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 +1,224 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "toc": true
+   },
+   "source": [
+    "# WS 08 Regression mit Standardisieren und Logarithmieren"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "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' ## for import of user defined module\n",
+    "#datapath = '../3_data'\n",
+    "codepath = '.././2_code' ## for import of user defined module\n",
+    "datapath = '../../3_data'\n",
+    "\n",
+    "from sys import path; path.insert(1, codepath)\n",
+    "from os import chdir; chdir(datapath)\n",
+    "\n",
+    "from bfh_cas_pml import prep_data\n",
+    "X_train, X_test, y_train, y_test = prep_data('melb_data_prep.csv', target='Price', seed=1234)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "-105513873.23403685\n",
+      "[ 245383.60581414 -141356.39759052  -40383.66643969  161336.03949841\n",
+      "   40391.14829949   83303.27089591]\n",
+      "[1331246.16325189 2557493.2373921   871684.82823291 1495633.275723\n",
+      " 1549557.61151302  634348.67092323]\n",
+      "0.5601419746121152\n"
+     ]
+    }
+   ],
+   "source": [
+    "## baseline\n",
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import r2_score\n",
+    "model = LinearRegression()\n",
+    "model.fit(X_train, y_train)\n",
+    "y_pred = model.predict(X_test)\n",
+    "\n",
+    "print(model.intercept_)\n",
+    "print(model.coef_[:6])\n",
+    "print(y_pred[:6])\n",
+    "print(r2_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1055902.69523731\n",
+      "[ 235020.76662584  -96493.73493151 -243470.62893089  106305.85273776\n",
+      "   35544.05464669   71047.51543032]\n",
+      "[1331246.16325187 2557493.23739203  871684.82823297 1495633.27572294\n",
+      " 1549557.611513    634348.67092323]\n",
+      "0.5601419746121148\n"
+     ]
+    }
+   ],
+   "source": [
+    "## scaled features\n",
+    "from sklearn.preprocessing import StandardScaler\n",
+    "scaler = StandardScaler()\n",
+    "scaler.fit(X_train)\n",
+    "X_train_sc = scaler.transform(X_train)\n",
+    "X_test_sc = scaler.transform(X_test)\n",
+    "\n",
+    "model = LinearRegression()\n",
+    "model.fit(X_train_sc, y_train)\n",
+    "y_pred = model.predict(X_test_sc)\n",
+    "\n",
+    "print(model.intercept_)\n",
+    "print(model.coef_[:6])\n",
+    "print(y_pred[:6])\n",
+    "print(r2_score(y_test, y_pred))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Fazit**\n",
+    "* Auswirkung von Skalieren der Features\n",
+    "  * Koeffizienten und Intercept: Einfluss\n",
+    "  * Prediction: kein Einfluss\n",
+    "  * Score: natürlich auch kein Einfluss, wird ja aus Prediction berechnet"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.5519266421486302\n"
+     ]
+    }
+   ],
+   "source": [
+    "## log target\n",
+    "y_train_log = np.log10(y_train)\n",
+    "y_test_log = np.log10(y_test)\n",
+    "\n",
+    "model = LinearRegression()\n",
+    "model.fit(X_train, y_train_log)\n",
+    "y_pred = model.predict(X_test)\n",
+    "print(r2_score(10**y_test_log, 10**y_pred))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Fazit**\n",
+    "* wird sogar etwas schlechter\n",
+    "* kombination mit skalierten Features erübrigt sich hier, da skalieren ja offenbar keinen Einfluss auf score hat"
+   ]
+  }
+ ],
+ "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 11 Regression - mit FE - 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": true
+  },
+  "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
+}