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 +1,223 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "toc": true
+   },
+   "source": [
+    "<h1>WS 10 Klassifikation - Modellvergleiche<span class=\"tocSkip\"></span></h1>\n",
+    "<div class=\"toc\"><ul class=\"toc-item\"></ul></div>"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "* vergleichen Sie alle bis jetzt vorgestellten Klassifikatoren miteinander in Bezug auf\n",
+    "  * Performance\n",
+    "  * Rechenzeiten, differenziert nach .fit() und .predict()  \n",
+    "  und visualisieren Sie die Ergebnisse\n",
+    "* Tipp: modifizieren / ergänzen Sie dazu den abgegebenen Code von Kapitel 2.2.6 Modellvergleiche\n",
+    "\n",
+    "* optional: fügen Sie andere, im Kurs nicht behandelte Klassifikatoren dazu, welche Sie in der Dokumentation von scikit-learn finden\n",
+    "* optional: falls Sie im Rahmen von Feaure Engineering alternatives Preprocessing erarbeitet haben, können Sie die Auswirkungen desselben jetzt auch noch einbeziehen\n",
+    "* optional: wie wirkt sich Skalierung (z.B. mit StandardScaler) auf die Performance von MLPClassifier aus?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "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",
+    "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('bank_data_prep.csv', target='y', seed=1234)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Funktionen (Klassen) importieren\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "## tbd ergänzen\n",
+    "\n",
+    "\n",
+    "\n",
+    "from sklearn.metrics import accuracy_score\n",
+    "import time  ## für Zeitmessung"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## Modelle definieren und in Liste hinterlegen\n",
+    "models = [\n",
+    "    KNeighborsClassifier(),\n",
+    "    DecisionTreeClassifier(min_impurity_decrease=0.002),\n",
+    "    RandomForestClassifier(n_estimators=100)\n",
+    "    ## tbd ergänzen\n",
+    "    \n",
+    "    \n",
+    "    \n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "KNeighborsClassifier()\n",
+      "DecisionTreeClassifier(min_impurity_decrease=0.002)\n",
+      "RandomForestClassifier()\n"
+     ]
+    }
+   ],
+   "source": [
+    "## zum Sammeln der Resultate\n",
+    "scores = []\n",
+    "times_fit = []\n",
+    "times_pred = []\n",
+    "model_names = []\n",
+    "\n",
+    "#print('Classifier                          Score      Time fit    Time pred')\n",
+    "#print('====================================================================')\n",
+    "\n",
+    "## Loop\n",
+    "for model in models:\n",
+    "    print(model)\n",
+    "    ## tbd\n",
+    "    \n",
+    "    ##   start timer1 - fit - stop timer1\n",
+    "    \n",
+    "    \n",
+    "    ##   start timer2 - predict - stop timer2\n",
+    "    \n",
+    "    \n",
+    "    ##   berechne Score & pick Modellname\n",
+    "    \n",
+    "    \n",
+    "    ##   Ergebnisse an vorbereitete Listen anhängen\n",
+    "    \n",
+    "    \n",
+    "    ##   Iterationsergebnisse in Konsole ausgeben (optional)\n",
+    "\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "## visualisieren\n",
+    "## tbd ergänzen\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "**Fazit:**  \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": "",
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "WS 10 Klassifikation - Modellvergleiche",
+   "title_sidebar": "Contents",
+   "toc_cell": true,
+   "toc_position": {
+    "height": "calc(100% - 180px)",
+    "left": "10px",
+    "top": "150px",
+    "width": "205.2px"
+   },
+   "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()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}