run grn evaluation is tested

notebooks/plot_scores.ipynb

@@ -0,0 +1,144 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def headmap(scores, name=''):\n",
+    "    import matplotlib.pyplot as plt\n",
+    "    import numpy as np\n",
+    "    import seaborn\n",
+    "    fig, ax = plt.subplots(1, 1, figsize=(4, 4), sharey=True)\n",
+    "    vmin = np.nanmin(scores)\n",
+    "    vmax = np.nanmax(scores)\n",
+    "\n",
+    "    seaborn.heatmap(scores, ax=ax, square=False, cbar=False, annot=True, fmt='.2f', vmin=vmin, vmax=vmax)\n",
+    "    # Remove only the ticks, keep labels\n",
+    "    ax.tick_params(left=False, bottom=False)\n",
+    "    ax.xaxis.set_tick_params(width=0)\n",
+    "    ax.yaxis.set_tick_params(width=0)\n",
+    "    ax.set_title(name, pad=10)\n",
+    "\n",
+    "\n",
+    "    plt.tight_layout()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "                ex(True)_tf(-1)  ex(False)_tf(-1)  ex(True)_tf(140)   \n",
+      "seurat_lognorm         0.278739          0.193066          0.278739  \\\n",
+      "lognorm                0.279906          0.194220          0.279906   \n",
+      "pearson                0.373893          0.301601          0.373893   \n",
+      "scgen_pearson          0.453783          0.377673          0.453783   \n",
+      "seurat_pearson         0.366976          0.290578          0.366976   \n",
+      "scgen_lognorm          0.376297          0.279118          0.376297   \n",
+      "\n",
+      "                ex(False)_tf(140)      Mean  \n",
+      "seurat_lognorm           0.193066  0.235902  \n",
+      "lognorm                  0.194220  0.237063  \n",
+      "pearson                  0.301601  0.337747  \n",
+      "scgen_pearson            0.377673  0.415728  \n",
+      "seurat_pearson           0.290578  0.328777  \n",
+      "scgen_lognorm            0.279118  0.327708  \n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import yaml\n",
+    "\n",
+    "# Load the YAML file\n",
+    "result_file = '../resources/results/0/scores.yaml'\n",
+    "with open(result_file, 'r') as file:\n",
+    "    data = yaml.safe_load(file)\n",
+    "\n",
+    "# Initialize a dictionary to hold DataFrames for each method_id\n",
+    "dfs = {}\n",
+    "\n",
+    "# Process each entry in the YAML file\n",
+    "for entry in data:\n",
+    "    method_id = entry['method_id']\n",
+    "    dataset_id = entry['dataset_id']\n",
+    "    \n",
+    "    # If the method_id is not yet in the dictionary, initialize an empty DataFrame\n",
+    "    if method_id not in dfs:\n",
+    "        dfs[method_id] = pd.DataFrame()\n",
+    "    \n",
+    "    # Create a dictionary with metric_ids as keys and metric_values as values\n",
+    "    metrics_dict = dict(zip(entry['metric_ids'], entry['metric_values']))\n",
+    "    \n",
+    "    # Convert the dictionary to a DataFrame with dataset_id as the index\n",
+    "    df_entry = pd.DataFrame(metrics_dict, index=[dataset_id])\n",
+    "    \n",
+    "    # Append the entry to the corresponding DataFrame\n",
+    "    dfs[method_id] = pd.concat([dfs[method_id], df_entry])\n",
+    "\n",
+    "# Example: Access the DataFrame for 'reg1-scenicplus'\n",
+    "df_scenicplus = dfs.get('reg1-scenicplus')\n",
+    "print(df_scenicplus)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import pandas as pd\n",
+    "# output_dir = '../out'\n",
+    "# grn_models = ['celloracle','scenicplus','figr']\n",
+    "\n",
+    "# col = 'ex(False)_tf(-1)'\n",
+    "# scores = pd.DataFrame()\n",
+    "# for grn in grn_models:\n",
+    "#     df = pd.read_csv(f\"{output_dir}/{grn}.csv\", index_col=0)\n",
+    "#     scores[grn] = df[col]\n",
+    "# headmap(scores, name=col)\n",
+    "\n",
+    "# col = 'ex(True)_tf(-1)'\n",
+    "# scores = pd.DataFrame()\n",
+    "# for grn in grn_models:\n",
+    "#     df = pd.read_csv(f\"{output_dir}/{grn}.csv\", index_col=0)\n",
+    "#     scores[grn] = df[col]\n",
+    "# headmap(scores, name=col)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "py10",
+   "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": "3.10.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

params/params.yaml

@@ -1,9 +1,9 @@
-# param_list:
-#   - id: test_process_perturbation
-#     perturbation_counts: "s3://openproblems-data/resources/grn/datasets_raw/perturbation_counts.h5ad"
+param_list:
+  - id: test_process_perturbation
+    perturbation_counts: "s3://openproblems-data/resources/grn/datasets_raw/perturbation_counts.h5ad"
 
-# output_state: "state.yaml"
-# publish_dir: "s3://openproblems-data/resources/grn/results/process_perturbation/run_5"
+output_state: "state.yaml"
+publish_dir: "s3://openproblems-data/resources/grn/results/process_perturbation/run_5"