refactor: move things around

2026-05-21 14:16:30 +02:00
parent 2fce3281a3
commit 41e15ed275
124 changed files with 404226 additions and 0 deletions
@@ -0,0 +1,217 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "toc": true
+   },
+   "source": [
+    "# WS 11 permutation_importance"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* ermitteln Sie die Importance der Features der *Rohdaten* von `melb_data.csv` unter Einsatz von `sklearn.inspection.ermutation_importance`\n",
+    "* setzen Sie dazu minimales Feature Engineering wie folgt ein:\n",
+    "  * entfernen fragwürdiger Variablen: 'Unnamed: 0', 'Suburb', 'Address', 'SellerG', 'Postcode', 'Bedroom2', 'Date', 'CouncilArea'\n",
+    "  * One-Hot encoding aller verbleibenden kategorialen Variablen (der Parameter `dummy_na=True` von `pd.get_dummies()` erstellt auch Dummy-Variablen für NAs)\n",
+    "  * einsetzen von geschätzten Werten für NAs in verbleibenden numerischen Variablen mit `sklearn.impute.KNNImputer`\n",
+    "* danach:\n",
+    "  * features - target - split\n",
+    "  * **kein** train - test - split\n",
+    "  * ermitteln der Importance unter Einsatz von \n",
+    "    * `sklearn.inspection.permutation_importance`\n",
+    "    * `sklearn.tree.DecisionTreeRegressor`\n",
+    "  * tabellarische und graphische Darstellung der Ergebnisse"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## prepare env, read and prepare data\n",
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import seaborn as sns; sns.set()\n",
+    "\n",
+    "codepath = '../2_code'\n",
+    "datapath = '../3_data'\n",
+    "from sys import path; path.insert(1, codepath)\n",
+    "from os import chdir; chdir(datapath)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## read data\n",
+    "data = pd.read_csv('melb_data.csv')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## drop columns\n",
+    "vars_to_drop = ['Unnamed: 0', 'Suburb', 'Address', 'SellerG', 'Postcode', 'Bedroom2', 'Date', 'CouncilArea']\n",
+    "data = data.drop(vars_to_drop, axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## one-hot encode (incl. NAs)\n",
+    "data = pd.get_dummies(data, drop_first=False, dummy_na=True)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## KNNImputer for NAs\n",
+    "## tbd\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## features - target - split\n",
+    "## tbd\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## permutation_importance\n",
+    "## tbd\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## collect results in a dataframe, ordered by mean\n",
+    "## tbd\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "## visualize results\n",
+    "## tbd\n",
+    "\n",
+    "\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "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": "3.11.7"
+  },
+  "toc": {
+   "base_numbering": "1",
+   "nav_menu": {},
+   "number_sections": false,
+   "sideBar": true,
+   "skip_h1_title": true,
+   "title_cell": "WS 14 Regression - Modellvergleiche 2 - solution",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "195.933px"
+   },
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "position": {
+    "height": "321.85px",
+    "left": "785px",
+    "right": "20px",
+    "top": "118px",
+    "width": "350px"
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}