BDC-team-1/2_Regression_logistique.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "ac01a6ea-bef6-4ace-89ff-1dc03a4215c2",
   "metadata": {},
   "source": [
    "# Segmentation des clients par régression logistique"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "bca785be-39f7-4583-9bd8-67c1134ae275",
   "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.metrics import accuracy_score, confusion_matrix, classification_report\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "59ce5096-4e2c-45c1-be78-43e14db4142c",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # modification des variables categorielles\n",
    " \n",
    "# ### variable gender\n",
    "# df1_customer_product[\"gender_label\"] = df1_customer_product[\"gender\"].map({\n",
    "#     0: 'female',\n",
    "#     1: 'male',\n",
    "#     2: 'other'\n",
    "# })\n",
    " \n",
    "# ### variable country -> on indique si le pays est france\n",
    "# df1_customer_product[\"country_fr\"] = df1_customer_product[\"country\"].apply(lambda x : int(x==\"fr\") if pd.notna(x) else np.nan)\n",
    "\n",
    "# # Création des indicatrices de gender\n",
    "# gender_dummies = pd.get_dummies(df1_customer_product[\"gender_label\"], prefix='gender').astype(int)\n",
    " \n",
    "# # Concaténation des indicatrices avec le dataframe d'origine\n",
    "# df1_customer_product = pd.concat([df1_customer_product, gender_dummies], axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3bf57816-b023-4e84-9450-095620bddebc",
   "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": 4,
   "id": "27002f2f-a78a-414c-8e4f-b15bf6dd9e40",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_7388/1677066092.py:7: DtypeWarning: Columns (21,39) 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_7388/1677066092.py:12: DtypeWarning: Columns (21,39) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  dataset_test = pd.read_csv(file_in, sep=\",\")\n"
     ]
    }
   ],
   "source": [
    "# Importation des données\n",
    "BUCKET = \"projet-bdc2324-team1/1_Output/Logistique Regression databases - First approach\"\n",
    "\n",
    "FILE_PATH_S3 = BUCKET + \"/\" + \"dataset_train.csv\"\n",
    "\n",
    "with fs.open(FILE_PATH_S3, mode=\"rb\") as file_in:\n",
    "    dataset_train = pd.read_csv(file_in, sep=\",\")\n",
    "\n",
    "FILE_PATH_S3 = BUCKET + \"/\" + \"dataset_test.csv\"\n",
    "\n",
    "with fs.open(FILE_PATH_S3, mode=\"rb\") as file_in:\n",
    "    dataset_test = pd.read_csv(file_in, sep=\",\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c3928b55-8821-46da-b3b5-a036efd6d2cf",
   "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>event_type_id</th>\n",
       "      <th>name_event_types</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2.0</td>\n",
       "      <td>offre muséale individuel</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4.0</td>\n",
       "      <td>spectacle vivant</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5.0</td>\n",
       "      <td>offre muséale groupe</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   event_type_id          name_event_types\n",
       "0            2.0  offre muséale individuel\n",
       "1            4.0          spectacle vivant\n",
       "2            5.0      offre muséale groupe\n",
       "3            NaN                       NaN"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset_train[['event_type_id', 'name_event_types']].drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7e8a9d4d-7e55-4173-a7f4-8b8baa9610d2",
   "metadata": {},
   "outputs": [],
   "source": [
    "#Choose type of event \n",
    "type_event_choosed = 5\n",
    "\n",
    "dataset_test = dataset_test[(dataset_test['event_type_id'] == type_event_choosed) | np.isnan(dataset_test['event_type_id'])]\n",
    "dataset_test['y_has_purchased'] = dataset_test['y_has_purchased'].fillna(0)\n",
    "dataset_train = dataset_train[(dataset_train['event_type_id'] == type_event_choosed) | np.isnan(dataset_train['event_type_id'])]\n",
    "dataset_train['y_has_purchased'] = dataset_train['y_has_purchased'].fillna(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "e20ced8f-df1c-43bb-8d15-79f414c8225c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "customer_id               0.000000\n",
       "event_type_id             0.984075\n",
       "nb_tickets                0.000000\n",
       "nb_purchases              0.000000\n",
       "total_amount              0.000000\n",
       "nb_suppliers              0.000000\n",
       "vente_internet_max        0.000000\n",
       "purchase_date_min         0.984075\n",
       "purchase_date_max         0.984075\n",
       "time_between_purchase     0.984075\n",
       "nb_tickets_internet       0.000000\n",
       "name_event_types          0.984075\n",
       "avg_amount                0.984075\n",
       "birthdate                 0.961026\n",
       "street_id                 0.000000\n",
       "is_partner                0.000000\n",
       "gender                    0.000000\n",
       "is_email_true             0.000000\n",
       "opt_in                    0.000000\n",
       "structure_id              0.869302\n",
       "profession                0.950730\n",
       "language                  0.991512\n",
       "mcp_contact_id            0.276103\n",
       "last_buying_date          0.633303\n",
       "max_price                 0.633303\n",
       "ticket_sum                0.000000\n",
       "average_price             0.105825\n",
       "fidelity                  0.000000\n",
       "average_purchase_delay    0.633303\n",
       "average_price_basket      0.633303\n",
       "average_ticket_basket     0.633303\n",
       "total_price               0.527478\n",
       "purchase_count            0.000000\n",
       "first_buying_date         0.633303\n",
       "country                   0.065583\n",
       "age                       0.961026\n",
       "tenant_id                 0.000000\n",
       "nb_campaigns              0.000000\n",
       "nb_campaigns_opened       0.000000\n",
       "time_to_open              0.536466\n",
       "y_has_purchased           0.000000\n",
       "dtype: float64"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset_train.isna().sum()/len(dataset_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "34bae3f7-d579-4f80-a38d-a83eb5ea8a7b",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy: 0.9999434695179565\n",
      "Confusion Matrix:\n",
      " [[123819      0]\n",
      " [     7      1]]\n",
      "Classification Report:\n",
      "               precision    recall  f1-score   support\n",
      "\n",
      "         0.0       1.00      1.00      1.00    123819\n",
      "         1.0       1.00      0.12      0.22         8\n",
      "\n",
      "    accuracy                           1.00    123827\n",
      "   macro avg       1.00      0.56      0.61    123827\n",
      "weighted avg       1.00      1.00      1.00    123827\n",
      "\n"
     ]
    }
   ],
   "source": [
    "\n",
    "reg_columns = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'nb_tickets_internet', 'opt_in', 'fidelity', 'nb_campaigns', 'nb_campaigns_opened']\n",
    "\n",
    "X_train = dataset_train[reg_columns]\n",
    "y_train = dataset_train['y_has_purchased']\n",
    "X_test = dataset_test[reg_columns]\n",
    "y_test = dataset_test['y_has_purchased']\n",
    "\n",
    "# Fit and transform the scaler on the training data\n",
    "scaler = StandardScaler()\n",
    "\n",
    "# Transform the test data using the same scaler\n",
    "X_train_scaled = scaler.fit_transform(X_train)\n",
    "X_test_scaled = scaler.fit_transform(X_test)\n",
    "\n",
    "# Create and fit the linear regression model\n",
    "logit_model = LogisticRegression(penalty='l1', solver='liblinear', C=1.0)\n",
    "logit_model.fit(X_train_scaled, y_train)\n",
    "\n",
    "y_pred = logit_model.predict(X_test_scaled)\n",
    "\n",
    "#Evaluation du modèle \n",
    "accuracy = accuracy_score(y_test, y_pred)\n",
    "conf_matrix = confusion_matrix(y_test, y_pred)\n",
    "class_report = classification_report(y_test, y_pred)\n",
    "\n",
    "print(\"Accuracy:\", accuracy)\n",
    "print(\"Confusion Matrix:\\n\", conf_matrix)\n",
    "print(\"Classification Report:\\n\", class_report)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "ccc78c36-3287-46e6-89ac-7494c1a7106a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=['Class 0', 'Class 1'], yticklabels=['Class 0', 'Class 1'])\n",
    "plt.xlabel('Predicted')\n",
    "plt.ylabel('Actual')\n",
    "plt.title('Confusion Matrix')\n",
    "plt.show()"
   ]
  }
 ],
 "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
}