161,covariates,train,0.9680207433016422
+0.5313306735508097,covariates,train,0.9680207433016422
+0.5313306735508097,covariates,train,0.9684528954191876
+0.5327387937103967,covariates,train,0.9684528954191876
+0.533912227176719,covariates,train,0.9684528954191876
+0.5350856606430415,covariates,train,0.9693171996542783
+0.5355550340295705,covariates,train,0.9693171996542783
+0.5364937808026284,covariates,train,0.9693171996542783
+0.536728467495893,covariates,train,0.9693171996542783
+0.536728467495893,covariates,train,0.9697493517718236
+0.5383712743487444,covariates,train,0.9697493517718236
+0.5404834545881249,covariates,train,0.9701815038893691
+0.5409528279746538,covariates,train,0.9706136560069144
+0.5418915747477118,covariates,train,0.9706136560069144
+0.5423609481342407,covariates,train,0.9710458081244598
+0.5442384416803567,covariates,train,0.9710458081244598
+0.5461159352264726,covariates,train,0.9710458081244598
+0.5468199953062661,covariates,train,0.9714779602420052
+0.5472893686927951,covariates,train,0.9714779602420052
+0.5496362356254401,covariates,train,0.9714779602420052
+0.5496362356254401,covariates,train,0.9719101123595506
+0.550105609011969,covariates,train,0.9719101123595506
+0.5512790424782915,covariates,train,0.9719101123595506
+0.5522177892513495,covariates,train,0.9719101123595506
+0.5526871626378784,covariates,train,0.9719101123595506
+0.5526871626378784,covariates,train,0.9723422644770959
+0.5540952827974653,covariates,train,0.9723422644770959
+0.5540952827974653,covariates,train,0.9727744165946414
+0.5550340295705234,covariates,train,0.9727744165946414
+0.5550340295705234,covariates,train,0.9732065687121867
+0.5555034029570524,covariates,train,0.9732065687121867
+0.5562074630368458,covariates,train,0.9732065687121867
+0.5569115231166393,covariates,train,0.973638720829732
+0.5571462098099038,covariates,train,0.9740708729472775
+0.5580849565829618,covariates,train,0.9740708729472775
+0.5585543299694907,covariates,train,0.9740708729472775
+0.5587890166627553,covariates,train,0.9745030250648228
+0.5601971368223422,covariates,train,0.9745030250648228
+0.5609011969021357,covariates,train,0.9749351771823682
+0.5618399436751936,covariates,train,0.9749351771823682
+0.5634827505280451,covariates,train,0.9749351771823682
+0.5634827505280451,covariates,train,0.9753673292999135
+0.563952123914574,covariates,train,0.975799481417459
+0.563952123914574,covariates,train,0.9762316335350043
+0.5646561839943676,covariates,train,0.9762316335350043
+0.564890870687632,covariates,train,0.9766637856525497
+0.565360244074161,covariates,train,0.9766637856525497
+0.5655949307674255,covariates,train,0.9766637856525497
+0.5655949307674255,covariates,train,0.9775280898876404
+0.567237737620277,covariates,train,0.9775280898876404
+0.5684111710865994,covariates,train,0.9775280898876404
+0.5716967847923022,covariates,train,0.9775280898876404
+0.5716967847923022,covariates,train,0.9779602420051858
+0.5719314714855668,covariates,train,0.9779602420051858
+0.5724008448720957,covariates,train,0.9779602420051858
+0.5726355315653603,covariates,train,0.9779602420051858
+0.5731049049518893,covariates,train,0.9779602420051858
+0.5731049049518893,covariates,train,0.9783923941227312
+0.5738089650316827,covariates,train,0.9783923941227312
+0.5742783384182117,covariates,train,0.9783923941227312
+0.5752170851912697,covariates,train,0.9783923941227312
+0.5754517718845341,covariates,train,0.9783923941227312
+0.5759211452710631,covariates,train,0.9783923941227312
+0.5763905186575922,covariates,train,0.9783923941227312
+0.5770945787373856,covariates,train,0.9783923941227312
+0.5775639521239145,covariates,train,0.9783923941227312
+0.5799108190565595,covariates,train,0.9783923941227312
+0.5808495658296174,covariates,train,0.9783923941227312
+0.581084252522882,covariates,train,0.9783923941227312
+0.581084252522882,covariates,train,0.9788245462402766
+0.5813189392161464,covariates,train,0.9788245462402766
+0.5813189392161464,covariates,train,0.9792566983578219
+0.5820229992959399,covariates,train,0.9792566983578219
+0.5829617460689979,covariates,train,0.9792566983578219
+0.5829617460689979,covariates,train,0.9796888504753674
+0.5839004928420558,covariates,train,0.9796888504753674
+0.5843698662285849,covariates,train,0.9796888504753674
+0.5843698662285849,covariates,train,0.9801210025929127
+0.5848392396151139,covariates,train,0.9801210025929127
+0.5848392396151139,covariates,train,0.9805531547104581
+0.5862473597747008,covariates,train,0.9805531547104581
+0.5867167331612297,covariates,train,0.9805531547104581
+0.5871861065477587,covariates,train,0.9805531547104581
+0.5881248533208168,covariates,train,0.9805531547104581
+0.5885942267073457,covariates,train,0.9805531547104581
+0.5895329734804037,covariates,train,0.9805531547104581
+0.5900023468669326,covariates,train,0.9805531547104581
+0.5907064069467262,covariates,train,0.9805531547104581
+0.5911757803332551,covariates,train,0.9805531547104581
+0.5911757803332551,covariates,train,0.9814174589455489
+0.5916451537197841,covariates,train,0.9814174589455489
+0.5923492137995776,covariates,train,0.9814174589455489
+0.594461394038958,covariates,train,0.9814174589455489
+0.594461394038958,covariates,train,0.9818496110630942
+0.5946960807322225,covariates,train,0.9818496110630942
+0.5946960807322225,covariates,train,0.9822817631806395
+0.5951654541187514,covariates,train,0.9822817631806395
+0.595869514198545,covariates,train,0.9822817631806395
+0.5963388875850739,covariates,train,0.9822817631806395
+0.5965735742783385,covariates,train,0.982713915298185
+0.5972776343581319,covariates,train,0.982713915298185
+0.5977470077446608,covariates,train,0.982713915298185
+0.5989204412109833,covariates,train,0.982713915298185
+0.5993898145975123,covariates,train,0.9835782195332757
+0.5998591879840413,covariates,train,0.9835782195332757
+0.6000938746773058,covariates,train,0.9840103716508211
+0.6026754283032152,covariates,train,0.9840103716508211
+0.6031448016897442,covariates,train,0.9840103716508211
+0.6033794883830087,covariates,train,0.9844425237683665
+0.6040835484628022,covariates,train,0.9844425237683665
+0.6045529218493312,covariates,train,0.9844425237683665
+0.6061957287021826,covariates,train,0.9844425237683665
+0.606899788781976,covariates,train,0.9844425237683665
+0.607369162168505,covariates,train,0.9844425237683665
+0.607369162168505,covariates,train,0.9848746758859118
+0.6085425956348275,covariates,train,0.9848746758859118
+0.6094813424078854,covariates,train,0.9848746758859118
+0.6106547758742079,covariates,train,0.9848746758859118
+0.6106547758742079,covariates,train,0.9853068280034573
+0.6111241492607369,covariates,train,0.9853068280034573
+0.6122975827270594,covariates,train,0.9853068280034573
+0.6132363295001173,covariates,train,0.9853068280034573
+0.6137057028866463,covariates,train,0.9853068280034573
+0.6144097629664398,covariates,train,0.9853068280034573
+0.6148791363529688,covariates,train,0.9853068280034573
+0.6151138230462333,covariates,train,0.9853068280034573
+0.6155831964327623,covariates,train,0.9853068280034573
+0.6158178831260267,covariates,train,0.9857389801210026
+0.6160525698192912,covariates,train,0.9857389801210026
+0.6165219432058202,covariates,train,0.9857389801210026
+0.6167566298990848,covariates,train,0.9857389801210026
+0.6179300633654072,covariates,train,0.9857389801210026
+0.6181647500586717,covariates,train,0.9857389801210026
+0.6186341234452006,covariates,train,0.9857389801210026
+0.6205116169913166,covariates,train,0.986171132238548
+0.621685050457639,covariates,train,0.986171132238548
+0.6219197371509035,covariates,train,0.9866032843560933
+0.6233278573104905,covariates,train,0.9870354364736387
+0.623562544003755,covariates,train,0.9870354364736387
+0.624031917390284,covariates,train,0.9870354364736387
+0.6252053508566064,covariates,train,0.9870354364736387
+0.6263787843229289,covariates,train,0.9870354364736387
+0.6273175310959869,covariates,train,0.9870354364736387
+0.6275522177892513,covariates,train,0.9870354364736387
+0.6280215911757804,covariates,train,0.9870354364736387
+0.6284909645623094,covariates,train,0.9870354364736387
+0.6289603379488383,covariates,train,0.9870354364736387
+0.6291950246421028,covariates,train,0.9874675885911841
+0.6303684581084252,covariates,train,0.9874675885911841
+0.6313072048814832,covariates,train,0.9874675885911841
+0.6315418915747477,covariates,train,0.9878997407087294
+0.6336540718141281,covariates,train,0.9878997407087294
+0.6338887585073927,covariates,train,0.9878997407087294
+0.6343581318939217,covariates,train,0.9878997407087294
+0.6345928185871861,covariates,train,0.9878997407087294
+0.6357662520535086,covariates,train,0.9878997407087294
+0.6364703121333021,covariates,train,0.9878997407087294
+0.636939685519831,covariates,train,0.9878997407087294
+0.637878432292889,covariates,train,0.9878997407087294
+0.6381131189861535,covariates,train,0.9878997407087294
+0.6395212391457404,covariates,train,0.9883318928262749
+0.639755925839005,covariates,train,0.9883318928262749
+0.640225299225534,covariates,train,0.9883318928262749
+0.6411640459985919,covariates,train,0.9883318928262749
+0.6425721661581788,covariates,train,0.9883318928262749
+0.6430415395447078,covariates,train,0.9883318928262749
+0.6439802863177658,covariates,train,0.9883318928262749
+0.6463271532504107,covariates,train,0.9883318928262749
+0.6475005867167332,covariates,train,0.9883318928262749
+0.6479699601032621,covariates,train,0.9883318928262749
+0.6500821403426426,covariates,train,0.9887640449438202
+0.6510208871157005,covariates,train,0.9887640449438202
+0.6514902605022296,covariates,train,0.9887640449438202
+0.6519596338887585,covariates,train,0.9887640449438202
+0.6524290072752875,covariates,train,0.9887640449438202
+0.6528983806618165,covariates,train,0.9891961970613656
+0.6538371274348744,covariates,train,0.9891961970613656
+0.6585308613001642,covariates,train,0.989628349178911
+0.6594696080732223,covariates,train,0.989628349178911
+0.6597042947664867,covariates,train,0.989628349178911
+0.6611124149260736,covariates,train,0.989628349178911
+0.6615817883126027,covariates,train,0.989628349178911
+0.6622858483923961,covariates,train,0.989628349178911
+0.6643980286317765,covariates,train,0.989628349178911
+0.6648674020183055,covariates,train,0.989628349178911
+0.6648674020183055,covariates,train,0.9900605012964564
+0.6658061487913636,covariates,train,0.9900605012964564
+0.6662755221778925,covariates,train,0.9900605012964564
+0.6667448955644215,covariates,train,0.9900605012964564
+0.6672142689509505,covariates,train,0.9900605012964564
+0.667448955644215,covariates,train,0.9900605012964564
+0.6681530157240084,covariates,train,0.9900605012964564
+0.668387702417273,covariates,train,0.9900605012964564
+0.6690917624970664,covariates,train,0.9900605012964564
+0.6700305092701244,covariates,train,0.9900605012964564
+0.6721426895095048,covariates,train,0.9900605012964564
+0.6728467495892982,covariates,train,0.9900605012964564
+0.6728467495892982,covariates,train,0.9904926534140017
+0.6735508096690918,covariates,train,0.9904926534140017
+0.6740201830556207,covariates,train,0.9904926534140017
+0.6747242431354142,covariates,train,0.9904926534140017
+0.6749589298286787,covariates,train,0.9904926534140017
+0.6777751701478526,covariates,train,0.9904926534140017
+0.6782445435343816,covariates,train,0.9904926534140017
+0.6787139169209105,covariates,train,0.9904926534140017
+0.680826097160291,covariates,train,0.9904926534140017
+0.6810607838535555,covariates,train,0.9904926534140017
+0.6815301572400845,covariates,train,0.9904926534140017
+0.6834076507862005,covariates,train,0.9904926534140017
+0.6838770241727294,covariates,train,0.9904926534140017
+0.6843463975592584,covariates,train,0.9904926534140017
+0.6845810842525228,covariates,train,0.9904926534140017
+0.6881013846514903,covariates,train,0.9909248055315472
+0.6885707580380193,covariates,train,0.9909248055315472
+0.6899788781976062,covariates,train,0.9909248055315472
+0.6904482515841351,covariates,train,0.9909248055315472
+0.6909176249706641,covariates,train,0.9909248055315472
+0.6913869983571932,covariates,train,0.9909248055315472
+0.6920910584369866,covariates,train,0.9909248055315472
+0.6923257451302511,covariates,train,0.9909248055315472
+0.6927951185167801,covariates,train,0.9909248055315472
+0.6934991785965736,covariates,train,0.9909248055315472
+0.695611358835954,covariates,train,0.9909248055315472
+0.6963154189157474,covariates,train,0.9909248055315472
+0.6967847923022764,covariates,train,0.9909248055315472
+0.6974888523820699,covariates,train,0.9909248055315472
+0.6984275991551279,covariates,train,0.9909248055315472
+0.6988969725416568,covariates,train,0.9909248055315472
+0.6996010326214503,covariates,train,0.9909248055315472
+0.7000704060079793,covariates,train,0.9909248055315472
+0.7003050927012439,covariates,train,0.9913569576490925
+0.7010091527810374,covariates,train,0.9913569576490925
+0.7014785261675663,covariates,train,0.9913569576490925
+0.7026519596338887,covariates,train,0.9913569576490925
+0.7031213330204178,covariates,train,0.9913569576490925
+0.7038253931002112,covariates,train,0.9913569576490925
+0.7073456934991786,covariates,train,0.9917891097666378
+0.7075803801924431,covariates,train,0.9917891097666378
+0.7089885003520301,covariates,train,0.9917891097666378
+0.7092231870452945,covariates,train,0.9917891097666378
+0.709927247125088,covariates,train,0.9917891097666378
+0.7118047406712039,covariates,train,0.9917891097666378
+0.7120394273644685,covariates,train,0.9917891097666378
+0.7129781741375264,covariates,train,0.9917891097666378
+0.7132128608307909,covariates,train,0.9917891097666378
+0.7139169209105843,covariates,train,0.9917891097666378
+0.7143862942971133,covariates,train,0.9917891097666378
+0.7146209809903779,covariates,train,0.9917891097666378
+0.7155597277634358,covariates,train,0.9917891097666378
+0.7176719080028162,covariates,train,0.9922212618841832
+0.7181412813893452,covariates,train,0.9922212618841832
+0.7183759680826097,covariates,train,0.9922212618841832
+0.7188453414691387,covariates,train,0.9922212618841832
+0.7200187749354612,covariates,train,0.9922212618841832
+0.7209575217085191,covariates,train,0.9922212618841832
+0.7211922084017837,covariates,train,0.9922212618841832
+0.7218962684815771,covariates,train,0.9922212618841832
+0.7221309551748416,covariates,train,0.9926534140017286
+0.7226003285613706,covariates,train,0.9926534140017286
+0.7233043886411641,covariates,train,0.9926534140017286
+0.7237737620276931,covariates,train,0.9926534140017286
+0.7240084487209575,covariates,train,0.9926534140017286
+0.7261206289603379,covariates,train,0.9943820224719101
+0.7268246890401314,covariates,train,0.9943820224719101
+0.7272940624266604,covariates,train,0.9943820224719101
+0.7277634358131894,covariates,train,0.9943820224719101
+0.7287021825862473,covariates,train,0.9943820224719101
+0.7301103027458343,covariates,train,0.9943820224719101
+0.7310490495188923,covariates,train,0.9943820224719101
+0.7336306031448017,covariates,train,0.9943820224719101
+0.7345693499178596,covariates,train,0.9943820224719101
+0.7352734099976531,covariates,train,0.9943820224719101
+0.7355080966909177,covariates,train,0.9948141745894555
+0.7359774700774466,covariates,train,0.9948141745894555
+0.7371509035437691,covariates,train,0.9948141745894555
+0.7376202769302981,covariates,train,0.9948141745894555
+0.7378549636235625,covariates,train,0.9948141745894555
+0.7397324571696785,covariates,train,0.9948141745894555
+0.7399671438629429,covariates,train,0.9948141745894555
+0.7404365172494719,covariates,train,0.9948141745894555
+0.74137526402253,covariates,train,0.9948141745894555
+0.7434874442619104,covariates,train,0.9948141745894555
+0.7439568176484394,covariates,train,0.9948141745894555
+0.7455996245012908,covariates,train,0.9948141745894555
+0.7472424313541423,covariates,train,0.9956784788245462
+0.7477118047406712,covariates,train,0.9956784788245462
+0.7484158648204646,covariates,train,0.9956784788245462
+0.7486505515137292,covariates,train,0.9956784788245462
+0.7493546115935227,covariates,train,0.9956784788245462
+0.7502933583665806,covariates,train,0.9956784788245462
+0.7514667918329031,covariates,train,0.9956784788245462
+0.752405538605961,covariates,train,0.9956784788245462
+0.7526402252992256,covariates,train,0.9956784788245462
+0.753813658765548,covariates,train,0.9956784788245462
+0.754752405538606,covariates,train,0.9956784788245462
+0.7549870922318704,covariates,train,0.9956784788245462
+0.7568645857779864,covariates,train,0.9956784788245462
+0.7573339591645154,covariates,train,0.9956784788245462
+0.7575686458577798,covariates,train,0.9956784788245462
+0.7582727059375733,covariates,train,0.9956784788245462
+0.7587420793241023,covariates,train,0.9956784788245462
+0.7592114527106313,covariates,train,0.9956784788245462
+0.7599155127904248,covariates,train,0.9956784788245462
+0.7601501994836892,covariates,train,0.9956784788245462
+0.7615583196432762,covariates,train,0.9956784788245462
+0.7617930063365407,covariates,train,0.9956784788245462
+0.7624970664163342,covariates,train,0.9956784788245462
+0.7646092466557146,covariates,train,0.9956784788245462
+0.7650786200422436,covariates,train,0.9956784788245462
+0.7653133067355081,covariates,train,0.9956784788245462
+0.7664867402018306,covariates,train,0.9956784788245462
+0.766721426895095,covariates,train,0.9956784788245462
+0.7678948603614175,covariates,train,0.9956784788245462
+0.7704764139873269,covariates,train,0.9961106309420916
+0.7707111006805915,covariates,train,0.9961106309420916
+0.7711804740671204,covariates,train,0.996542783059637
+0.7721192208401784,covariates,train,0.996542783059637
+0.7725885942267073,covariates,train,0.996542783059637
+0.7739967143862942,covariates,train,0.996542783059637
+0.7749354611593523,covariates,train,0.996542783059637
+0.7756395212391457,covariates,train,0.996542783059637
+0.7761088946256747,covariates,train,0.996542783059637
+0.7775170147852617,covariates,train,0.996542783059637
+0.7786904482515842,covariates,train,0.996542783059637
+0.7789251349448486,covariates,train,0.9969749351771824
+0.7796291950246421,covariates,train,0.9969749351771824
+0.7805679417977001,covariates,train,0.9969749351771824
+0.7808026284909646,covariates,train,0.9969749351771824
+0.7826801220370805,covariates,train,0.9969749351771824
+0.783384182116874,covariates,train,0.9969749351771824
+0.7852616756629899,covariates,train,0.9969749351771824
+0.7859657357427834,covariates,train,0.9969749351771824
+0.7869044825158413,covariates,train,0.9969749351771824
+0.7883126026754284,covariates,train,0.9969749351771824
+0.7887819760619573,covariates,train,0.9969749351771824
+0.7894860361417507,covariates,train,0.9969749351771824
+0.7897207228350153,covariates,train,0.9969749351771824
+0.7901900962215442,covariates,train,0.9969749351771824
+0.7904247829148088,covariates,train,0.9969749351771824
+0.7908941563013377,covariates,train,0.9969749351771824
+0.7915982163811311,covariates,train,0.9969749351771824
+0.7920675897676601,covariates,train,0.9974070872947277
+0.7923022764609247,covariates,train,0.9974070872947277
+0.7927716498474536,covariates,train,0.9974070872947277
+0.7944144567003051,covariates,train,0.9974070872947277
+0.795822576859892,covariates,train,0.9974070872947277
+0.7969960103262145,covariates,train,0.9974070872947277
+0.7974653837127434,covariates,train,0.9974070872947277
+0.797700070406008,covariates,train,0.9974070872947277
+0.798169443792537,covariates,train,0.9974070872947277
+0.7995775639521239,covariates,train,0.9974070872947277
+0.8016897441915043,covariates,train,0.9974070872947277
+0.8028631776578268,covariates,train,0.9974070872947277
+0.8038019244308847,covariates,train,0.9978392394122731
+0.8040366111241493,covariates,train,0.9978392394122731
+0.8054447312837362,covariates,train,0.9978392394122731
+0.8059141046702651,covariates,train,0.9978392394122731
+0.8077915982163811,covariates,train,0.9978392394122731
+0.8089650316827036,covariates,train,0.9978392394122731
+0.8103731518422905,covariates,train,0.9978392394122731
+0.8122506453884065,covariates,train,0.9978392394122731
+0.8129547054681999,covariates,train,0.9978392394122731
+0.813893452241258,covariates,train,0.9978392394122731
+0.8155362590941093,covariates,train,0.9982713915298185
+0.8157709457873739,covariates,train,0.9982713915298185
+0.8162403191739028,covariates,train,0.9982713915298185
+0.8185871861065478,covariates,train,0.9982713915298185
+0.8209340530391926,covariates,train,0.9987035436473639
+0.8211687397324572,covariates,train,0.9987035436473639
+0.8221074865055151,covariates,train,0.9991356957649092
+0.8230462332785731,covariates,train,0.9991356957649092
+0.8237502933583666,covariates,train,0.9991356957649092
+0.8246890401314245,covariates,train,0.9991356957649092
+0.8251584135179535,covariates,train,0.9991356957649092
+0.826331846984276,covariates,train,0.9991356957649092
+0.8284440272236564,covariates,train,0.9991356957649092
+0.8286787139169209,covariates,train,0.9991356957649092
+0.8291480873034499,covariates,train,0.9991356957649092
+0.8305562074630368,covariates,train,0.9991356957649092
+0.8312602675428303,covariates,train,0.9991356957649092
+0.8314949542360948,covariates,train,0.9991356957649092
+0.8326683877024172,covariates,train,0.9991356957649092
+0.8357193147148557,covariates,train,0.9991356957649092
+0.8371274348744426,covariates,train,0.9991356957649092
+0.8375968082609716,covariates,train,0.9991356957649092
+0.8394743018070875,covariates,train,0.9991356957649092
+0.840178361886881,covariates,train,0.9991356957649092
+0.84064773527341,covariates,train,0.9991356957649092
+0.8434639755925839,covariates,train,0.9991356957649092
+0.8436986622858484,covariates,train,0.9991356957649092
+0.8446374090589064,covariates,train,0.9991356957649092
+0.8451067824454354,covariates,train,0.9991356957649092
+0.8467495892982868,covariates,train,0.9991356957649092
+0.8469842759915512,covariates,train,0.9991356957649092
+0.8490964562309317,covariates,train,0.9991356957649092
+0.854494250176015,covariates,train,0.9991356957649092
+0.8551983102558085,covariates,train,0.9991356957649092
+0.8561370570288664,covariates,train,0.9991356957649092
+0.8575451771884535,covariates,train,0.9991356957649092
+0.8577798638817179,covariates,train,0.9991356957649092
+0.8587186106547758,covariates,train,0.9991356957649092
+0.8594226707345693,covariates,train,0.9991356957649092
+0.8645857779863881,covariates,train,0.9991356957649092
+0.8657592114527106,covariates,train,0.9991356957649092
+0.8671673316122975,covariates,train,0.9991356957649092
+0.8676367049988266,covariates,train,0.9991356957649092
+0.8699835719314715,covariates,train,0.9991356957649092
+0.8753813658765548,covariates,train,0.9991356957649092
+0.8758507392630838,covariates,train,0.9991356957649092
+0.8765547993428773,covariates,train,0.9991356957649092
+0.8767894860361417,covariates,train,0.9991356957649092
+0.8793710396620512,covariates,train,0.9991356957649092
+0.8800750997418446,covariates,train,0.9991356957649092
+0.884064773527341,covariates,train,0.9991356957649092
+0.8859422670734569,covariates,train,0.9991356957649092
+0.8864116404599859,covariates,train,0.9991356957649092
+0.8880544473128373,covariates,train,0.9991356957649092
+0.8889931940858953,covariates,train,0.9991356957649092
+0.8899319408589533,covariates,train,0.9991356957649092
+0.8901666275522178,covariates,train,0.9991356957649092
+0.8967378549636236,covariates,train,0.9991356957649092
+0.8972072283501525,covariates,train,0.9991356957649092
+0.9004928420558554,covariates,train,0.9991356957649092
+0.9009622154423844,covariates,train,0.9991356957649092
+0.9023703356019713,covariates,train,0.9991356957649092
+0.9028397089885003,covariates,train,0.9991356957649092
+0.9033090823750294,covariates,train,0.9991356957649092
+0.9080028162403192,covariates,train,0.9991356957649092
+0.9094109363999061,covariates,train,0.9991356957649092
+0.9117578033325511,covariates,train,0.9991356957649092
+0.915043417038254,covariates,train,0.9991356957649092
+0.9152781037315184,covariates,train,0.9991356957649092
+0.9223187045294532,covariates,train,0.9991356957649092
+0.9225533912227176,covariates,train,0.9991356957649092
+0.9241961980755691,covariates,train,0.9991356957649092
+0.9263083783149495,covariates,train,0.9991356957649092
+0.9267777517014786,covariates,train,0.9991356957649092
+0.9291246186341234,covariates,train,0.9991356957649092
+0.929359305327388,covariates,train,0.9991356957649092
+0.9352264726590003,covariates,train,0.9995678478824547
+0.9354611593522647,covariates,train,0.9995678478824547
+0.9368692795118517,covariates,train,0.9995678478824547
+0.9371039662051162,covariates,train,0.9995678478824547
+0.9375733395916451,covariates,train,0.9995678478824547
+0.9415630133771415,covariates,train,0.9995678478824547
+0.941797700070406,covariates,train,0.9995678478824547
+0.942267073456935,covariates,train,0.9995678478824547
+0.9504811077211922,covariates,train,0.9995678478824547
+0.9509504811077212,covariates,train,0.9995678478824547
+0.9532973480403661,covariates,train,0.9995678478824547
+0.9535320347336306,covariates,train,0.9995678478824547
+0.9540014081201595,covariates,train,1.0
+0.9554095282797466,covariates,train,1.0
+0.955644214973011,covariates,train,1.0
+0.9610420089180943,covariates,train,1.0
+0.9622154423844168,covariates,train,1.0
+0.9664398028631777,covariates,train,1.0
+0.9671438629429712,covariates,train,1.0
+0.9744191504341704,covariates,train,1.0
+0.9753578972072283,covariates,train,1.0
+0.9760619572870218,covariates,train,1.0
+0.9770007040600798,covariates,train,1.0
+0.9816944379253696,covariates,train,1.0
+0.9821638113118986,covariates,train,1.0
+0.983337244778221,covariates,train,1.0
+0.9835719314714856,covariates,train,1.0
+0.9845106782445435,covariates,train,1.0
+0.9877962919502464,covariates,train,1.0
+0.9885003520300399,covariates,train,1.0
+0.9887350387233044,covariates,train,1.0
+0.9913165923492138,covariates,train,1.0
+0.9924900258155362,covariates,train,1.0
+0.9929593992020652,covariates,train,1.0
+0.9950715794414456,covariates,train,1.0
+0.9955409528279746,covariates,train,1.0
+0.9964796996010327,covariates,train,1.0
+0.9971837596808261,covariates,train,1.0
+0.9974184463740906,covariates,train,1.0
+0.9981225064538841,covariates,train,1.0
+0.9990612532269421,covariates,train,1.0
+0.9997653133067355,covariates,train,1.0
+1.0,covariates,train,1.0
diff --git a/jupyter_data/roc_vega_spec.json b/jupyter_data/roc_vega_spec.json
new file mode 100644
index 0000000..83b4e2c
--- /dev/null
+++ b/jupyter_data/roc_vega_spec.json
@@ -0,0 +1,307 @@
+{
+  "width": 600,
+  "height": 400,
+  "padding": {"top": 10,"left": 70,"bottom": 60,"right": 190},
+  "signals": [
+    {
+      "name": "index_fpr",
+      "init": 0.4,
+      "streams": [{
+        "type": "mousemove",
+        "expr": "clamp(eventX(), 0, eventGroup('root').width)",
+        "scale": {"name": "xscale", "invert": true}
+      }]
+    }
+  ],
+  "data": [
+    {
+      "name": "roc",
+      "url": "jupyter_data/roc_output.csv",
+      "format": {"type": "csv"},
+      "transform": [
+        {
+          "type": "aggregate",
+          "groupby": ["partition", "feature_set", "false_positive_rate"],
+          "summarize": [{
+            "field": "true_positive_rate", "ops": ["min"], "as": ["true_positive_rate"]            
+          }]            
+        },
+        {
+          "type": "formula",
+          "field": "legend",
+          "expr": "datum.partition + ' (' + datum.feature_set + ')'"
+        }
+      ]
+    },
+    {
+      "name": "roc_index_lookup",
+      "source": "roc",
+      "transform": [
+        {
+          "type": "filter",
+          "test": "datum.false_positive_rate >= index_fpr"
+        },        
+        {
+          "type": "aggregate",
+          "groupby": ["legend"],
+          "summarize": [{
+            "field": "false_positive_rate", "ops": ["min"], "as": ["min_false_positive_rate"]      
+          }]            
+        }
+      ]        
+    },
+    {
+      "name": "roc_index",
+      "source": "roc",
+      "transform": [
+        {
+          "type": "lookup",
+          "on": "roc_index_lookup", "onKey": "legend",
+          "keys": ["legend"], "as": ["lookup"], "default": -1
+        },        
+        {
+          "type": "filter",
+          "test": "datum.false_positive_rate == datum.lookup.min_false_positive_rate"
+        },
+        {
+          "type": "aggregate",
+          "groupby": ["legend", "partition", "feature_set"],
+          "summarize": [{
+            "field": "false_positive_rate", "ops": ["min"], "as": ["agg_false_positive_rate"],
+            "field": "true_positive_rate", "ops": ["min"], "as": ["agg_true_positive_rate"]          
+          }] 
+        }
+      ]        
+    },
+    {
+      "name": "dash_data",
+      "values": [{"strokeDash": [0,0]},{"strokeDash": [5,7]}]
+    },
+    {
+      "name": "dash_legend",
+      "values": [{"strokeDash": [0,0]},{"strokeDash": [3,3]}]
+    },
+    {
+      "name": "legend_auc",
+      "url": "jupyter_data/auc.csv",
+      "format": {"type": "csv"},
+      "transform": [
+        {
+          "type": "formula",
+          "field": "legend",
+          "expr": "datum.partition + ' (' + datum.feature_set + ')'"
+        }
+      ]
+    }
+  ],
+  "scales": [
+    {
+      "name": "xscale",
+      "type": "linear",
+      "domain": {"data": "roc","field": "false_positive_rate"},
+      "range": "width",
+      "zero": "true",
+      "round": "true"
+    },
+    {
+      "name": "yscale",
+      "type": "linear",
+      "domain": {"data": "roc","field": "true_positive_rate"},
+      "range": "height",
+      "zero": "true",
+      "round": "true",
+      "nice": "true"
+    },
+    {
+      "name": "colorscale",
+      "type": "ordinal",
+      "domain": {"data": "roc","field": "feature_set"},
+      "range": ["#FF0000","#5254a3", "#fd8d3c"]
+    },
+    {
+      "name": "dashscale",
+      "type": "ordinal",
+      "domain": {"data": "roc","field": "partition"},
+      "range": {"data": "dash_data","field": "strokeDash"}
+    },
+    {
+      "name": "dashlegendscale",
+      "type": "ordinal",
+      "domain": {"data": "roc","field": "partition"},
+      "range": {"data": "dash_legend","field": "strokeDash"}
+    },
+    {
+      "name": "legendrow",
+      "type": "linear",
+      "domain": {"data": "legend_auc", "field": "legend_index"},
+      "rangeMin": 0,
+      "rangeMax": 110
+    }
+  ],
+  "axes": [
+    {
+      "type": "x",
+      "title": "False positive rate",
+      "scale": "xscale",
+      "format": "%"
+    },
+    {
+      "type": "y",
+      "title": "True positive rate",
+      "scale": "yscale",
+      "format": "%"
+    }
+  ],
+  "legends": [
+    {
+      "title": "feature set",
+      "fill": "colorscale",
+      "properties": {
+       "title": {
+         "fontSize": {"value": 16}
+       },
+       "labels": {
+         "fontSize": {"value": 15}
+       },
+        "legend": {"x": {"value": 440},"y": {"value": 250}},
+        "symbols": {
+          "size": {"value": 250},
+          "strokeWidth": {"value": 3},
+          "stroke": {"scale": "colorscale","field": "data"},
+          "shape": {
+              "value": "M-0.5,-0.0L0.5,0"
+          }
+        }
+      }
+    },
+    {
+      "title": "partition",
+      "stroke": "dashlegendscale",
+      "properties": {
+       "title": {
+         "fontSize": {"value": 16}
+       },
+       "labels": {
+         "fontSize": {"value": 15},         
+          "text": {"field": "data"}
+       },
+        "symbols": {
+          "size": {"value": 250},
+          "stroke": {"value": "black"},
+          "strokeWidth": {"value": 3},
+          "strokeDash": {"scale": "dashlegendscale","field": "data"},
+          "shape": {
+              "value": "M-0.5,-0.0L0.5,0"
+          }
+        },
+        "legend": {"x": {"value": 440},"y": {"value": 320}}
+      }
+    }
+  ],
+  "marks": [
+    { 
+      "type":"rule",
+      "properties": {
+        "update": {
+          "x": {"scale": "xscale", "signal": "index_fpr"},
+          "y": {"value": 0},
+          "y2": {"field": {"group": "height"}},
+          "stroke": {"value": "red"}
+        }
+      }
+    },
+    {
+      "type": "group",
+      "from": {
+        "data": "roc",
+        "transform": [{"type": "facet","groupby": "legend"}]
+      },
+      "marks": [
+      {
+        "type": "line",
+        "properties": {
+          "update": {
+            "x": {
+              "scale": "xscale",
+              "field": "false_positive_rate"
+            },
+            "y": {
+              "scale": "yscale",
+              "field": "true_positive_rate"
+            },
+            "stroke": {"scale": "colorscale","field": "feature_set"},
+            "strokeWidth": {"value": 4},
+            "strokeOpacity": {"value": 0.6},
+            "strokeDash": {"scale": "dashscale","field": "partition"}
+          }
+        }
+      }]
+    },  
+    {
+      "type": "group",
+      "from": {
+        "data": "roc_index",
+        "transform": [
+          {
+            "type": "lookup",
+            "on": "legend_auc", "onKey": "legend",
+            "keys": ["legend"], "as": ["lookup"], "default": -1
+          },
+          {"type": "facet", "groupby": "legend"}
+        ]
+      },
+      "properties": {
+        "update": {        
+          "y": {"value": 100},
+          "x": {"scale": "xscale", "signal": "index_fpr", "offset": 10},
+          "width": {"value": 200},
+          "height": {"value": 140},
+          "strokeWidth": {"value": 0.5},
+          "stroke": {"value": "black"}
+        }
+      },
+      "marks": [
+      {
+        "type": "group",
+        "properties": {
+          "update": {
+            "x": {"value": 4},
+            "y": {"scale": "legendrow","field": "lookup.legend_index", "offset": 5}
+            }
+          },
+          "marks": [
+            {
+              "type": "text",
+              "properties": {
+                "update": {
+                  "x": {"value": 0},
+                  "y": {"value": 5},
+                  "fontSize": {"value": 11},
+                  "fill": {"value": "black"},
+                  "fontWeight": {"value": "bold"},
+                  "text": {
+                    "template": "{{parent.legend}}"
+                  }
+                }
+              }
+            },
+            {
+              "type": "text",
+              "properties": {
+                "update": {
+                  "x": {"value": 0},
+                  "y": {"value": 15},
+                  "fontSize": {"value": 11},
+                  "fill": {"value": "black"},
+                  "text": {
+                    "template": "TPR: {{parent.agg_true_positive_rate|number: '.3p'}}, FPR: {{index_fpr|number: '.3p'}}, AUC {{parent.lookup.auc|number: '.3p'}}"
+                  }
+                }
+              }
+            }
+          ]
+        }    
+      ]
+    }
+  ]
+}
\ No newline at end of file