{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test For `DataDrifChecher`-`pydrift` \n",
    "\n",
    "We're going to test how it works with the famous titanic dataset\n",
    "\n",
    "# Dependencies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "from pydrift import DataDriftChecker\n",
    "from pydrift.constants import PATH_DATA, RANDOM_STATE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read Data "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_titanic = pd.read_csv(PATH_DATA / 'titanic.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Constants "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "TARGET = 'Survived'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Data Split\n",
    "\n",
    "We drop `PassengerId`, `Name`, `Cabin`, `Ticket` because are features with high cardinality (passenger related variables)\n",
    "\n",
    "50% sample will give us a non-drift problem"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "X = df_titanic.drop(columns=['PassengerId', 'Name', 'Cabin', 'Ticket', TARGET])\n",
    "y = df_titanic[TARGET]\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(\n",
    "    X, y, test_size=.5, random_state=RANDOM_STATE, stratify=y\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Instanciate `pydrift.DataDriftChecker` "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_drift_checker_ok = DataDriftChecker(X_train, X_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test  `ml_model_can_discriminate` Feature"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x309.6 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "No drift found in discriminative model step\n",
      "\n",
      "AUC drift check model: 0.50\n",
      "AUC threshold: .5 ± 0.10\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ok.ml_model_can_discriminate();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test Numerical Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "No drift found in numerical columns check step\n",
      "\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ok.check_numerical_columns();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test Categorical Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "No drift found in categorical columns check step\n",
      "\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ok.check_categorical_columns();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Same But  Make It Drift\n",
    "\n",
    "`pydrift` tells you that the problem is in `Sex` feature (as is obviously in this example)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x309.6 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drift found in discriminative model step, take a look on the most discriminative features (plots when minimal is set to False)\n",
      "\n",
      "AUC drift check model: 1.00\n",
      "AUC threshold: .5 ± 0.10\n"
     ]
    }
   ],
   "source": [
    "X_women = X[X['Sex'] == 'female']\n",
    "X_men = X[X['Sex'] == 'male']\n",
    "\n",
    "data_drift_checker_ko = DataDriftChecker(X_women, X_men)\n",
    "data_drift_checker_ko.ml_model_can_discriminate();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test Numerical Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drift found in numerical columns check step, take a look on the variables that are drifted, if one is not important you could simply delete it, otherwise check the data source\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Features drifted (numerical): Pclass, Age, SibSp, Parch, Fare\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ko.check_numerical_columns();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test Categorical Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drift found in categorical columns check step, take a look on the variables that are drifted, if one is not important you could simply delete it, otherwise check the data source\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Features drifted (categorical): Sex, Embarked\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ko.check_categorical_columns();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# All Drifted Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Age', 'Embarked', 'Fare', 'Parch', 'Pclass', 'Sex', 'SibSp'}"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_drift_checker_ko.drifted_features"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Same But  Make It Drift With Various Features\n",
    "\n",
    "`pydrift` detects that the problem is but `Pclass` and `Fare` feature (again obviously because this is an example)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 576x309.6 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drift found in discriminative model step, take a look on the most discriminative features (plots when minimal is set to False)\n",
      "\n",
      "AUC drift check model: 1.00\n",
      "AUC threshold: .5 ± 0.10\n"
     ]
    }
   ],
   "source": [
    "mask = (X['Pclass'] > 1) & (X['Fare'] > 10)\n",
    "\n",
    "X_mask = X[mask]\n",
    "X_unmask = X[~mask]\n",
    "\n",
    "data_drift_checker_ko_2 = DataDriftChecker(X_mask, X_unmask)\n",
    "data_drift_checker_ko_2.ml_model_can_discriminate();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test Numerical Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drift found in numerical columns check step, take a look on the variables that are drifted, if one is not important you could simply delete it, otherwise check the data source\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Features drifted (numerical): Pclass, Age, SibSp, Parch, Fare\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ko_2.check_numerical_columns();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Test Categorical Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Drift found in categorical columns check step, take a look on the variables that are drifted, if one is not important you could simply delete it, otherwise check the data source\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Features drifted (categorical): Sex, Embarked\n"
     ]
    }
   ],
   "source": [
    "data_drift_checker_ko_2.check_categorical_columns();"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# All Drifted Features "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'Age', 'Embarked', 'Fare', 'Parch', 'Pclass', 'Sex', 'SibSp'}"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data_drift_checker_ko_2.drifted_features"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}