Add anaylsis module (#22)

* anaylsis

* finalize notebook, docs

* docs

* gray 2D umap

* docs, umaps

* customized colors

* update docs

3.normalize_data/raw_data_umaps.ipynb

@@ -20,7 +20,7 @@
     "import sys\n",
     "sys.path.append(\"../utils\")\n",
     "from load_utils import compile_mitocheck_batch_data, split_data\n",
-    "from analysis_utils import get_2D_umap_embeddings, show_2D_umap"
+    "from analysis_utils import get_2D_umap_embeddings, show_2D_umap_from_embeddings"
    ]
   },
   {
@@ -539,7 +539,7 @@
     "\n",
     "for metadata_field in metadata_fields:\n",
     "    metadata = metadata_dataframe[metadata_field]\n",
-    "    show_2D_umap(x_data, y_data, metadata, f\"{results_dir}/controls_{metadata_field}.png\")"
+    "    show_2D_umap_from_embeddings(x_data, y_data, metadata, f\"{results_dir}/controls_{metadata_field}.png\")"
    ]
   }
  ],

4.analyze_data/README.md

@@ -0,0 +1,33 @@
+# 4. Analyze Data
+
+In this module, we analyze the normalized training data features from [3.normalize_data](../3.normalize_data/normalized_data/training_data.csv.gz).
+
+### Feature Analysis
+
+We use [UMAP](https://github.com/lmcinnes/umap) for analyis of features.
+UMAP was introduced in [McInnes, L, Healy, J, 2018](https://arxiv.org/abs/1802.03426) as a manifold learning technique for dimension reduction.
+We use UMAP to reduce the feature data from 1280 features to 1, 2, and 3 dimensions.
+We use [Matplotlib](https://matplotlib.org/) to visualize the 1D, 2D, and 3D UMAPS.
+
+For each reduction with UMAP, we create two types of visualizations.
+The first visualization colors all points by their phenotypic class.
+The second visualization colors points for only certain phenotypic classes, with all other phenotypic classes being colored gray.
+
+**Note:** Phenotypic classes colored in second visualization can be changed with the `classes_2 = [
+` variable in [analyze_data.ipynb](analyze_data.ipynb).
+
+## Step 1: Analyze Data
+
+Use the commands below to analyze training data.
+All UMAPs will be saved to [umaps/](umaps/).
+
+```sh
+# Make sure you are located in 4.analyze_data
+cd 4.analyze_data
+
+# Activate mitocheck_data conda environment
+conda activate mitocheck_data
+
+# Analyze data
+bash analyze_data.sh
+```