tutorial/model_drift/tutorial02-modeldrift-high-datadrift.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "9b6f3ff7",
   "metadata": {},
   "source": [
    "# Detect High Model Drift \n",
    "<b>With this tutorial you:</b><br />\n",
    "Understand how to use Eurybia to detect datadrift\n",
    "\n",
    "Contents:\n",
    "- Detect data drift  \n",
    "- Compile Drift over years\n",
    "\n",
    "This public dataset comes from :\n",
    "\n",
    "https://www.kaggle.com/sobhanmoosavi/us-accidents/version/10\n",
    "\n",
    "---\n",
    "Acknowledgements\n",
    "- Moosavi, Sobhan, Mohammad Hossein Samavatian, Srinivasan Parthasarathy, and Rajiv Ramnath. “A Countrywide Traffic Accident Dataset.”, 2019.\n",
    "- Moosavi, Sobhan, Mohammad Hossein Samavatian, Srinivasan Parthasarathy, Radu Teodorescu, and Rajiv Ramnath. \"Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insights.\" In proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, ACM, 2019.\n",
    "---\n",
    "\n",
    "In this tutorial, the data are not loaded raw, a data preparation to facilitate the use of the tutorial has been done. You can find it here : \n",
    "https://github.com/MAIF/eurybia/blob/master/eurybia/data/dataprep_US_car_accidents.ipynb"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6ee7dedd",
   "metadata": {},
   "source": [
    "**Requirements notice** : the following tutorial may use third party modules not included in Eurybia.  \n",
    "You can find them all in one file [on our Github repository](https://github.com/MAIF/eurybia/blob/master/requirements.dev.txt) or you can manually install those you are missing, if any."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8c767469",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from category_encoders import OrdinalEncoder\n",
    "import catboost\n",
    "from eurybia import SmartDrift\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn import metrics\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "939acff0",
   "metadata": {},
   "source": [
    "## Import Dataset and split in training and production dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e0b10b1b",
   "metadata": {},
   "outputs": [],
   "source": [
    "from eurybia.data.data_loader import data_loading"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "6d3d1d90",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_car_accident = data_loading(\"us_car_accident\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8a0a6ef4",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Start_Lat</th>\n",
       "      <th>Start_Lng</th>\n",
       "      <th>Distance(mi)</th>\n",
       "      <th>Temperature(F)</th>\n",
       "      <th>Humidity(%)</th>\n",
       "      <th>Visibility(mi)</th>\n",
       "      <th>Wind_Direction</th>\n",
       "      <th>Weather_Condition</th>\n",
       "      <th>day_of_week_acc</th>\n",
       "      <th>Nautical_Twilight</th>\n",
       "      <th>season_acc</th>\n",
       "      <th>cible</th>\n",
       "      <th>year_acc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>37.5</td>\n",
       "      <td>-122.3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>73.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.112071</td>\n",
       "      <td>Fair</td>\n",
       "      <td>3</td>\n",
       "      <td>Day</td>\n",
       "      <td>autumn</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>33.4</td>\n",
       "      <td>-112.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.175655</td>\n",
       "      <td>Fair</td>\n",
       "      <td>5</td>\n",
       "      <td>Night</td>\n",
       "      <td>spring</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28.0</td>\n",
       "      <td>-82.3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.172628</td>\n",
       "      <td>Cloudy</td>\n",
       "      <td>1</td>\n",
       "      <td>Night</td>\n",
       "      <td>autumn</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33.1</td>\n",
       "      <td>-117.3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.195514</td>\n",
       "      <td>Fair</td>\n",
       "      <td>0</td>\n",
       "      <td>Night</td>\n",
       "      <td>winter</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>39.8</td>\n",
       "      <td>-86.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.145093</td>\n",
       "      <td>Fair</td>\n",
       "      <td>6</td>\n",
       "      <td>Day</td>\n",
       "      <td>winter</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Start_Lat  Start_Lng  Distance(mi)  Temperature(F)  Humidity(%)  \\\n",
       "0       37.5     -122.3           0.0            73.0         44.0   \n",
       "1       33.4     -112.6           0.0            59.0         55.0   \n",
       "2       28.0      -82.3           1.0            77.0         89.0   \n",
       "3       33.1     -117.3           1.0            69.0         11.0   \n",
       "4       39.8      -86.0           0.0            43.0         81.0   \n",
       "\n",
       "   Visibility(mi)  Wind_Direction Weather_Condition  day_of_week_acc  \\\n",
       "0            10.0        0.112071              Fair                3   \n",
       "1            10.0        0.175655              Fair                5   \n",
       "2            10.0        0.172628            Cloudy                1   \n",
       "3            10.0        0.195514              Fair                0   \n",
       "4            10.0        0.145093              Fair                6   \n",
       "\n",
       "  Nautical_Twilight season_acc  cible  year_acc  \n",
       "0               Day     autumn      0      2020  \n",
       "1             Night     spring      0      2020  \n",
       "2             Night     autumn      0      2020  \n",
       "3             Night     winter      0      2020  \n",
       "4               Day     winter      0      2020  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_car_accident.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "78f258f5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Start_Lat</th>\n",
       "      <th>Start_Lng</th>\n",
       "      <th>Distance(mi)</th>\n",
       "      <th>Temperature(F)</th>\n",
       "      <th>Humidity(%)</th>\n",
       "      <th>Visibility(mi)</th>\n",
       "      <th>Wind_Direction</th>\n",
       "      <th>Weather_Condition</th>\n",
       "      <th>day_of_week_acc</th>\n",
       "      <th>Nautical_Twilight</th>\n",
       "      <th>season_acc</th>\n",
       "      <th>cible</th>\n",
       "      <th>year_acc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>37.5</td>\n",
       "      <td>-122.3</td>\n",
       "      <td>0.0</td>\n",
       "      <td>73.0</td>\n",
       "      <td>44.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.112071</td>\n",
       "      <td>Fair</td>\n",
       "      <td>3</td>\n",
       "      <td>Day</td>\n",
       "      <td>autumn</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>33.4</td>\n",
       "      <td>-112.6</td>\n",
       "      <td>0.0</td>\n",
       "      <td>59.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.175655</td>\n",
       "      <td>Fair</td>\n",
       "      <td>5</td>\n",
       "      <td>Night</td>\n",
       "      <td>spring</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>28.0</td>\n",
       "      <td>-82.3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>77.0</td>\n",
       "      <td>89.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.172628</td>\n",
       "      <td>Cloudy</td>\n",
       "      <td>1</td>\n",
       "      <td>Night</td>\n",
       "      <td>autumn</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>33.1</td>\n",
       "      <td>-117.3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>69.0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.195514</td>\n",
       "      <td>Fair</td>\n",
       "      <td>0</td>\n",
       "      <td>Night</td>\n",
       "      <td>winter</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>39.8</td>\n",
       "      <td>-86.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>43.0</td>\n",
       "      <td>81.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>0.145093</td>\n",
       "      <td>Fair</td>\n",
       "      <td>6</td>\n",
       "      <td>Day</td>\n",
       "      <td>winter</td>\n",
       "      <td>0</td>\n",
       "      <td>2020</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Start_Lat  Start_Lng  Distance(mi)  Temperature(F)  Humidity(%)  \\\n",
       "0       37.5     -122.3           0.0            73.0         44.0   \n",
       "1       33.4     -112.6           0.0            59.0         55.0   \n",
       "2       28.0      -82.3           1.0            77.0         89.0   \n",
       "3       33.1     -117.3           1.0            69.0         11.0   \n",
       "4       39.8      -86.0           0.0            43.0         81.0   \n",
       "\n",
       "   Visibility(mi)  Wind_Direction Weather_Condition  day_of_week_acc  \\\n",
       "0            10.0        0.112071              Fair                3   \n",
       "1            10.0        0.175655              Fair                5   \n",
       "2            10.0        0.172628            Cloudy                1   \n",
       "3            10.0        0.195514              Fair                0   \n",
       "4            10.0        0.145093              Fair                6   \n",
       "\n",
       "  Nautical_Twilight season_acc  cible  year_acc  \n",
       "0               Day     autumn      0      2020  \n",
       "1             Night     spring      0      2020  \n",
       "2             Night     autumn      0      2020  \n",
       "3             Night     winter      0      2020  \n",
       "4               Day     winter      0      2020  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_car_accident.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "05039303",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(31935, 13)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_car_accident.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "a1d226fa",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Let us consider that the column \"year_acc\" corresponds to the reference date. \n",
    "#In 2016, a model was trained using data. And in next years, we want to detect data drift on new data in production to predict\n",
    "df_accident_baseline = df_car_accident.loc[df_car_accident['year_acc'] == 2016]\n",
    "df_accident_2017 = df_car_accident.loc[df_car_accident['year_acc'] == 2017]\n",
    "df_accident_2018 = df_car_accident.loc[df_car_accident['year_acc'] == 2018]\n",
    "df_accident_2019 = df_car_accident.loc[df_car_accident['year_acc'] == 2019]\n",
    "df_accident_2020 = df_car_accident.loc[df_car_accident['year_acc'] == 2020]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "1e81bb4e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>cible</th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>year_acc</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2016</th>\n",
       "      <td>71.331283</td>\n",
       "      <td>28.668717</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2017</th>\n",
       "      <td>68.273017</td>\n",
       "      <td>31.726983</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2018</th>\n",
       "      <td>66.641250</td>\n",
       "      <td>33.358750</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2019</th>\n",
       "      <td>79.600182</td>\n",
       "      <td>20.399818</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2020</th>\n",
       "      <td>90.525000</td>\n",
       "      <td>9.475000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "cible             0          1\n",
       "year_acc                      \n",
       "2016      71.331283  28.668717\n",
       "2017      68.273017  31.726983\n",
       "2018      66.641250  33.358750\n",
       "2019      79.600182  20.399818\n",
       "2020      90.525000   9.475000"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#We will train a classification model to predict the severity of an accident. 0 for a less severe accident and 1 for a severe accident.\n",
    "#Let's check percentage in class 0 and 1\n",
    "pd.crosstab(df_car_accident.year_acc, df_car_accident.cible, normalize = 'index')*100"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "c13ca2a5",
   "metadata": {},
   "outputs": [],
   "source": [
    "y_df_learning=df_accident_baseline['cible'].to_frame()\n",
    "X_df_learning=df_accident_baseline[df_accident_baseline.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2017=df_accident_2017['cible'].to_frame()\n",
    "X_df_2017=df_accident_2017[df_accident_2017.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2018=df_accident_2018['cible'].to_frame()\n",
    "X_df_2018=df_accident_2018[df_accident_2018.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2019=df_accident_2019['cible'].to_frame()\n",
    "X_df_2019=df_accident_2019[df_accident_2019.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2020=df_accident_2020['cible'].to_frame()\n",
    "X_df_2020=df_accident_2020[df_accident_2020.columns.difference(['cible','year_acc'])]\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "676b7cd8",
   "metadata": {},
   "source": [
    "## Building Supervized Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "daba7f7d",
   "metadata": {},
   "outputs": [],
   "source": [
    "features = ['Start_Lat', 'Start_Lng', 'Distance(mi)', 'Temperature(F)',\n",
    "       'Humidity(%)', 'Visibility(mi)', 'Wind_Direction',\n",
    "       'Weather_Condition', 'day_of_week_acc', 'Nautical_Twilight',\n",
    "       'season_acc']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "c4b67a87",
   "metadata": {},
   "outputs": [],
   "source": [
    "df_car_accident = data_loading(\"us_car_accident\")\n",
    "df_accident_baseline = df_car_accident.loc[df_car_accident['year_acc'] == 2016]\n",
    "df_accident_2017 = df_car_accident.loc[df_car_accident['year_acc'] == 2017]\n",
    "df_accident_2018 = df_car_accident.loc[df_car_accident['year_acc'] == 2018]\n",
    "df_accident_2019 = df_car_accident.loc[df_car_accident['year_acc'] == 2019]\n",
    "df_accident_2020 = df_car_accident.loc[df_car_accident['year_acc'] == 2020]\n",
    "\n",
    "y_df_learning=df_accident_baseline['cible'].to_frame()\n",
    "X_df_learning=df_accident_baseline[df_accident_baseline.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2017=df_accident_2017['cible'].to_frame()\n",
    "X_df_2017=df_accident_2017[df_accident_2017.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2018=df_accident_2018['cible'].to_frame()\n",
    "X_df_2018=df_accident_2018[df_accident_2018.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2019=df_accident_2019['cible'].to_frame()\n",
    "X_df_2019=df_accident_2019[df_accident_2019.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "y_df_2020=df_accident_2020['cible'].to_frame()\n",
    "X_df_2020=df_accident_2020[df_accident_2020.columns.difference(['cible','year_acc'])]\n",
    "\n",
    "features = ['Start_Lat', 'Start_Lng', 'Distance(mi)', 'Temperature(F)',\n",
    "   'Humidity(%)', 'Visibility(mi)', 'Wind_Direction',\n",
    "   'Weather_Condition', 'day_of_week_acc', 'Nautical_Twilight',\n",
    "   'season_acc']\n",
    "\n",
    "features_to_encode = [col for col in X_df_learning[features].columns if X_df_learning[col].dtype not in ('float64','int64')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "268f65bc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Distance(mi)</th>\n",
       "      <th>Humidity(%)</th>\n",
       "      <th>Nautical_Twilight</th>\n",
       "      <th>Start_Lat</th>\n",
       "      <th>Start_Lng</th>\n",
       "      <th>Temperature(F)</th>\n",
       "      <th>Visibility(mi)</th>\n",
       "      <th>Weather_Condition</th>\n",
       "      <th>Wind_Direction</th>\n",
       "      <th>day_of_week_acc</th>\n",
       "      <th>season_acc</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8001</th>\n",
       "      <td>0.0</td>\n",
       "      <td>83.0</td>\n",
       "      <td>Day</td>\n",
       "      <td>45.4</td>\n",
       "      <td>-122.8</td>\n",
       "      <td>60.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>Overcast</td>\n",
       "      <td>0.333966</td>\n",
       "      <td>2</td>\n",
       "      <td>summer</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8006</th>\n",
       "      <td>0.0</td>\n",
       "      <td>46.0</td>\n",
       "      <td>Day</td>\n",
       "      <td>35.1</td>\n",
       "      <td>-80.8</td>\n",
       "      <td>94.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>Partly Cloudy</td>\n",
       "      <td>0.193432</td>\n",
       "      <td>2</td>\n",
       "      <td>summer</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8015</th>\n",
       "      <td>0.0</td>\n",
       "      <td>97.0</td>\n",
       "      <td>Day</td>\n",
       "      <td>35.2</td>\n",
       "      <td>-80.8</td>\n",
       "      <td>43.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>Overcast</td>\n",
       "      <td>0.197866</td>\n",
       "      <td>2</td>\n",
       "      <td>winter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8018</th>\n",
       "      <td>2.0</td>\n",
       "      <td>91.0</td>\n",
       "      <td>Day</td>\n",
       "      <td>40.8</td>\n",
       "      <td>-84.6</td>\n",
       "      <td>24.0</td>\n",
       "      <td>5.0</td>\n",
       "      <td>Overcast</td>\n",
       "      <td>0.315414</td>\n",
       "      <td>0</td>\n",
       "      <td>winter</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8021</th>\n",
       "      <td>0.0</td>\n",
       "      <td>68.0</td>\n",
       "      <td>Day</td>\n",
       "      <td>34.0</td>\n",
       "      <td>-118.4</td>\n",
       "      <td>68.0</td>\n",
       "      <td>10.0</td>\n",
       "      <td>Clear</td>\n",
       "      <td>0.193432</td>\n",
       "      <td>3</td>\n",
       "      <td>autumn</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      Distance(mi)  Humidity(%) Nautical_Twilight  Start_Lat  Start_Lng  \\\n",
       "8001           0.0         83.0               Day       45.4     -122.8   \n",
       "8006           0.0         46.0               Day       35.1      -80.8   \n",
       "8015           0.0         97.0               Day       35.2      -80.8   \n",
       "8018           2.0         91.0               Day       40.8      -84.6   \n",
       "8021           0.0         68.0               Day       34.0     -118.4   \n",
       "\n",
       "      Temperature(F)  Visibility(mi) Weather_Condition  Wind_Direction  \\\n",
       "8001            60.0            10.0          Overcast        0.333966   \n",
       "8006            94.0            10.0     Partly Cloudy        0.193432   \n",
       "8015            43.0             1.0          Overcast        0.197866   \n",
       "8018            24.0             5.0          Overcast        0.315414   \n",
       "8021            68.0            10.0             Clear        0.193432   \n",
       "\n",
       "      day_of_week_acc season_acc  \n",
       "8001                2     summer  \n",
       "8006                2     summer  \n",
       "8015                2     winter  \n",
       "8018                0     winter  \n",
       "8021                3     autumn  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_df_learning.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8f971d9b",
   "metadata": {},
   "outputs": [],
   "source": [
    "features_to_encode = [col for col in X_df_learning[features].columns if X_df_learning[col].dtype not in ('float64','int64')]\n",
    "\n",
    "encoder = OrdinalEncoder(cols=features_to_encode)\n",
    "encoder = encoder.fit(X_df_learning[features])\n",
    "\n",
    "X_df_learning_encoded=encoder.transform(X_df_learning)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "1e7fc14c",
   "metadata": {},
   "outputs": [],
   "source": [
    "Xtrain, Xtest, ytrain, ytest = train_test_split(X_df_learning_encoded, y_df_learning, train_size=0.75, random_state=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "d65eadcb",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_pool_cat = catboost.Pool(data=Xtrain, label= ytrain, cat_features = features_to_encode)\n",
    "test_pool_cat = catboost.Pool(data=Xtest, label= ytest, cat_features = features_to_encode)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "8bcecc82",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "3e4ecd32488c49faa7d4f5a345faa643",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "MetricVisualizer(layout=Layout(align_self='stretch', height='500px'))"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model = catboost.CatBoostClassifier(loss_function= \"Logloss\", eval_metric=\"Logloss\",\n",
    "                                    learning_rate=0.143852,\n",
    "                                    iterations=300,\n",
    "                                    l2_leaf_reg=15,\n",
    "                                    max_depth = 4,\n",
    "                                    use_best_model=True,\n",
    "                                    custom_loss=['Accuracy', 'AUC', 'Logloss'])\n",
    "\n",
    "model = model.fit(train_pool_cat, plot=True,eval_set=test_pool_cat, verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "ae73b71a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.7689429564506236\n"
     ]
    }
   ],
   "source": [
    "proba = model.predict_proba(Xtest)\n",
    "print(metrics.roc_auc_score(ytest,proba[:,1]))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f8010a48",
   "metadata": {},
   "source": [
    "## Use Eurybia for data validation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "c7ae204e",
   "metadata": {},
   "outputs": [],
   "source": [
    "from eurybia import SmartDrift"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "f8456034",
   "metadata": {},
   "outputs": [],
   "source": [
    "SD = SmartDrift(df_current=X_df_2017,\n",
    "                df_baseline=X_df_learning,\n",
    "                deployed_model=model, # Optional: put in perspective result with importance on deployed model\n",
    "                encoding=encoder # Optional: if deployed_model and encoder to use this model\n",
    "               )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "3d998196",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "CPU times: user 7 µs, sys: 3 µs, total: 10 µs\n",
      "Wall time: 18.4 µs\n",
      "The computed AUC on the X_test used to build datadrift_classifier is equal to: 0.6459837259371833\n"
     ]
    }
   ],
   "source": [
    "%time\n",
    "SD.compile(full_validation=True, # Optional: to save time, leave the default False value. If True, analyze consistency on modalities between columns.\n",
    "           date_compile_auc = '01/01/2017', # Optional: useful when computing the drift for a time that is not now\n",
    "           datadrift_file = \"car_accident_auc.csv\" # Optional: name of the csv file that contains the performance history of data drift\n",
    "          )\n",
    "                 "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "01c2f690",
   "metadata": {},
   "source": [
    "As soon as compile() method, Eurybia displays default consistency checks as warnings.<br />\n",
    "If some modalities are not present during training and are in production dataset, the deployed model will consider them wrongly.<br />\n",
    "Inversely, if some modalities are present during training and are not in production dataset, it means that some profiles are missing."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c733b40f",
   "metadata": {},
   "source": [
    "## Add model drift in report"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ba8578c8",
   "metadata": {},
   "source": [
    "For the moment, the model drift part of eurybia only consists of displaying performance of deployed model. \n",
    "(We hope to bring new features in the future on this part)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "65e4592d",
   "metadata": {},
   "source": [
    "### Put model performance in DataFrame"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "f53935dd",
   "metadata": {},
   "outputs": [],
   "source": [
    "proba = model.predict_proba(X_df_2017)\n",
    "performance = metrics.roc_auc_score(y_df_2017,proba[:,1]).round(5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "4be8debb",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Create Dataframe to track performance over the years\n",
    "df_performance = pd.DataFrame({'annee': [2017], 'mois':[1], 'performance': [performance]})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "136261b6",
   "metadata": {},
   "outputs": [],
   "source": [
    "SD.add_data_modeldrift(dataset=df_performance,metric='performance') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "af9bf77a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "Report saved to ./report_car_accident_modeldrift_2017.html. To upload and share your report, create a free Datapane account by running `!datapane signup`."
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "SD.generate_report(    \n",
    "    output_file='report_car_accident_modeldrift_2017.html',    \n",
    "    title_story=\"Model drift Report\",\n",
    "    title_description=\"\"\"US Car accident model drift 2017\"\"\", # Optional: add a subtitle to describe report\n",
    "    project_info_file=\"../../eurybia/data/project_info_car_accident.yml\" # Optional: add information on report\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0aca5ec4",
   "metadata": {},
   "source": [
    "This tutorial contains only anlysis on additional features of model drift. For more detailed information on data drift, you can consult these tutorials : (https://github.com/MAIF/eurybia/tree/master/tutorial/model_drift/tutorial02-datadrift-high-datadrift.ipynb)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6710b459",
   "metadata": {},
   "source": [
    "## Compile Drift over years"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4bd535e1",
   "metadata": {},
   "source": [
    "### Compile Drift et generate report for Year 2018"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "756c9de1",
   "metadata": {},
   "outputs": [],
   "source": [
    "SD = SmartDrift(df_current=X_df_2018,\n",
    "                df_baseline=X_df_learning,\n",
    "                deployed_model=model, # Optional: put in perspective result with importance on deployed model\n",
    "                encoding=encoder # Optional: if deployed_model and encoder to use this model\n",
    "               )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "572b1f06",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The computed AUC on the X_test used to build datadrift_classifier is equal to: 0.6911612512986636\n"
     ]
    }
   ],
   "source": [
    "SD.compile(full_validation=True, # Optional: to save time, leave the default False value. If True, analyze consistency on modalities between columns.\n",
    "           date_compile_auc = '01/01/2018', # Optional: useful when computing the drift for a time that is not now\n",
    "           datadrift_file = \"car_accident_auc.csv\" # Optional: name of the csv file that contains the performance history of data drift\n",
    "          )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ecebfa0c",
   "metadata": {},
   "outputs": [],
   "source": [
    "proba = model.predict_proba(X_df_2018)\n",
    "performance = metrics.roc_auc_score(y_df_2018,proba[:,1]).round(5)\n",
    "df_performance = df_performance.append({'annee': 2018, 'mois':1, 'performance': performance}, ignore_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "810c6da6",
   "metadata": {},
   "source": [
    "### Compile Drift et generate report for Year 2019"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "0912c225",
   "metadata": {},
   "outputs": [],
   "source": [
    "SD = SmartDrift(df_current=X_df_2019,\n",
    "                df_baseline=X_df_learning,\n",
    "                deployed_model=model, # Optional: put in perspective result with importance on deployed model\n",
    "                encoding=encoder # Optional: if deployed_model and encoder to use this model\n",
    "               )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "eacffb97",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The computed AUC on the X_test used to build datadrift_classifier is equal to: 0.9131375742708316\n"
     ]
    }
   ],
   "source": [
    "SD.compile(full_validation=True, # Optional: to save time, leave the default False value. If True, analyze consistency on modalities between columns.\n",
    "           date_compile_auc = '01/01/2019', # Optional: useful when computing the drift for a time that is not now\n",
    "           datadrift_file = \"car_accident_auc.csv\" # Optional: name of the csv file that contains the performance history of data drift\n",
    "          )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "985c1960",
   "metadata": {},
   "outputs": [],
   "source": [
    "proba = model.predict_proba(X_df_2019)\n",
    "performance = metrics.roc_auc_score(y_df_2019,proba[:,1]).round(5)\n",
    "df_performance = df_performance.append({'annee': 2019, 'mois':1, 'performance': performance}, ignore_index=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1fbd247b",
   "metadata": {},
   "source": [
    "### Compile Drift et generate report for Year 2020"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "bf363bc6",
   "metadata": {},
   "outputs": [],
   "source": [
    "SD = SmartDrift(df_current=X_df_2020,\n",
    "                df_baseline=X_df_learning,\n",
    "                deployed_model=model, # Optional: put in perspective result with importance on deployed model\n",
    "                encoding=encoder # Optional: if deployed_model and encoder to use this model\n",
    "               )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "f7b102bf",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The variable Weather_Condition has mismatching unique values:\n",
      "[] | ['Overcast', 'Clear', 'Scattered Clouds']\n",
      "\n",
      "The computed AUC on the X_test used to build datadrift_classifier is equal to: 0.9358807623200552\n"
     ]
    }
   ],
   "source": [
    "SD.compile(full_validation=True, # Optional: to save time, leave the default False value. If True, analyze consistency on modalities between columns.\n",
    "           date_compile_auc = '01/01/2020', # Optional: useful when computing the drift for a time that is not now\n",
    "           datadrift_file = \"car_accident_auc.csv\" # Optional: name of the csv file that contains the performance history of data drift\n",
    "          )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2636bcb7",
   "metadata": {},
   "outputs": [],
   "source": [
    "proba = model.predict_proba(X_df_2020)\n",
    "performance = metrics.roc_auc_score(y_df_2020,proba[:,1]).round(5)\n",
    "df_performance = df_performance.append({'annee': 2020, 'mois':1, 'performance': performance}, ignore_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "f9d09d5e",
   "metadata": {},
   "outputs": [],
   "source": [
    "SD.add_data_modeldrift(dataset=df_performance,metric='performance') "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "a936527c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "SD.plot.generate_historical_datadrift_metric() # works if date_compile_auc and/or datadrift_file are filled"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2324467b",
   "metadata": {},
   "source": [
    "In 2019 and 2020, data drift is very high. Is there any impact on the performance of the model?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "64665647",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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"
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "SD.plot.generate_modeldrift_data() # works if add_data_modeldrift used before                "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "438706e2",
   "metadata": {},
   "source": [
    "While data drift was high in 2019, the impact on model performance is low. In 2020, data drift leads to a decrease in model performance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "c9089d96",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "Report saved to ./report_car_accident_modeldrift_2020.html. To upload and share your report, create a free Datapane account by running `!datapane signup`."
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "SD.generate_report(    \n",
    "    output_file='report_car_accident_modeldrift_2020.html',    \n",
    "    title_story=\"Model drift Report\",\n",
    "    title_description=\"\"\"US Car accident model drift 2020\"\"\", # Optional: add a subtitle to describe report\n",
    "    project_info_file=\"../../eurybia/data/project_info_car_accident.yml\" # Optional: add information on report\n",
    "    ) "
   ]
  }
 ],
 "metadata": {
  "interpreter": {
   "hash": "13d044b7eb1183d24388c730821bfdfb708fbb1f7ef396dd9449b9735574aa76"
  },
  "kernelspec": {
   "display_name": "dev_eurybia",
   "language": "python",
   "name": "dev_eurybia"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {
    "height": "calc(100% - 180px)",
    "left": "10px",
    "top": "150px",
    "width": "336px"
   },
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}