cas-pml/SL/aufgaben/template/4_WS/WS 10 Vorlage.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "toc": true
   },
   "source": [
    "# WS 10 Performancevergleiche Regression"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* Vergleichen Sie alle Regressoren (ausser `SVR` und `MLPRegressor`) mit folgenden Modifikationen\n",
    "  * die Vergleiche werden ohne und mit Standardisierung der Features durchgeführt\n",
    "  * die Resultate (r2_score) werden in Form einer Heatmap zusammengestellt\n",
    "* informieren Sie sich zum Vorgehen am Code in 3.4 Regression - Modellvergleiche.ipynb\n",
    "* Präsentation der Ergebnisse als \n",
    "  * seaborn heatmap\n",
    "  * alternative Visualisierung: Grouped barplots"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {
    "tags": []
   },
   "source": [
    "## for scikit-learn 1.4.2, to silence warnings regarding physical cores\n",
    "import os\n",
    "os.environ['LOKY_MAX_CPU_COUNT'] = '4' ## depending on the hardware used"
   ]
  },
  {
   "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'\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('melb_data_prep.csv', target='Price', seed=1234)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-04-08T10:33:02.116059Z",
     "start_time": "2020-04-08T10:33:02.087399Z"
    }
   },
   "outputs": [],
   "source": [
    "## standardize features (lead: train)\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)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-04-08T10:33:02.294366Z",
     "start_time": "2020-04-08T10:33:02.120049Z"
    }
   },
   "outputs": [],
   "source": [
    "## import trainer classes\n",
    "## tbd\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-04-08T10:33:02.326199Z",
     "start_time": "2020-04-08T10:33:02.299732Z"
    }
   },
   "outputs": [],
   "source": [
    "## define models\n",
    "## tbd\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-04-08T10:33:15.141363Z",
     "start_time": "2020-04-08T10:33:02.341448Z"
    }
   },
   "outputs": [],
   "source": [
    "## compare models\n",
    "## tbd: prepare empty lists for results\n",
    "\n",
    "\n",
    "\n",
    "# for model in models:\n",
    "\n",
    "    ## not scaled\n",
    "    ## tbd\n",
    "    \n",
    "    \n",
    "    \n",
    "    ## scaled\n",
    "    ## tbd\n",
    "    \n",
    "\n",
    "    "
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-04-08T10:33:15.742776Z",
     "start_time": "2020-04-08T10:33:15.150619Z"
    }
   },
   "source": [
    "## visualize results\n",
    "\"\"\"\n",
    "scores = pd.DataFrame(\n",
    "    {'r2_no': r2_nos, \n",
    "     'r2_yes': r2_yess\n",
    "    }, index=regressors)\n",
    "\n",
    "sns.heatmap(scores);\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Fazit:**  \n",
    "* tbd"
   ]
  }
 ],
 "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",
   "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
}