cas-pml/SL/aufgaben/template/4_WS/Loesungen/WS 14 Loesung.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "toc": true
   },
   "source": [
    "# WS 14 Random Search CV"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "* untersuchen Sie Kombinationen von Parameterwerten bei RandomForestClassifier\n",
    "* Vorschlag:\n",
    "  * n_estimators in [50, 100, 150, 200]\n",
    "  * max_features in [3, 5, 7, 9]\n",
    "  * criterion in ['gini', 'entropy']\n",
    "  * min_samples_leaf in [1, 2, 3, 4]\n",
    "* wenden Sie 5-fach Kreuzvalidierung an\n",
    "* setzen Sie die Anzahl der zu untersuchenden Kombinationen auf 12\n",
    "* arbeiten Sie ohne setzen von random_state, damit anschliessend die Ergebnisse verglichen werden können"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "## import libraries\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "## load data\n",
    "datapath = '../../3_data'\n",
    "from os import chdir; chdir(datapath)\n",
    "bank_df = pd.read_csv('bank_data_prep.csv')\n",
    "\n",
    "## features - target - split\n",
    "X = bank_df.drop('y', axis=1)\n",
    "y = bank_df['y']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "best_params_ : {'n_estimators': 50, 'min_samples_leaf': 4, 'max_features': 9, 'criterion': 'entropy'}\n",
      "best_score_  : 0.8884381338742393\n",
      "CPU times: total: 3.09 s\n",
      "Wall time: 43.6 s\n"
     ]
    }
   ],
   "source": [
    "%%time\n",
    "## import classes from sklearn\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.model_selection import RandomizedSearchCV\n",
    "\n",
    "## define parameter grid\n",
    "parameter_grid = {'n_estimators': [50, 100, 150, 200],\n",
    "                  'max_features': [3, 5, 7, 9],\n",
    "                  'criterion': ['gini', 'entropy'],\n",
    "                  'min_samples_leaf': [1, 2, 3, 4]}\n",
    "\n",
    "## define RandomizedSearchCV\n",
    "rscv = RandomizedSearchCV(\n",
    "    estimator=RandomForestClassifier(random_state=1234), \n",
    "    param_distributions=parameter_grid, \n",
    "    cv=5,\n",
    "    n_iter=12,\n",
    "    random_state=1234,\n",
    "    n_jobs=-1)\n",
    "\n",
    "## run RandomizedSearchCV\n",
    "rscv.fit(X, y)\n",
    "\n",
    "## evaluate RandomizedSearchCV\n",
    "print('best_params_ :', rscv.best_params_)\n",
    "print('best_score_  :', rscv.best_score_)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#rscv.best_estimator_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(9860, 29)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Fazit:**\n",
    "* n_estimators: [50, 100, 150, 200] -> 50\n",
    "  * hier müsste der Suchbereich nach unten erweiter werden\n",
    "* max_features: [3, 5, 7, 9] -> 9\n",
    "  * hier müsste der Suchbereich nach oben erweiter werden\n",
    "* criterion: ['gini', 'entropy']\n",
    "  * Suchbereich ok\n",
    "* min_samples_leaf: [1, 2, 3, 4] -> 4\n",
    "  * hier müsste der Suchbereich nach oben erweiter werden"
   ]
  }
 ],
 "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 17 Validierung - Random Search CV",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "195.867px"
   },
   "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": "306.85px",
    "left": "862px",
    "right": "20px",
    "top": "137px",
    "width": "350px"
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}