{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "56949d8f-4eaf-4685-9989-ba0b4b1945b7",
   "metadata": {},
   "source": [
    "# Baseline logit on spectacle companies with statmodels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "72480e84-2ccc-481a-9353-1199e4358d62",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import os\n",
    "import s3fs\n",
    "import re\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.ensemble import RandomForestClassifier\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix, classification_report, recall_score\n",
    "from sklearn.utils import class_weight\n",
    "from sklearn.neighbors import KNeighborsClassifier\n",
    "from sklearn.pipeline import Pipeline\n",
    "from sklearn.compose import ColumnTransformer\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.impute import SimpleImputer\n",
    "from sklearn.model_selection import GridSearchCV\n",
    "from sklearn.preprocessing import StandardScaler, MaxAbsScaler, MinMaxScaler\n",
    "from sklearn.metrics import make_scorer, f1_score, balanced_accuracy_score\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.metrics import roc_curve, auc, precision_recall_curve, average_precision_score\n",
    "from sklearn.exceptions import ConvergenceWarning, DataConversionWarning\n",
    "\n",
    "import statsmodels.api as sm\n",
    "\n",
    "import pickle\n",
    "import warnings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7090dc21-7889-4776-a0a4-f7c6a5416d53",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create filesystem object\n",
    "S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
    "fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "2f0d08c9-5b26-4eff-9c89-4a46f427dbf7",
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_train_test():\n",
    "    BUCKET = \"projet-bdc2324-team1/Generalization/musique\"\n",
    "    File_path_train = BUCKET + \"/Train_set.csv\"\n",
    "    File_path_test = BUCKET + \"/Test_set.csv\"\n",
    "    \n",
    "    with fs.open( File_path_train, mode=\"rb\") as file_in:\n",
    "        dataset_train = pd.read_csv(file_in, sep=\",\")\n",
    "        # dataset_train['y_has_purchased'] = dataset_train['y_has_purchased'].fillna(0)\n",
    "\n",
    "    with fs.open(File_path_test, mode=\"rb\") as file_in:\n",
    "        dataset_test = pd.read_csv(file_in, sep=\",\")\n",
    "        # dataset_test['y_has_purchased'] = dataset_test['y_has_purchased'].fillna(0)\n",
    "    \n",
    "    return dataset_train, dataset_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "438d0138-a254-464c-9e94-f7436576c1d5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def features_target_split(dataset_train, dataset_test):\n",
    "    features_l = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', \n",
    "            'time_between_purchase', 'nb_tickets_internet', 'fidelity',  'is_email_true', 'opt_in', #'is_partner',\n",
    "            'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']\n",
    "    X_train = dataset_train[features_l]\n",
    "    y_train = dataset_train[['y_has_purchased']]\n",
    "\n",
    "    X_test = dataset_test[features_l]\n",
    "    y_test = dataset_test[['y_has_purchased']]\n",
    "    return X_train, X_test, y_train, y_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "ebe9a887-61a4-4a5e-ac64-231307dd7647",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_570/3642896088.py:7: DtypeWarning: Columns (38) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  dataset_train = pd.read_csv(file_in, sep=\",\")\n",
      "/tmp/ipykernel_570/3642896088.py:11: DtypeWarning: Columns (38) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  dataset_test = pd.read_csv(file_in, sep=\",\")\n"
     ]
    }
   ],
   "source": [
    "dataset_train, dataset_test = load_train_test()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "b21fdea2-02c4-4222-b4e0-635e423f91c2",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "customer_id                    0\n",
       "nb_tickets                     0\n",
       "nb_purchases                   0\n",
       "total_amount                   0\n",
       "nb_suppliers                   0\n",
       "vente_internet_max             0\n",
       "purchase_date_min              0\n",
       "purchase_date_max              0\n",
       "time_between_purchase          0\n",
       "nb_tickets_internet            0\n",
       "street_id                      0\n",
       "structure_id              327067\n",
       "mcp_contact_id            135224\n",
       "fidelity                       0\n",
       "tenant_id                      0\n",
       "is_partner                     0\n",
       "deleted_at                354365\n",
       "gender                         0\n",
       "is_email_true                  0\n",
       "opt_in                         0\n",
       "last_buying_date          119201\n",
       "max_price                 119201\n",
       "ticket_sum                     0\n",
       "average_price             115193\n",
       "average_purchase_delay    119203\n",
       "average_price_basket      119203\n",
       "average_ticket_basket     119203\n",
       "total_price                 4008\n",
       "purchase_count                 0\n",
       "first_buying_date         119201\n",
       "country                    56856\n",
       "gender_label                   0\n",
       "gender_female                  0\n",
       "gender_male                    0\n",
       "gender_other                   0\n",
       "country_fr                 56856\n",
       "nb_campaigns                   0\n",
       "nb_campaigns_opened            0\n",
       "time_to_open              224310\n",
       "y_has_purchased                0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset_train.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "42c4d034-8bc1-4ebb-a1ff-60c0a86f8f7c",
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = features_target_split(dataset_train, dataset_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "94b4498d-6ae8-4c96-adbc-7ba1b8348160",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Shape train :  (354365, 17)\n",
      "Shape test :  (151874, 17)\n"
     ]
    }
   ],
   "source": [
    "print(\"Shape train : \", X_train.shape)\n",
    "print(\"Shape test : \", X_test.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6224fd31-c190-4168-b395-e0bf5806d79d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{0.0: 0.5481283836040216, 1.0: 5.694439980716696}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Compute Weights\n",
    "weights = class_weight.compute_class_weight(class_weight = 'balanced', classes = np.unique(y_train['y_has_purchased']),\n",
    "                                            y = y_train['y_has_purchased'])\n",
    "\n",
    "weight_dict = {np.unique(y_train['y_has_purchased'])[i]: weights[i] for i in range(len(np.unique(y_train['y_has_purchased'])))}\n",
    "weight_dict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "id": "4680f202-979e-483f-89b8-9df877203bcf",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0.54812838, 0.54812838, 0.54812838, ..., 5.69443998, 0.54812838,\n",
       "       0.54812838])"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Calcul des poids inverses à la fréquence des classes\n",
    "class_counts = np.bincount(y_train['y_has_purchased'])\n",
    "class_weights = len(y_train['y_has_purchased']) / (2 * class_counts)\n",
    "\n",
    "# Sélection des poids correspondants à chaque observation\n",
    "weights = class_weights[y_train['y_has_purchased'].values.astype(int)]\n",
    "weights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "id": "5f747be4-e70b-491c-8f0a-46cb278a2dee",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[354365. 354365. 354365. ... 354365. 354365. 354365.]\n",
      "354365\n"
     ]
    }
   ],
   "source": [
    "print(2 * weights * class_counts[y_train['y_has_purchased'].values.astype(int)])\n",
    "print(len(y_train['y_has_purchased']))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 124,
   "id": "648fb542-0186-493d-b274-be2c26a11967",
   "metadata": {},
   "outputs": [],
   "source": [
    "# model logit\n",
    "X = X_train.astype(int)\n",
    "# X = sm.add_constant(X.drop(\"gender_other\", axis=1))\n",
    "y = y_train['y_has_purchased'].values\n",
    "\n",
    "# print(X,y)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 125,
   "id": "978b9ebc-aa97-41d7-a48f-d1f79c1ed482",
   "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>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>gender_other</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>91</td>\n",
       "      <td>91</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>55</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0                0             0             0             0   \n",
       "1                0             0             0             0   \n",
       "2                0             0             0             0   \n",
       "3                0             0             0             0   \n",
       "4                0             0             0             0   \n",
       "...            ...           ...           ...           ...   \n",
       "354360           0             0             0             0   \n",
       "354361           0             0             0             0   \n",
       "354362           2             2            50             1   \n",
       "354363           1             1            55             1   \n",
       "354364           0             0             0             0   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                        0                550                550   \n",
       "1                        0                550                550   \n",
       "2                        0                550                550   \n",
       "3                        0                550                550   \n",
       "4                        0                550                550   \n",
       "...                    ...                ...                ...   \n",
       "354360                   0                550                550   \n",
       "354361                   0                550                550   \n",
       "354362                   0                 91                 91   \n",
       "354363                   0                 52                 52   \n",
       "354364                   0                550                550   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                          -1                    0         1              1   \n",
       "1                          -1                    0         0              1   \n",
       "2                          -1                    0         1              1   \n",
       "3                          -1                    0         0              1   \n",
       "4                          -1                    0         0              1   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354360                     -1                    0         0              1   \n",
       "354361                     -1                    0         0              1   \n",
       "354362                      0                    0         4              1   \n",
       "354363                      0                    0         1              1   \n",
       "354364                     -1                    0         0              1   \n",
       "\n",
       "        opt_in  gender_female  gender_male  gender_other  nb_campaigns  \\\n",
       "0            1              1            0             0            13   \n",
       "1            1              0            0             1            10   \n",
       "2            1              0            1             0            14   \n",
       "3            0              0            0             1             9   \n",
       "4            0              0            0             1             4   \n",
       "...        ...            ...          ...           ...           ...   \n",
       "354360       0              0            0             1             7   \n",
       "354361       1              0            1             0            11   \n",
       "354362       0              1            0             0             6   \n",
       "354363       1              0            1             0             3   \n",
       "354364       0              0            1             0             7   \n",
       "\n",
       "        nb_campaigns_opened  \n",
       "0                         4  \n",
       "1                         9  \n",
       "2                         0  \n",
       "3                         0  \n",
       "4                         0  \n",
       "...                     ...  \n",
       "354360                    0  \n",
       "354361                    2  \n",
       "354362                    6  \n",
       "354363                    0  \n",
       "354364                    0  \n",
       "\n",
       "[354365 rows x 17 columns]"
      ]
     },
     "execution_count": 125,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "id": "81b38ceb-5005-417d-a9a6-b2dac181a8fb",
   "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>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>354365.000000</td>\n",
       "      <td>354365.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>406.981861</td>\n",
       "      <td>396.551502</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>189.343612</td>\n",
       "      <td>195.881681</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.009640</td>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>188.475293</td>\n",
       "      <td>153.457966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       purchase_date_min  purchase_date_max\n",
       "count      354365.000000      354365.000000\n",
       "mean          406.981861         396.551502\n",
       "std           189.343612         195.881681\n",
       "min             0.009640           0.000000\n",
       "25%           188.475293         153.457966\n",
       "50%           550.000000         550.000000\n",
       "75%           550.000000         550.000000\n",
       "max           550.000000         550.000000"
      ]
     },
     "execution_count": 138,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train[[\"purchase_date_min\", \"purchase_date_max\"]].describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "id": "60effd66-2914-4cf9-aa0c-4e2f9dd13895",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "count    354365.000000\n",
       "mean         10.430360\n",
       "std          56.442718\n",
       "min           0.000000\n",
       "25%           0.000000\n",
       "50%           0.000000\n",
       "75%           0.000000\n",
       "max         547.443350\n",
       "dtype: float64"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(X_train[\"purchase_date_min\"] - X_train[\"purchase_date_max\"]).describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 145,
   "id": "7a99e480-9e11-448d-806e-3b71925a19db",
   "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>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>gender_other</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10.0</td>\n",
       "      <td>9.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>9.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354358</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354359</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>12.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>550.0</td>\n",
       "      <td>-1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>179675 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0              0.0           0.0           0.0           0.0   \n",
       "1              0.0           0.0           0.0           0.0   \n",
       "2              0.0           0.0           0.0           0.0   \n",
       "3              0.0           0.0           0.0           0.0   \n",
       "4              0.0           0.0           0.0           0.0   \n",
       "...            ...           ...           ...           ...   \n",
       "354358         0.0           0.0           0.0           0.0   \n",
       "354359         0.0           0.0           0.0           0.0   \n",
       "354360         0.0           0.0           0.0           0.0   \n",
       "354361         0.0           0.0           0.0           0.0   \n",
       "354364         0.0           0.0           0.0           0.0   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                      0.0              550.0              550.0   \n",
       "1                      0.0              550.0              550.0   \n",
       "2                      0.0              550.0              550.0   \n",
       "3                      0.0              550.0              550.0   \n",
       "4                      0.0              550.0              550.0   \n",
       "...                    ...                ...                ...   \n",
       "354358                 0.0              550.0              550.0   \n",
       "354359                 0.0              550.0              550.0   \n",
       "354360                 0.0              550.0              550.0   \n",
       "354361                 0.0              550.0              550.0   \n",
       "354364                 0.0              550.0              550.0   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                        -1.0                  0.0         1           True   \n",
       "1                        -1.0                  0.0         0           True   \n",
       "2                        -1.0                  0.0         1           True   \n",
       "3                        -1.0                  0.0         0           True   \n",
       "4                        -1.0                  0.0         0           True   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354358                   -1.0                  0.0         0           True   \n",
       "354359                   -1.0                  0.0         0           True   \n",
       "354360                   -1.0                  0.0         0           True   \n",
       "354361                   -1.0                  0.0         0           True   \n",
       "354364                   -1.0                  0.0         0           True   \n",
       "\n",
       "        opt_in  gender_female  gender_male  gender_other  nb_campaigns  \\\n",
       "0         True              1            0             0          13.0   \n",
       "1         True              0            0             1          10.0   \n",
       "2         True              0            1             0          14.0   \n",
       "3        False              0            0             1           9.0   \n",
       "4        False              0            0             1           4.0   \n",
       "...        ...            ...          ...           ...           ...   \n",
       "354358   False              1            0             0           1.0   \n",
       "354359    True              0            1             0          12.0   \n",
       "354360   False              0            0             1           7.0   \n",
       "354361    True              0            1             0          11.0   \n",
       "354364   False              0            1             0           7.0   \n",
       "\n",
       "        nb_campaigns_opened  \n",
       "0                       4.0  \n",
       "1                       9.0  \n",
       "2                       0.0  \n",
       "3                       0.0  \n",
       "4                       0.0  \n",
       "...                     ...  \n",
       "354358                  0.0  \n",
       "354359                  2.0  \n",
       "354360                  0.0  \n",
       "354361                  2.0  \n",
       "354364                  0.0  \n",
       "\n",
       "[179675 rows x 17 columns]"
      ]
     },
     "execution_count": 145,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train[X_train[\"time_between_purchase\"]==-1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 126,
   "id": "2475f2fe-3d1f-4845-9ede-0416dac83271",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Colonnes à standardiser\n",
    "\n",
    "\"\"\"\n",
    "var_num = ['nb_tickets', 'nb_purchases', \"total_amount\", \"nb_suppliers\", \"vente_internet_max\",\n",
    "                          \"purchase_date_min\", \"purchase_date_max\", \"time_between_purchase\", \"nb_tickets_internet\",\n",
    "                          \"fidelity\", \"nb_campaigns\", \"nb_campaigns_opened\"]\n",
    "                          \"\"\"\n",
    "\n",
    "numeric_features = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', \n",
    "            'time_between_purchase', 'nb_tickets_internet', 'fidelity',  'is_email_true', 'opt_in', #'is_partner',\n",
    "            'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']\n",
    "\n",
    "# Standardisation des colonnes sélectionnées\n",
    "scaler = StandardScaler()\n",
    "X[var_num] = scaler.fit_transform(X[var_num])\n",
    "X[numeric_features] = scaler.fit_transform(X[numeric_features])\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 128,
   "id": "1763bad4-36b5-4ebb-9702-b77ba19fb30e",
   "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>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>gender_other</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.004316</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>1.151186</td>\n",
       "      <td>1.071079</td>\n",
       "      <td>-0.775306</td>\n",
       "      <td>-0.434568</td>\n",
       "      <td>0.607945</td>\n",
       "      <td>0.522567</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>1.151186</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>-0.775306</td>\n",
       "      <td>2.301137</td>\n",
       "      <td>0.306155</td>\n",
       "      <td>1.701843</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.004316</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>1.151186</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>1.289813</td>\n",
       "      <td>-0.434568</td>\n",
       "      <td>0.708542</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>-0.868669</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>-0.775306</td>\n",
       "      <td>2.301137</td>\n",
       "      <td>0.205558</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>-0.868669</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>-0.775306</td>\n",
       "      <td>2.301137</td>\n",
       "      <td>-0.297426</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>-0.868669</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>-0.775306</td>\n",
       "      <td>2.301137</td>\n",
       "      <td>0.004365</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>1.151186</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>1.289813</td>\n",
       "      <td>-0.434568</td>\n",
       "      <td>0.406752</td>\n",
       "      <td>0.050856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>-0.000838</td>\n",
       "      <td>0.092966</td>\n",
       "      <td>-0.009150</td>\n",
       "      <td>1.219633</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>-1.665887</td>\n",
       "      <td>-1.557073</td>\n",
       "      <td>-0.175269</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>0.069949</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>-0.868669</td>\n",
       "      <td>1.071079</td>\n",
       "      <td>-0.775306</td>\n",
       "      <td>-0.434568</td>\n",
       "      <td>-0.096232</td>\n",
       "      <td>0.994277</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>-0.012631</td>\n",
       "      <td>0.021122</td>\n",
       "      <td>-0.005227</td>\n",
       "      <td>1.219633</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>-1.871668</td>\n",
       "      <td>-1.755983</td>\n",
       "      <td>-0.175269</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.004316</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>1.151186</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>1.289813</td>\n",
       "      <td>-0.434568</td>\n",
       "      <td>-0.398023</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>0.058193</td>\n",
       "      <td>-0.868669</td>\n",
       "      <td>-0.933638</td>\n",
       "      <td>1.289813</td>\n",
       "      <td>-0.434568</td>\n",
       "      <td>0.004365</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0        -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "1        -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "2        -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "3        -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "4        -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "...            ...           ...           ...           ...   \n",
       "354360   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "354361   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "354362   -0.000838      0.092966     -0.009150      1.219633   \n",
       "354363   -0.012631      0.021122     -0.005227      1.219633   \n",
       "354364   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                -0.599511           0.755994           0.783940   \n",
       "1                -0.599511           0.755994           0.783940   \n",
       "2                -0.599511           0.755994           0.783940   \n",
       "3                -0.599511           0.755994           0.783940   \n",
       "4                -0.599511           0.755994           0.783940   \n",
       "...                    ...                ...                ...   \n",
       "354360           -0.599511           0.755994           0.783940   \n",
       "354361           -0.599511           0.755994           0.783940   \n",
       "354362           -0.599511          -1.665887          -1.557073   \n",
       "354363           -0.599511          -1.871668          -1.755983   \n",
       "354364           -0.599511           0.755994           0.783940   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                   -0.192978            -0.264693 -0.004316       0.058193   \n",
       "1                   -0.192978            -0.264693 -0.029071       0.058193   \n",
       "2                   -0.192978            -0.264693 -0.004316       0.058193   \n",
       "3                   -0.192978            -0.264693 -0.029071       0.058193   \n",
       "4                   -0.192978            -0.264693 -0.029071       0.058193   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354360              -0.192978            -0.264693 -0.029071       0.058193   \n",
       "354361              -0.192978            -0.264693 -0.029071       0.058193   \n",
       "354362              -0.175269            -0.264693  0.069949       0.058193   \n",
       "354363              -0.175269            -0.264693 -0.004316       0.058193   \n",
       "354364              -0.192978            -0.264693 -0.029071       0.058193   \n",
       "\n",
       "          opt_in  gender_female  gender_male  gender_other  nb_campaigns  \\\n",
       "0       1.151186       1.071079    -0.775306     -0.434568      0.607945   \n",
       "1       1.151186      -0.933638    -0.775306      2.301137      0.306155   \n",
       "2       1.151186      -0.933638     1.289813     -0.434568      0.708542   \n",
       "3      -0.868669      -0.933638    -0.775306      2.301137      0.205558   \n",
       "4      -0.868669      -0.933638    -0.775306      2.301137     -0.297426   \n",
       "...          ...            ...          ...           ...           ...   \n",
       "354360 -0.868669      -0.933638    -0.775306      2.301137      0.004365   \n",
       "354361  1.151186      -0.933638     1.289813     -0.434568      0.406752   \n",
       "354362 -0.868669       1.071079    -0.775306     -0.434568     -0.096232   \n",
       "354363  1.151186      -0.933638     1.289813     -0.434568     -0.398023   \n",
       "354364 -0.868669      -0.933638     1.289813     -0.434568      0.004365   \n",
       "\n",
       "        nb_campaigns_opened  \n",
       "0                  0.522567  \n",
       "1                  1.701843  \n",
       "2                 -0.420854  \n",
       "3                 -0.420854  \n",
       "4                 -0.420854  \n",
       "...                     ...  \n",
       "354360            -0.420854  \n",
       "354361             0.050856  \n",
       "354362             0.994277  \n",
       "354363            -0.420854  \n",
       "354364            -0.420854  \n",
       "\n",
       "[354365 rows x 17 columns]"
      ]
     },
     "execution_count": 128,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 122,
   "id": "23d6c06c-8708-4714-906b-a1ed664377bb",
   "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>const</th>\n",
       "      <th>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.004316</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0.607945</td>\n",
       "      <td>0.522567</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.306155</td>\n",
       "      <td>1.701843</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.004316</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.708542</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.205558</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.297426</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0.004365</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.406752</td>\n",
       "      <td>0.050856</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.000838</td>\n",
       "      <td>0.092966</td>\n",
       "      <td>-0.009150</td>\n",
       "      <td>1.219633</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>-1.665887</td>\n",
       "      <td>-1.557073</td>\n",
       "      <td>-0.175269</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>0.069949</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.096232</td>\n",
       "      <td>0.994277</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.012631</td>\n",
       "      <td>0.021122</td>\n",
       "      <td>-0.005227</td>\n",
       "      <td>1.219633</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>-1.871668</td>\n",
       "      <td>-1.755983</td>\n",
       "      <td>-0.175269</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.004316</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>-0.398023</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.024425</td>\n",
       "      <td>-0.050722</td>\n",
       "      <td>-0.048383</td>\n",
       "      <td>-0.768294</td>\n",
       "      <td>-0.599511</td>\n",
       "      <td>0.755994</td>\n",
       "      <td>0.783940</td>\n",
       "      <td>-0.192978</td>\n",
       "      <td>-0.264693</td>\n",
       "      <td>-0.029071</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0.004365</td>\n",
       "      <td>-0.420854</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        const  nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0         1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "1         1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "2         1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "3         1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "4         1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "...       ...         ...           ...           ...           ...   \n",
       "354360    1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "354361    1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "354362    1.0   -0.000838      0.092966     -0.009150      1.219633   \n",
       "354363    1.0   -0.012631      0.021122     -0.005227      1.219633   \n",
       "354364    1.0   -0.024425     -0.050722     -0.048383     -0.768294   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                -0.599511           0.755994           0.783940   \n",
       "1                -0.599511           0.755994           0.783940   \n",
       "2                -0.599511           0.755994           0.783940   \n",
       "3                -0.599511           0.755994           0.783940   \n",
       "4                -0.599511           0.755994           0.783940   \n",
       "...                    ...                ...                ...   \n",
       "354360           -0.599511           0.755994           0.783940   \n",
       "354361           -0.599511           0.755994           0.783940   \n",
       "354362           -0.599511          -1.665887          -1.557073   \n",
       "354363           -0.599511          -1.871668          -1.755983   \n",
       "354364           -0.599511           0.755994           0.783940   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                   -0.192978            -0.264693 -0.004316              1   \n",
       "1                   -0.192978            -0.264693 -0.029071              1   \n",
       "2                   -0.192978            -0.264693 -0.004316              1   \n",
       "3                   -0.192978            -0.264693 -0.029071              1   \n",
       "4                   -0.192978            -0.264693 -0.029071              1   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354360              -0.192978            -0.264693 -0.029071              1   \n",
       "354361              -0.192978            -0.264693 -0.029071              1   \n",
       "354362              -0.175269            -0.264693  0.069949              1   \n",
       "354363              -0.175269            -0.264693 -0.004316              1   \n",
       "354364              -0.192978            -0.264693 -0.029071              1   \n",
       "\n",
       "        opt_in  gender_female  gender_male  nb_campaigns  nb_campaigns_opened  \n",
       "0            1              1            0      0.607945             0.522567  \n",
       "1            1              0            0      0.306155             1.701843  \n",
       "2            1              0            1      0.708542            -0.420854  \n",
       "3            0              0            0      0.205558            -0.420854  \n",
       "4            0              0            0     -0.297426            -0.420854  \n",
       "...        ...            ...          ...           ...                  ...  \n",
       "354360       0              0            0      0.004365            -0.420854  \n",
       "354361       1              0            1      0.406752             0.050856  \n",
       "354362       0              1            0     -0.096232             0.994277  \n",
       "354363       1              0            1     -0.398023            -0.420854  \n",
       "354364       0              0            1      0.004365            -0.420854  \n",
       "\n",
       "[354365 rows x 17 columns]"
      ]
     },
     "execution_count": 122,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 133,
   "id": "0e968aa1-fbec-47db-b570-4730ef7eebf2",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/mamba/lib/python3.11/site-packages/statsmodels/discrete/discrete_model.py:2385: RuntimeWarning: overflow encountered in exp\n",
      "  return 1/(1+np.exp(-X))\n",
      "/opt/mamba/lib/python3.11/site-packages/statsmodels/discrete/discrete_model.py:2443: RuntimeWarning: divide by zero encountered in log\n",
      "  return np.sum(np.log(self.cdf(q * linpred)))\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Warning: Maximum number of iterations has been exceeded.\n",
      "         Current function value: inf\n",
      "         Iterations: 35\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/mamba/lib/python3.11/site-packages/statsmodels/base/model.py:607: ConvergenceWarning: Maximum Likelihood optimization failed to converge. Check mle_retvals\n",
      "  warnings.warn(\"Maximum Likelihood optimization failed to \"\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                           Logit Regression Results                           \n",
      "==============================================================================\n",
      "Dep. Variable:                      y   No. Observations:               354365\n",
      "Model:                          Logit   Df Residuals:                   354349\n",
      "Method:                           MLE   Df Model:                           15\n",
      "Date:                Thu, 14 Mar 2024   Pseudo R-squ.:                    -inf\n",
      "Time:                        10:47:16   Log-Likelihood:                   -inf\n",
      "converged:                      False   LL-Null:                   -1.0540e+05\n",
      "Covariance Type:            nonrobust   LLR p-value:                     1.000\n",
      "=========================================================================================\n",
      "                            coef    std err          z      P>|z|      [0.025      0.975]\n",
      "-----------------------------------------------------------------------------------------\n",
      "nb_tickets                4.9213      0.267     18.448      0.000       4.398       5.444\n",
      "nb_purchases             -7.9446      0.140    -56.905      0.000      -8.218      -7.671\n",
      "total_amount              0.3039      0.061      4.945      0.000       0.183       0.424\n",
      "nb_suppliers              0.1067      0.008     13.678      0.000       0.091       0.122\n",
      "vente_internet_max       -0.2784      0.008    -34.612      0.000      -0.294      -0.263\n",
      "purchase_date_min       -41.9693      2.640    -15.895      0.000     -47.144     -36.794\n",
      "purchase_date_max        43.2793      2.734     15.829      0.000      37.920      48.638\n",
      "time_between_purchase    12.7237      0.789     16.132      0.000      11.178      14.270\n",
      "nb_tickets_internet      -0.0212      0.014     -1.510      0.131      -0.049       0.006\n",
      "fidelity                 22.0749      0.222     99.561      0.000      21.640      22.509\n",
      "is_email_true             0.0225      0.004      6.145      0.000       0.015       0.030\n",
      "opt_in                   -0.1245      0.004    -30.646      0.000      -0.133      -0.117\n",
      "gender_female             0.0018        nan        nan        nan         nan         nan\n",
      "gender_male               0.0118        nan        nan        nan         nan         nan\n",
      "gender_other             -0.0182        nan        nan        nan         nan         nan\n",
      "nb_campaigns             -0.0049      0.005     -0.961      0.336      -0.015       0.005\n",
      "nb_campaigns_opened       0.0867      0.005     18.211      0.000       0.077       0.096\n",
      "=========================================================================================\n"
     ]
    }
   ],
   "source": [
    "# Création du modèle de régression logistique avec poids équilibrés\n",
    "# model_logit = sm.Logit(y, X, weights=weights)\n",
    "model_logit = sm.Logit(y, X)\n",
    "\n",
    "# Ajustement du modèle aux données\n",
    "result = model_logit.fit()\n",
    "\n",
    "# Affichage des résultats\n",
    "print(result.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 130,
   "id": "d1660ef9-438f-4427-ac2d-aa8179614e40",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([ 1.07107945, -0.93363755])"
      ]
     },
     "execution_count": 130,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X[\"gender_female\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 131,
   "id": "2079bae6-bce3-4de7-bf49-180177c31a55",
   "metadata": {},
   "outputs": [],
   "source": [
    "numeric_features = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', \n",
    "            'time_between_purchase', 'nb_tickets_internet', 'fidelity',  'is_email_true', 'opt_in', #'is_partner',\n",
    "            'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']\n",
    "\n",
    "numeric_transformer = Pipeline(steps=[\n",
    "    #(\"imputer\", SimpleImputer(strategy=\"mean\")),  \n",
    "    (\"scaler\", StandardScaler()) \n",
    "])\n",
    "\n",
    "categorical_features = ['opt_in']  \n",
    "\n",
    "# Transformer for the categorical features\n",
    "categorical_transformer = Pipeline(steps=[\n",
    "    #(\"imputer\", SimpleImputer(strategy=\"most_frequent\")),  # Impute missing values with the most frequent\n",
    "    (\"onehot\", OneHotEncoder(handle_unknown='ignore', sparse_output=False))\n",
    "])\n",
    "\n",
    "preproc = ColumnTransformer(\n",
    "    transformers=[\n",
    "        (\"num\", numeric_transformer, numeric_features),\n",
    "        (\"cat\", categorical_transformer, categorical_features)\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "id": "a9fe1c60-0732-426f-b176-9c95718e546f",
   "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>const</th>\n",
       "      <th>gender_other</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>1.0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        const  gender_other\n",
       "0         1.0             0\n",
       "1         1.0             1\n",
       "2         1.0             0\n",
       "3         1.0             1\n",
       "4         1.0             1\n",
       "...       ...           ...\n",
       "354360    1.0             1\n",
       "354361    1.0             0\n",
       "354362    1.0             0\n",
       "354363    1.0             0\n",
       "354364    1.0             0\n",
       "\n",
       "[354365 rows x 2 columns]"
      ]
     },
     "execution_count": 105,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sm.add_constant(X[\"gender_other\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "id": "b8c92b7c-1df0-4384-82e7-1e8cc0d333fa",
   "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>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>11</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>91</td>\n",
       "      <td>91</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>55</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 16 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0                0             0             0             0   \n",
       "1                0             0             0             0   \n",
       "2                0             0             0             0   \n",
       "3                0             0             0             0   \n",
       "4                0             0             0             0   \n",
       "...            ...           ...           ...           ...   \n",
       "354360           0             0             0             0   \n",
       "354361           0             0             0             0   \n",
       "354362           2             2            50             1   \n",
       "354363           1             1            55             1   \n",
       "354364           0             0             0             0   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                        0                550                550   \n",
       "1                        0                550                550   \n",
       "2                        0                550                550   \n",
       "3                        0                550                550   \n",
       "4                        0                550                550   \n",
       "...                    ...                ...                ...   \n",
       "354360                   0                550                550   \n",
       "354361                   0                550                550   \n",
       "354362                   0                 91                 91   \n",
       "354363                   0                 52                 52   \n",
       "354364                   0                550                550   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                          -1                    0         1              1   \n",
       "1                          -1                    0         0              1   \n",
       "2                          -1                    0         1              1   \n",
       "3                          -1                    0         0              1   \n",
       "4                          -1                    0         0              1   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354360                     -1                    0         0              1   \n",
       "354361                     -1                    0         0              1   \n",
       "354362                      0                    0         4              1   \n",
       "354363                      0                    0         1              1   \n",
       "354364                     -1                    0         0              1   \n",
       "\n",
       "        opt_in  gender_female  gender_male  nb_campaigns  nb_campaigns_opened  \n",
       "0            1              1            0            13                    4  \n",
       "1            1              0            0            10                    9  \n",
       "2            1              0            1            14                    0  \n",
       "3            0              0            0             9                    0  \n",
       "4            0              0            0             4                    0  \n",
       "...        ...            ...          ...           ...                  ...  \n",
       "354360       0              0            0             7                    0  \n",
       "354361       1              0            1            11                    2  \n",
       "354362       0              1            0             6                    6  \n",
       "354363       1              0            1             3                    0  \n",
       "354364       0              0            1             7                    0  \n",
       "\n",
       "[354365 rows x 16 columns]"
      ]
     },
     "execution_count": 106,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.drop(\"gender_other\", axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "061dcabd-383d-4b76-a9f0-8647daed2c9e",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "id": "fc4ffbf6-ab7e-47cf-a717-c25477d92493",
   "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>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>gender_other</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>14</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>11</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>91</td>\n",
       "      <td>91</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>55</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>52</td>\n",
       "      <td>52</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>550</td>\n",
       "      <td>550</td>\n",
       "      <td>-1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0                0             0             0             0   \n",
       "1                0             0             0             0   \n",
       "2                0             0             0             0   \n",
       "3                0             0             0             0   \n",
       "4                0             0             0             0   \n",
       "...            ...           ...           ...           ...   \n",
       "354360           0             0             0             0   \n",
       "354361           0             0             0             0   \n",
       "354362           2             2            50             1   \n",
       "354363           1             1            55             1   \n",
       "354364           0             0             0             0   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                        0                550                550   \n",
       "1                        0                550                550   \n",
       "2                        0                550                550   \n",
       "3                        0                550                550   \n",
       "4                        0                550                550   \n",
       "...                    ...                ...                ...   \n",
       "354360                   0                550                550   \n",
       "354361                   0                550                550   \n",
       "354362                   0                 91                 91   \n",
       "354363                   0                 52                 52   \n",
       "354364                   0                550                550   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                          -1                    0         1              1   \n",
       "1                          -1                    0         0              1   \n",
       "2                          -1                    0         1              1   \n",
       "3                          -1                    0         0              1   \n",
       "4                          -1                    0         0              1   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354360                     -1                    0         0              1   \n",
       "354361                     -1                    0         0              1   \n",
       "354362                      0                    0         4              1   \n",
       "354363                      0                    0         1              1   \n",
       "354364                     -1                    0         0              1   \n",
       "\n",
       "        opt_in  gender_female  gender_male  gender_other  nb_campaigns  \\\n",
       "0            1              1            0             0            13   \n",
       "1            1              0            0             1            10   \n",
       "2            1              0            1             0            14   \n",
       "3            0              0            0             1             9   \n",
       "4            0              0            0             1             4   \n",
       "...        ...            ...          ...           ...           ...   \n",
       "354360       0              0            0             1             7   \n",
       "354361       1              0            1             0            11   \n",
       "354362       0              1            0             0             6   \n",
       "354363       1              0            1             0             3   \n",
       "354364       0              0            1             0             7   \n",
       "\n",
       "        nb_campaigns_opened  \n",
       "0                         4  \n",
       "1                         9  \n",
       "2                         0  \n",
       "3                         0  \n",
       "4                         0  \n",
       "...                     ...  \n",
       "354360                    0  \n",
       "354361                    2  \n",
       "354362                    6  \n",
       "354363                    0  \n",
       "354364                    0  \n",
       "\n",
       "[354365 rows x 17 columns]"
      ]
     },
     "execution_count": 107,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "id": "f15b0d69-8470-4a36-bd25-9536a36c4756",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(354365,)"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weights.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "id": "e97e26f6-b854-41e3-bbdf-318065b03254",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(354365, 17)"
      ]
     },
     "execution_count": 74,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "id": "49621874-1e8c-4cb5-84a9-a5c9715f3b06",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(354365,)"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "id": "8072cd81-d63f-430e-b0b2-c0589cf18871",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "nb_tickets               0\n",
       "nb_purchases             0\n",
       "total_amount             0\n",
       "nb_suppliers             0\n",
       "vente_internet_max       0\n",
       "purchase_date_min        0\n",
       "purchase_date_max        0\n",
       "time_between_purchase    0\n",
       "nb_tickets_internet      0\n",
       "fidelity                 0\n",
       "is_email_true            0\n",
       "opt_in                   0\n",
       "gender_female            0\n",
       "gender_male              0\n",
       "gender_other             0\n",
       "nb_campaigns             0\n",
       "nb_campaigns_opened      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "id": "6f07a66f-5a46-4409-b0b6-ff5e212296f0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0., 1.])"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_train[\"y_has_purchased\"].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "id": "4587c36f-94bf-458b-b819-60250eb17c59",
   "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>nb_tickets</th>\n",
       "      <th>nb_purchases</th>\n",
       "      <th>total_amount</th>\n",
       "      <th>nb_suppliers</th>\n",
       "      <th>vente_internet_max</th>\n",
       "      <th>purchase_date_min</th>\n",
       "      <th>purchase_date_max</th>\n",
       "      <th>time_between_purchase</th>\n",
       "      <th>nb_tickets_internet</th>\n",
       "      <th>fidelity</th>\n",
       "      <th>is_email_true</th>\n",
       "      <th>opt_in</th>\n",
       "      <th>gender_female</th>\n",
       "      <th>gender_male</th>\n",
       "      <th>gender_other</th>\n",
       "      <th>nb_campaigns</th>\n",
       "      <th>nb_campaigns_opened</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>13.0</td>\n",
       "      <td>4.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>10.0</td>\n",
       "      <td>9.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>14.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>9.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>4.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354360</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354361</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>11.0</td>\n",
       "      <td>2.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354362</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2.0</td>\n",
       "      <td>50.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>91.030556</td>\n",
       "      <td>91.020139</td>\n",
       "      <td>0.010417</td>\n",
       "      <td>0.0</td>\n",
       "      <td>4</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>6.0</td>\n",
       "      <td>6.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354363</th>\n",
       "      <td>1.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>55.0</td>\n",
       "      <td>1.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>52.284028</td>\n",
       "      <td>52.284028</td>\n",
       "      <td>0.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>1</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>3.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>354364</th>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0.0</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>550.000000</td>\n",
       "      <td>-1.000000</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>7.0</td>\n",
       "      <td>0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>354365 rows × 17 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        nb_tickets  nb_purchases  total_amount  nb_suppliers  \\\n",
       "0              0.0           0.0           0.0           0.0   \n",
       "1              0.0           0.0           0.0           0.0   \n",
       "2              0.0           0.0           0.0           0.0   \n",
       "3              0.0           0.0           0.0           0.0   \n",
       "4              0.0           0.0           0.0           0.0   \n",
       "...            ...           ...           ...           ...   \n",
       "354360         0.0           0.0           0.0           0.0   \n",
       "354361         0.0           0.0           0.0           0.0   \n",
       "354362         2.0           2.0          50.0           1.0   \n",
       "354363         1.0           1.0          55.0           1.0   \n",
       "354364         0.0           0.0           0.0           0.0   \n",
       "\n",
       "        vente_internet_max  purchase_date_min  purchase_date_max  \\\n",
       "0                      0.0         550.000000         550.000000   \n",
       "1                      0.0         550.000000         550.000000   \n",
       "2                      0.0         550.000000         550.000000   \n",
       "3                      0.0         550.000000         550.000000   \n",
       "4                      0.0         550.000000         550.000000   \n",
       "...                    ...                ...                ...   \n",
       "354360                 0.0         550.000000         550.000000   \n",
       "354361                 0.0         550.000000         550.000000   \n",
       "354362                 0.0          91.030556          91.020139   \n",
       "354363                 0.0          52.284028          52.284028   \n",
       "354364                 0.0         550.000000         550.000000   \n",
       "\n",
       "        time_between_purchase  nb_tickets_internet  fidelity  is_email_true  \\\n",
       "0                   -1.000000                  0.0         1           True   \n",
       "1                   -1.000000                  0.0         0           True   \n",
       "2                   -1.000000                  0.0         1           True   \n",
       "3                   -1.000000                  0.0         0           True   \n",
       "4                   -1.000000                  0.0         0           True   \n",
       "...                       ...                  ...       ...            ...   \n",
       "354360              -1.000000                  0.0         0           True   \n",
       "354361              -1.000000                  0.0         0           True   \n",
       "354362               0.010417                  0.0         4           True   \n",
       "354363               0.000000                  0.0         1           True   \n",
       "354364              -1.000000                  0.0         0           True   \n",
       "\n",
       "        opt_in  gender_female  gender_male  gender_other  nb_campaigns  \\\n",
       "0         True              1            0             0          13.0   \n",
       "1         True              0            0             1          10.0   \n",
       "2         True              0            1             0          14.0   \n",
       "3        False              0            0             1           9.0   \n",
       "4        False              0            0             1           4.0   \n",
       "...        ...            ...          ...           ...           ...   \n",
       "354360   False              0            0             1           7.0   \n",
       "354361    True              0            1             0          11.0   \n",
       "354362   False              1            0             0           6.0   \n",
       "354363    True              0            1             0           3.0   \n",
       "354364   False              0            1             0           7.0   \n",
       "\n",
       "        nb_campaigns_opened  \n",
       "0                       4.0  \n",
       "1                       9.0  \n",
       "2                       0.0  \n",
       "3                       0.0  \n",
       "4                       0.0  \n",
       "...                     ...  \n",
       "354360                  0.0  \n",
       "354361                  2.0  \n",
       "354362                  6.0  \n",
       "354363                  0.0  \n",
       "354364                  0.0  \n",
       "\n",
       "[354365 rows x 17 columns]"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X_train"
   ]
  }
 ],
 "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}