Added draft of Jupyter Notebook outlining basic functionality of the new stats module

Author: ymahlich

notebooks/dataset_statistics.ipynb

@@ -0,0 +1,122 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# iPython magic to autoreload modules everytime code is executed to propagate changes to the code\n",
+    "%load_ext autoreload\n",
+    "%autoreload 2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import coderdata as cd\n",
+    "from coderdata.utils.stats import summarize_response_metric\n",
+    "from coderdata.utils.stats import plot_response_metric\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import math"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset_prefix = 'beataml'"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cd.download_data_by_prefix(dataset_prefix)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "data = cd.DatasetLoader(dataset_prefix)\n",
+    "summary_stats = summarize_response_metric(data=data)\n",
+    "summary_stats"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "metrics = summary_stats.index.values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "ncol = 3\n",
+    "nrow = math.ceil(len(metrics)/ncol)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "fig, axs = plt.subplots(nrows=nrow, ncols=ncol, figsize=(ncol*3, nrow*3))\n",
+    "\n",
+    "k = 0\n",
+    "for i in range(0, nrow):\n",
+    "    for j in range(0, ncol):\n",
+    "        if k < len(metrics):\n",
+    "            plot_response_metric(data=data, metric=metrics[k], bins=10, ax=axs[i, j])\n",
+    "        else:\n",
+    "            axs[i, j].axis('off')\n",
+    "        k += 1\n",
+    "\n",
+    "fig.set_layout_engine('tight')\n",
+    "fig.suptitle(f'Distribution of drug response values in \"{dataset_prefix}\"')\n",
+    "\n",
+    "# uncomment next line to save plot\n",
+    "# fig.savefig(f'{dataset_prefix}.png')"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "coderdata",
+   "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": "3.12.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}