Update python-linear-model-overfitting.ipynb

CausalAIBook · Jun 28, 2024 · a4d5d6c · a4d5d6c
1 parent e60fcef
commit a4d5d6c
Showing 1 changed file with 101 additions and 1 deletion.
diff --git a/PM1/python-linear-model-overfitting.ipynb b/PM1/python-linear-model-overfitting.ipynb
@@ -1 +1,101 @@
-{"cells":[{"cell_type":"markdown","metadata":{"_execution_state":"idle","_uuid":"051d70d956493feee0c6d64651c6a088724dca2a","id":"GC3FBi5L7OLq","papermill":{"duration":0.005457,"end_time":"2021-02-10T13:42:51.332609","exception":false,"start_time":"2021-02-10T13:42:51.327152","status":"completed"},"tags":[]},"source":["# Simple Exercise on Overfitting\n"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"YTaOmenI7TfT"},"outputs":[],"source":["import numpy as np\n","import statsmodels.api as sm\n","\n","def regression_stats(n,p):\n","  np.random.seed(123)\n","  X = np.random.normal(size=(n,p))\n","  y = np.random.normal(size=(n,1))\n","  print(f\"p/n is: {p/n if n != 0 else np.inf}\")\n","  print(f\"R^2 is {sm.OLS(y, X).fit().rsquared}\")\n","  print(f\"Adjusted R^2 is {sm.OLS(y, X).fit().rsquared_adj}\")"]},{"cell_type":"code","execution_count":null,"metadata":{"id":"C57WYtYM7OL0","papermill":{"duration":0.998738,"end_time":"2021-02-10T13:42:52.344388","exception":false,"start_time":"2021-02-10T13:42:51.345650","status":"completed"},"tags":[]},"outputs":[],"source":["regression_stats(1000, 1000)\n","regression_stats(1000, 500)\n","regression_stats(1000, 50)"]}],"metadata":{"colab":{"provenance":[]},"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":"3.8.7"},"papermill":{"default_parameters":{},"duration":4.940504,"end_time":"2021-02-10T13:42:53.102123","environment_variables":{},"exception":null,"input_path":"__notebook__.ipynb","output_path":"__notebook__.ipynb","parameters":{},"start_time":"2021-02-10T13:42:48.161619","version":"2.2.2"}},"nbformat":4,"nbformat_minor":0}
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "_execution_state": "idle",
+    "_uuid": "051d70d956493feee0c6d64651c6a088724dca2a",
+    "id": "GC3FBi5L7OLq",
+    "papermill": {
+     "duration": 0.005457,
+     "end_time": "2021-02-10T13:42:51.332609",
+     "exception": false,
+     "start_time": "2021-02-10T13:42:51.327152",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "source": [
+    "# Simple Exercise on Overfitting\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "YTaOmenI7TfT"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import statsmodels.api as sm\n",
+    "\n",
+    "\n",
+    "def regression_stats(n, p):\n",
+    "    np.random.seed(123)\n",
+    "    X = np.random.normal(size=(n, p))\n",
+    "    y = np.random.normal(size=(n, 1))\n",
+    "    print(f\"p/n is: {p/n if n != 0 else np.inf}\")\n",
+    "    print(f\"R^2 is {sm.OLS(y, X).fit().rsquared}\")\n",
+    "    print(f\"Adjusted R^2 is {sm.OLS(y, X).fit().rsquared_adj}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "C57WYtYM7OL0",
+    "papermill": {
+     "duration": 0.998738,
+     "end_time": "2021-02-10T13:42:52.344388",
+     "exception": false,
+     "start_time": "2021-02-10T13:42:51.345650",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "regression_stats(1000, 1000)\n",
+    "regression_stats(1000, 500)\n",
+    "regression_stats(1000, 50)"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.5"
+  },
+  "papermill": {
+   "default_parameters": {},
+   "duration": 4.940504,
+   "end_time": "2021-02-10T13:42:53.102123",
+   "environment_variables": {},
+   "exception": null,
+   "input_path": "__notebook__.ipynb",
+   "output_path": "__notebook__.ipynb",
+   "parameters": {},
+   "start_time": "2021-02-10T13:42:48.161619",
+   "version": "2.2.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}