{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "# Feature Engineering\n",
    "# Klassifikation\n",
    "## Instanzbasierte Modelle\n",
    "## Regelbasierte Modelle\n",
    "## Mathematische Modelle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import sys\n",
    "sys.path.append('./')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:39.858981Z",
     "start_time": "2020-03-17T12:01:37.904657Z"
    }
   },
   "outputs": [],
   "source": [
    "## preparation\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns; sns.set()\n",
    "%matplotlib inline\n",
    "\n",
    "datapath = '../3_data'\n",
    "from os import chdir; chdir(datapath)\n",
    "\n",
    "from bfh_cas_pml import prep_data, prep_demo_data\n",
    "X_train, X_test, y_train, y_test = prep_data('bank_data_prep.csv', 'y', seed = 1234)\n",
    "X_demo, y_demo = prep_demo_data('demo_data_class.csv', 'y')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LinearDiscriminantAnalysis\n",
    "#### Theorie"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "kein Code zu diesem Kapitel"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Praxis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:40.035126Z",
     "start_time": "2020-03-17T12:01:39.864400Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8487982963188317\n"
     ]
    }
   ],
   "source": [
    "from sklearn.discriminant_analysis import LinearDiscriminantAnalysis\n",
    "model = LinearDiscriminantAnalysis()\n",
    "model.fit(X_train, y_train) \n",
    "print(model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:40.051095Z",
     "start_time": "2020-03-17T12:01:40.038394Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'covariance_estimator': None, 'n_components': None, 'priors': None, 'shrinkage': None, 'solver': 'svd', 'store_covariance': False, 'tol': 0.0001}\n"
     ]
    }
   ],
   "source": [
    "print(model.get_params())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### QuadraticDiscriminantAnalysis (eine Variante)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:40.144808Z",
     "start_time": "2020-03-17T12:01:40.054435Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7246729540614543\n"
     ]
    }
   ],
   "source": [
    "from sklearn.discriminant_analysis \\\n",
    "    import QuadraticDiscriminantAnalysis\n",
    "model = QuadraticDiscriminantAnalysis()\n",
    "model.fit(X_train, y_train)\n",
    "print(model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:40.160468Z",
     "start_time": "2020-03-17T12:01:40.149447Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'priors': None, 'reg_param': 0.0, 'store_covariance': False, 'tol': 0.0001}\n"
     ]
    }
   ],
   "source": [
    "print(model.get_params())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "### SVC\n",
    "#### Theorie\n",
    "#### Praxis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:47.205171Z",
     "start_time": "2020-03-17T12:01:40.196843Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7161545482202616\n"
     ]
    }
   ],
   "source": [
    "from sklearn.svm import SVC\n",
    "model = SVC()\n",
    "model.fit(X_train, y_train) \n",
    "print(model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:47.221147Z",
     "start_time": "2020-03-17T12:01:47.210935Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'C': 1.0, 'break_ties': False, 'cache_size': 200, 'class_weight': None, 'coef0': 0.0, 'decision_function_shape': 'ovr', 'degree': 3, 'gamma': 'scale', 'kernel': 'rbf', 'max_iter': -1, 'probability': False, 'random_state': None, 'shrinking': True, 'tol': 0.001, 'verbose': False}\n"
     ]
    }
   ],
   "source": [
    "print(model.get_params())"
   ]
  },
  {
   "cell_type": "raw",
   "metadata": {},
   "source": [
    "## with scaled features\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "scaler = StandardScaler()\n",
    "\n",
    "scaler.fit(X_train)\n",
    "X_train_sc = scaler.transform(X_train)\n",
    "X_test_sc = scaler.transform(X_test)\n",
    "\n",
    "model.fit(X_train_sc, y_train) \n",
    "print(model.score(X_test_sc, y_test))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### GaussianNB\n",
    "in aller Kürze"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Theorie"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "classes_ : ['A' 'B']\n",
      "class_prior_ : [0.55555556 0.44444444]\n",
      "\n",
      "theta_ :\n",
      " [[5.58666667]\n",
      " [4.26666667]]\n",
      "\n",
      "var_ :\n",
      " [[0.31182222]\n",
      " [0.23055556]]\n"
     ]
    }
   ],
   "source": [
    "## demo of GaussianNB interna with demo data\n",
    "X_nb_train = X_demo\n",
    "y_nb_train = y_demo\n",
    "\n",
    "X_nb_train = X_nb_train.drop('X2', axis=1)\n",
    "#print(X_train)\n",
    "\n",
    "from sklearn.naive_bayes import GaussianNB\n",
    "model = GaussianNB()\n",
    "model.fit(X_nb_train, y_nb_train)\n",
    "\n",
    "## print model attributes\n",
    "print('classes_ :', model.classes_)\n",
    "print('class_prior_ :', model.class_prior_)\n",
    "print('\\ntheta_ :\\n', model.theta_)\n",
    "print('\\nvar_ :\\n', model.var_)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Praxis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:47.963126Z",
     "start_time": "2020-03-17T12:01:47.897232Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7337998174627319\n"
     ]
    }
   ],
   "source": [
    "from sklearn.naive_bayes import GaussianNB\n",
    "model = GaussianNB()\n",
    "model.fit(X_train, y_train) \n",
    "print(model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:48.042848Z",
     "start_time": "2020-03-17T12:01:48.032106Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'priors': None, 'var_smoothing': 1e-09}\n"
     ]
    }
   ],
   "source": [
    "print(model.get_params())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### LogisticRegression\n",
    "#### Theorie\n",
    "#### Praxis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2020-03-17T12:01:56.666086Z",
     "start_time": "2020-03-17T12:01:56.130695Z"
    },
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.8475813811986614\n"
     ]
    }
   ],
   "source": [
    "from sklearn.linear_model import LogisticRegression\n",
    "model = LogisticRegression(max_iter=4000)\n",
    "model.fit(X_train, y_train) \n",
    "print(model.score(X_test, y_test))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "C                    : 1.0  \n",
      "class_weight         : None \n",
      "dual                 : False\n",
      "fit_intercept        : True \n",
      "intercept_scaling    : 1    \n",
      "l1_ratio             : None \n",
      "max_iter             : 4000 \n",
      "multi_class          : deprecated\n",
      "n_jobs               : None \n",
      "penalty              : l2   \n",
      "random_state         : None \n",
      "solver               : lbfgs\n",
      "tol                  : 0.0001\n",
      "verbose              : 0    \n",
      "warm_start           : False\n"
     ]
    }
   ],
   "source": [
    "for key, value in model.get_params().items():\n",
    "    print(\"%-20s : %-5s\"  % (key, value))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "teaching",
   "language": "python",
   "name": "teaching"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.0"
  },
  "toc": {
   "base_numbering": "2.3",
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "2.3 Klassifikation - Mathematische Modelle",
   "title_sidebar": "Contents",
   "toc_cell": true,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "202.667px"
   },
   "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": "316.717px",
    "left": "782px",
    "right": "20px",
    "top": "119px",
    "width": "350px"
   },
   "types_to_exclude": [
    "module",
    "function",
    "builtin_function_or_method",
    "instance",
    "_Feature"
   ],
   "window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}