{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "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": 2,
   "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",
    "from sklearn.ensemble import AdaBoostClassifier\n",
    "from sklearn.ensemble import GradientBoostingClassifier\n",
    "from sklearn.ensemble import HistGradientBoostingClassifier\n",
    "from catboost import CatBoostClassifier ## optional\n",
    "from lightgbm.sklearn import LGBMClassifier ## optional\n",
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis\n",
    "from sklearn.svm import SVC\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "from sklearn.metrics import accuracy_score\n",
    "import time  ## für Zeitmessung"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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",
    "    AdaBoostClassifier(),\n",
    "    GradientBoostingClassifier(),\n",
    "    HistGradientBoostingClassifier(),\n",
    "    CatBoostClassifier(logging_level='Silent'), ## optional\n",
    "    LGBMClassifier(), ## optional\n",
    "    LinearDiscriminantAnalysis(),\n",
    "    QuadraticDiscriminantAnalysis(),\n",
    "    SVC(kernel='rbf', probability=True, gamma='auto'), ## dauert zu lange\n",
    "    GaussianNB(),\n",
    "    MLPClassifier(),\n",
    "    LogisticRegression(max_iter=1000)\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classifier                          Score      Time fit    Time pred\n",
      "====================================================================\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\werne\\anaconda3\\Lib\\site-packages\\joblib\\externals\\loky\\backend\\context.py:110: UserWarning: Could not find the number of physical cores for the following reason:\n",
      "found 0 physical cores < 1\n",
      "Returning the number of logical cores instead. You can silence this warning by setting LOKY_MAX_CPU_COUNT to the number of cores you want to use.\n",
      "  warnings.warn(\n",
      "  File \"C:\\Users\\werne\\anaconda3\\Lib\\site-packages\\joblib\\externals\\loky\\backend\\context.py\", line 217, in _count_physical_cores\n",
      "    raise ValueError(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "KNeighborsClassifier                0.7493     0.0159      1.1670\n",
      "DecisionTreeClassifier              0.8588     0.0321      0.0000\n",
      "RandomForestClassifier              0.8771     1.6460      0.1163\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\werne\\anaconda3\\Lib\\site-packages\\sklearn\\ensemble\\_weight_boosting.py:519: FutureWarning: The SAMME.R algorithm (the default) is deprecated and will be removed in 1.6. Use the SAMME algorithm to circumvent this warning.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AdaBoostClassifier                  0.8585     1.2637      0.0591\n",
      "GradientBoostingClassifier          0.8768     2.1752      0.0141\n",
      "HistGradientBoostingClassifier      0.8820     1.0203      0.0312\n",
      "CatBoostClassifier                  0.8829    11.0474      0.0157\n",
      "[LightGBM] [Info] Number of positive: 3087, number of negative: 3486\n",
      "[LightGBM] [Info] Auto-choosing row-wise multi-threading, the overhead of testing was 0.001409 seconds.\n",
      "You can set `force_row_wise=true` to remove the overhead.\n",
      "And if memory is not enough, you can set `force_col_wise=true`.\n",
      "[LightGBM] [Info] Total Bins 701\n",
      "[LightGBM] [Info] Number of data points in the train set: 6573, number of used features: 29\n",
      "[LightGBM] [Info] [binary:BoostFromScore]: pavg=0.469649 -> initscore=-0.121555\n",
      "[LightGBM] [Info] Start training from score -0.121555\n",
      "LGBMClassifier                      0.8850     0.4560      0.0156\n",
      "LinearDiscriminantAnalysis          0.8488     0.0790      0.0000\n",
      "QuadraticDiscriminantAnalysis       0.7247     0.0375      0.0095\n",
      "SVC                                 0.8220    32.1415      4.1063\n",
      "GaussianNB                          0.7338     0.0157      0.0156\n",
      "MLPClassifier                       0.6355     1.0404      0.0156\n",
      "LogisticRegression                  0.8448     1.4159      0.0100\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\werne\\anaconda3\\Lib\\site-packages\\sklearn\\linear_model\\_logistic.py:469: ConvergenceWarning: lbfgs failed to converge (status=1):\n",
      "STOP: TOTAL NO. of ITERATIONS REACHED LIMIT.\n",
      "\n",
      "Increase the number of iterations (max_iter) or scale the data as shown in:\n",
      "    https://scikit-learn.org/stable/modules/preprocessing.html\n",
      "Please also refer to the documentation for alternative solver options:\n",
      "    https://scikit-learn.org/stable/modules/linear_model.html#logistic-regression\n",
      "  n_iter_i = _check_optimize_result(\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",
    "    \n",
    "    ## start timer1 - fit - stop timer1\n",
    "    start_time_fit = time.time()\n",
    "    model.fit(X_train, y_train)\n",
    "    time_fit = time.time() - start_time_fit\n",
    "    \n",
    "    ## start timer2 - predict - stop timer2\n",
    "    start_time_pred = time.time()\n",
    "    y_pred = model.predict(X_test)\n",
    "    time_pred = time.time() - start_time_pred\n",
    "    \n",
    "    ## berechne Score & pick Modellname\n",
    "    score = accuracy_score(y_test, y_pred)\n",
    "    model_name = model.__class__.__name__  ## Modellname extrahieren (f. Output)\n",
    "    \n",
    "    ## Ergebnisse an vorbereitete Listen anhängen\n",
    "    scores.append(score)\n",
    "    times_fit.append(time_fit)\n",
    "    times_pred.append(time_pred)\n",
    "    model_names.append(model_name)\n",
    "    \n",
    "    ## Iterationsergebnisse in Konsole ausgeben (optional)\n",
    "    print('%-32s   %7.4f    %7.4f     %7.4f' % (model_name, score, time_fit, time_pred))  ## console output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x400 with 3 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "## vizualisation, ordered by decreasing accuracy\n",
    "\n",
    "results = pd.DataFrame({\n",
    "    'models' : model_names,\n",
    "    'scores' : scores,\n",
    "    'times_fit' : times_fit,\n",
    "    'times_pred' : times_pred}\n",
    ").sort_values(by='scores', ascending=False)\n",
    "#print(results)\n",
    "\n",
    "order = results.sort_values('scores', ascending=False).models\n",
    "\n",
    "sns.set(font_scale=1.5) \n",
    "f, axes = plt.subplots(nrows=1, ncols=3, figsize=(10, 4), sharex=False)\n",
    "\n",
    "ax = sns.barplot(data=results, x=scores, y=model_names, color='lightblue', order=order, ax=axes[0])\n",
    "ax.set_xlabel('accuracy')\n",
    "ax.set(xlim=(0.5, 1))\n",
    "\n",
    "ax = sns.barplot(x=times_fit, y=model_names, color='darksalmon', order=order, ax=axes[1])\n",
    "ax.set_xlabel('time fit [s]')\n",
    "ax.set_yticklabels('')\n",
    "ax.set_ylabel('')\n",
    "\n",
    "ax = sns.barplot(x=times_pred, y=model_names, color='darksalmon', order=order, ax=axes[2])\n",
    "ax.set_xlabel('times pred [s]')\n",
    "ax.set_yticklabels('')\n",
    "ax.set_ylabel('');"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "best_model     : LGBMClassifier\n",
      "best_score     : 0.8850015211439002\n",
      "best_pred_time : 0.015624046325683594\n",
      "best_fit_time  : 0.45603370666503906\n"
     ]
    }
   ],
   "source": [
    "## Zusammenfassung des besten Modells\n",
    "print('best_model     :', model_names[scores.index(max(scores))])\n",
    "print('best_score     :', max(scores))\n",
    "print('best_pred_time :', times_pred[scores.index(max(scores))])\n",
    "print('best_fit_time  :', times_fit[scores.index(max(scores))])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                           models    scores\n",
      "7                  LGBMClassifier  0.885002\n",
      "6              CatBoostClassifier  0.882872\n",
      "5  HistGradientBoostingClassifier  0.881959\n",
      "2          RandomForestClassifier  0.877092\n",
      "4      GradientBoostingClassifier  0.876787\n"
     ]
    }
   ],
   "source": [
    "## print top 5 models\n",
    "print(pd.DataFrame({\n",
    "    'models': model_names,\n",
    "    'scores': scores\n",
    "}).sort_values(by='scores', ascending=False).head(5))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Fazit:**  \n",
    "(für diese Datenlage!)\n",
    "* Top 5 accuracy_score: \n",
    "  * LGBMClassifier\n",
    "  * CatBoostClassifier\n",
    "  * HistGradientBoostingClassifier\n",
    "  * RandomForestClassifier\n",
    "  * GradientBoostingClassifier\n",
    "  \n",
    "* Long runners:\n",
    "  * CatBoostClassifier\n",
    "  * SVC\n",
    "  \n",
    "* für weitere Untersuchungen, z.B. verfeinertes Parameter Tuning könnten aus obiger Zusammenstellung 3 bis 5 Methoden ausgewählt werden\n",
    "* ein weiteres Kriterium, welches aber erst im Rahmen von Validierung (Kap. 4) in Betracht zu ziehen wäre ist die Abhängigkeit der Performance von random_state, die **Stabilität** (mehr dazu aber zu gegebener Zeit)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**optional: wie wirkt sich Skalierung (z.B. mit StandardScaler) auf die Performance von MLPClassifier aus?**"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.6975965926376635\n",
      "0.8256769090355948\n",
      "804\n"
     ]
    }
   ],
   "source": [
    "## scale features with StandardScaler\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler().fit(X_train)\n",
    "X_train_scaled = scaler.transform(X_train)\n",
    "X_test_scaled = scaler.transform(X_test)\n",
    "\n",
    "## MLPClassifier score without scaling\n",
    "from sklearn.neural_network import MLPClassifier\n",
    "model = MLPClassifier(random_state = 1234)\n",
    "model.fit(X_train, y_train) \n",
    "print(model.score(X_test, y_test))\n",
    "\n",
    "## MLPClassifier score with scaling\n",
    "model = MLPClassifier(max_iter=1000, random_state = 1234)\n",
    "model.fit(X_train_scaled, y_train) \n",
    "print(model.score(X_test_scaled, y_test))\n",
    "\n",
    "## show number of iterations\n",
    "print(model.n_iter_)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Fazit:**\n",
    "* wird tatsächlich besser, erreicht aber mit der gegebenen Parametrisierung die Performance der besten Ensemble Methoden nicht"
   ]
  }
 ],
 "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 - solution",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "205.2px"
   },
   "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()) "
    }
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}