push coefficient
This commit is contained in:
parent
b9aa0d7578
commit
09f4bd3fe4
436
useless/Computes_log_coeff.ipynb
Normal file
436
useless/Computes_log_coeff.ipynb
Normal file
|
|
@ -0,0 +1,436 @@
|
||||||
|
{
|
||||||
|
"cells": [
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 1,
|
||||||
|
"id": "135a67de-cff8-4345-bacc-d9f9fa68a41f",
|
||||||
|
"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": "9a6254df-d496-4957-89ea-9ed2b74049dd",
|
||||||
|
"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": 5,
|
||||||
|
"id": "922cf05f-8343-4ed0-ad62-3ef1f17c0730",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"def load_train_test():\n",
|
||||||
|
" BUCKET = \"projet-bdc2324-team1/1_Temp/1_0_Modelling_Datasets/musee\"\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\n",
|
||||||
|
"\n",
|
||||||
|
"\n",
|
||||||
|
"def features_target_split(dataset_train, dataset_test):\n",
|
||||||
|
" features_l = ['nb_campaigns', 'taux_ouverture_mail', 'prop_purchases_internet', 'nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'time_to_open',\n",
|
||||||
|
" 'purchases_10_2021','purchases_10_2022', 'purchases_11_2021', 'purchases_12_2021','purchases_1_2022', 'purchases_2_2022', 'purchases_3_2022',\n",
|
||||||
|
" 'purchases_4_2022', 'purchases_5_2021', 'purchases_5_2022', 'purchases_6_2021', 'purchases_6_2022', 'purchases_7_2021', 'purchases_7_2022', 'purchases_8_2021',\n",
|
||||||
|
" 'purchases_8_2022','purchases_9_2021', 'purchases_9_2022', 'purchase_date_min', 'purchase_date_max', 'nb_targets', 'gender_female', 'gender_male',\n",
|
||||||
|
" 'achat_internet', 'categorie_age_0_10', 'categorie_age_10_20', 'categorie_age_20_30','categorie_age_30_40',\n",
|
||||||
|
" 'categorie_age_40_50', 'categorie_age_50_60', 'categorie_age_60_70', 'categorie_age_70_80', 'categorie_age_plus_80','categorie_age_inconnue',\n",
|
||||||
|
" 'country_fr', 'is_profession_known', 'is_zipcode_known', 'opt_in', 'target_optin', 'target_newsletter', 'target_scolaire', 'target_entreprise', 'target_famille',\n",
|
||||||
|
" 'target_jeune', 'target_abonne']\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": 6,
|
||||||
|
"id": "2584e454-111b-4c39-881b-676841cb5aa1",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stderr",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"/tmp/ipykernel_498/3950829189.py:7: DtypeWarning: Columns (10,24,25) 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_498/3950829189.py:11: DtypeWarning: Columns (10,24,25) 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": 7,
|
||||||
|
"id": "a32ea7f8-e2d3-44db-8937-5afda9447b58",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"X_train, X_test, y_train, y_test = features_target_split(dataset_train, dataset_test)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 22,
|
||||||
|
"id": "3bdc8840-7f45-416f-8ee0-307db201c496",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"const 0\n",
|
||||||
|
"nb_campaigns 0\n",
|
||||||
|
"taux_ouverture_mail 0\n",
|
||||||
|
"prop_purchases_internet 0\n",
|
||||||
|
"nb_tickets 0\n",
|
||||||
|
"nb_purchases 0\n",
|
||||||
|
"total_amount 0\n",
|
||||||
|
"nb_suppliers 0\n",
|
||||||
|
"time_to_open 0\n",
|
||||||
|
"purchases_10_2021 0\n",
|
||||||
|
"purchases_10_2022 0\n",
|
||||||
|
"purchases_11_2021 0\n",
|
||||||
|
"purchases_12_2021 0\n",
|
||||||
|
"purchases_1_2022 0\n",
|
||||||
|
"purchases_2_2022 0\n",
|
||||||
|
"purchases_3_2022 0\n",
|
||||||
|
"purchases_4_2022 0\n",
|
||||||
|
"purchases_5_2021 0\n",
|
||||||
|
"purchases_5_2022 0\n",
|
||||||
|
"purchases_6_2021 0\n",
|
||||||
|
"purchases_6_2022 0\n",
|
||||||
|
"purchases_7_2021 0\n",
|
||||||
|
"purchases_7_2022 0\n",
|
||||||
|
"purchases_8_2021 0\n",
|
||||||
|
"purchases_8_2022 0\n",
|
||||||
|
"purchases_9_2021 0\n",
|
||||||
|
"purchases_9_2022 0\n",
|
||||||
|
"purchase_date_min 0\n",
|
||||||
|
"purchase_date_max 0\n",
|
||||||
|
"nb_targets 0\n",
|
||||||
|
"gender_female 0\n",
|
||||||
|
"gender_male 0\n",
|
||||||
|
"achat_internet 0\n",
|
||||||
|
"categorie_age_0_10 0\n",
|
||||||
|
"categorie_age_10_20 0\n",
|
||||||
|
"categorie_age_20_30 0\n",
|
||||||
|
"categorie_age_30_40 0\n",
|
||||||
|
"categorie_age_40_50 0\n",
|
||||||
|
"categorie_age_50_60 0\n",
|
||||||
|
"categorie_age_60_70 0\n",
|
||||||
|
"categorie_age_70_80 0\n",
|
||||||
|
"categorie_age_plus_80 0\n",
|
||||||
|
"categorie_age_inconnue 0\n",
|
||||||
|
"country_fr 0\n",
|
||||||
|
"is_profession_known 0\n",
|
||||||
|
"is_zipcode_known 0\n",
|
||||||
|
"opt_in 0\n",
|
||||||
|
"target_optin 0\n",
|
||||||
|
"target_newsletter 0\n",
|
||||||
|
"target_scolaire 0\n",
|
||||||
|
"target_entreprise 0\n",
|
||||||
|
"target_famille 0\n",
|
||||||
|
"target_jeune 0\n",
|
||||||
|
"target_abonne 0\n",
|
||||||
|
"dtype: int64"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 22,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"X_train.isna().sum()"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 17,
|
||||||
|
"id": "3c3ac545-52e0-4d0c-afdc-fff70f468a94",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"1.0"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 17,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"most_frequent_value = X_train['country_fr'].mode()[0]\n",
|
||||||
|
"most_frequent_value"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 21,
|
||||||
|
"id": "0fcdc5ee-bcea-4436-be9b-92b79d27a230",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"X_train['country_fr'] = X_train['country_fr'].fillna(most_frequent_value)\n",
|
||||||
|
"X_train['time_to_open'] = X_train['time_to_open'].fillna(0)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 8,
|
||||||
|
"id": "7ecdaf1a-b5e4-4880-871e-363eae6fe4e1",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"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'])))}"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 9,
|
||||||
|
"id": "a6b56090-cfe9-4772-810c-d36bf12aceca",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"data": {
|
||||||
|
"text/plain": [
|
||||||
|
"array([0.52239696, 0.52239696, 0.52239696, ..., 0.52239696, 0.52239696,\n",
|
||||||
|
" 0.52239696])"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
"execution_count": 9,
|
||||||
|
"metadata": {},
|
||||||
|
"output_type": "execute_result"
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"\n",
|
||||||
|
"class_counts = np.bincount(y_train['y_has_purchased'])\n",
|
||||||
|
"class_weights = len(y_train['y_has_purchased']) / (2 * class_counts)\n",
|
||||||
|
"\n",
|
||||||
|
"weights = class_weights[y_train['y_has_purchased'].values.astype(int)]\n",
|
||||||
|
"weights"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 13,
|
||||||
|
"id": "bfaea23e-7d7a-4c0d-96f6-4ab4c7c2ff51",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"X_train = sm.add_constant(X_train)"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 26,
|
||||||
|
"id": "4cf97ae5-9dcf-4f4c-91b3-3b1f339a6213",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"numeric_features = ['nb_campaigns', 'taux_ouverture_mail', 'prop_purchases_internet', 'nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers',\n",
|
||||||
|
" 'purchases_10_2021','purchases_10_2022', 'purchases_11_2021', 'purchases_12_2021','purchases_1_2022', 'purchases_2_2022', 'purchases_3_2022',\n",
|
||||||
|
" 'purchases_4_2022', 'purchases_5_2021', 'purchases_5_2022', 'purchases_6_2021', 'purchases_6_2022', 'purchases_7_2021', 'purchases_7_2022', 'purchases_8_2021',\n",
|
||||||
|
" 'purchases_8_2022','purchases_9_2021', 'purchases_9_2022', 'purchase_date_min', 'purchase_date_max', 'nb_targets', 'time_to_open']"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 27,
|
||||||
|
"id": "debb36df-3c2f-4cf7-83a9-ad6e4f6b0470",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": [
|
||||||
|
"scaler = StandardScaler()\n",
|
||||||
|
"\n",
|
||||||
|
"X_train_scaled_columns = scaler.fit_transform(X_train[numeric_features])\n",
|
||||||
|
"\n",
|
||||||
|
"X_train_scaled = X_train.copy() #\n",
|
||||||
|
"X_train_scaled[numeric_features] = X_train_scaled_columns"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": 28,
|
||||||
|
"id": "7eaa6160-20a0-4a78-ac38-0411e19707ed",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [
|
||||||
|
{
|
||||||
|
"name": "stderr",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"/opt/mamba/lib/python3.11/site-packages/statsmodels/base/optimizer.py:18: FutureWarning: Keyword arguments have been passed to the optimizer that have no effect. The list of allowed keyword arguments for method newton is: tol, ridge_factor. The list of unsupported keyword arguments passed include: weights. After release 0.14, this will raise.\n",
|
||||||
|
" warnings.warn(\n"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"name": "stdout",
|
||||||
|
"output_type": "stream",
|
||||||
|
"text": [
|
||||||
|
"Optimization terminated successfully.\n",
|
||||||
|
" Current function value: 0.136180\n",
|
||||||
|
" Iterations 9\n",
|
||||||
|
" Logit Regression Results \n",
|
||||||
|
"==============================================================================\n",
|
||||||
|
"Dep. Variable: y_has_purchased No. Observations: 434278\n",
|
||||||
|
"Model: Logit Df Residuals: 434226\n",
|
||||||
|
"Method: MLE Df Model: 51\n",
|
||||||
|
"Date: Thu, 04 Apr 2024 Pseudo R-squ.: 0.2305\n",
|
||||||
|
"Time: 06:09:09 Log-Likelihood: -59140.\n",
|
||||||
|
"converged: True LL-Null: -76855.\n",
|
||||||
|
"Covariance Type: nonrobust LLR p-value: 0.000\n",
|
||||||
|
"===========================================================================================\n",
|
||||||
|
" coef std err z P>|z| [0.025 0.975]\n",
|
||||||
|
"-------------------------------------------------------------------------------------------\n",
|
||||||
|
"const -4.0679 1.65e+06 -2.46e-06 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"nb_campaigns 0.0916 0.012 7.352 0.000 0.067 0.116\n",
|
||||||
|
"taux_ouverture_mail 0.0012 0.011 0.106 0.916 -0.021 0.023\n",
|
||||||
|
"prop_purchases_internet -0.1995 0.067 -2.972 0.003 -0.331 -0.068\n",
|
||||||
|
"nb_tickets 0.5956 0.193 3.091 0.002 0.218 0.973\n",
|
||||||
|
"nb_purchases 0.1598 1.71e+06 9.37e-08 1.000 -3.34e+06 3.34e+06\n",
|
||||||
|
"total_amount -0.1938 0.071 -2.724 0.006 -0.333 -0.054\n",
|
||||||
|
"nb_suppliers 0.0282 0.021 1.348 0.178 -0.013 0.069\n",
|
||||||
|
"time_to_open 0.2785 0.018 15.534 0.000 0.243 0.314\n",
|
||||||
|
"purchases_10_2021 0.0417 4.76e+04 8.76e-07 1.000 -9.34e+04 9.34e+04\n",
|
||||||
|
"purchases_10_2022 0.4578 2.72e+05 1.68e-06 1.000 -5.33e+05 5.33e+05\n",
|
||||||
|
"purchases_11_2021 0.0252 4.92e+04 5.12e-07 1.000 -9.65e+04 9.65e+04\n",
|
||||||
|
"purchases_12_2021 0.0221 6.3e+04 3.5e-07 1.000 -1.24e+05 1.24e+05\n",
|
||||||
|
"purchases_1_2022 0.0083 5.49e+04 1.52e-07 1.000 -1.08e+05 1.08e+05\n",
|
||||||
|
"purchases_2_2022 0.0462 7.59e+04 6.09e-07 1.000 -1.49e+05 1.49e+05\n",
|
||||||
|
"purchases_3_2022 0.0928 1.07e+05 8.67e-07 1.000 -2.1e+05 2.1e+05\n",
|
||||||
|
"purchases_4_2022 0.1446 1.65e+05 8.75e-07 1.000 -3.24e+05 3.24e+05\n",
|
||||||
|
"purchases_5_2021 -0.0427 4.84e+04 -8.83e-07 1.000 -9.48e+04 9.48e+04\n",
|
||||||
|
"purchases_5_2022 0.1412 1.67e+05 8.46e-07 1.000 -3.27e+05 3.27e+05\n",
|
||||||
|
"purchases_6_2021 -0.0252 5.55e+04 -4.54e-07 1.000 -1.09e+05 1.09e+05\n",
|
||||||
|
"purchases_6_2022 0.1246 1.84e+05 6.77e-07 1.000 -3.6e+05 3.6e+05\n",
|
||||||
|
"purchases_7_2021 -0.0252 5.55e+04 -4.55e-07 1.000 -1.09e+05 1.09e+05\n",
|
||||||
|
"purchases_7_2022 -0.0074 2.1e+05 -3.54e-08 1.000 -4.12e+05 4.12e+05\n",
|
||||||
|
"purchases_8_2021 0.0116 5.26e+04 2.21e-07 1.000 -1.03e+05 1.03e+05\n",
|
||||||
|
"purchases_8_2022 0.0554 2.4e+05 2.31e-07 1.000 -4.7e+05 4.7e+05\n",
|
||||||
|
"purchases_9_2021 -0.0320 5.47e+04 -5.85e-07 1.000 -1.07e+05 1.07e+05\n",
|
||||||
|
"purchases_9_2022 0.2349 2.2e+05 1.07e-06 1.000 -4.32e+05 4.32e+05\n",
|
||||||
|
"purchase_date_min 0.0781 0.025 3.092 0.002 0.029 0.128\n",
|
||||||
|
"purchase_date_max -0.5228 0.026 -20.021 0.000 -0.574 -0.472\n",
|
||||||
|
"nb_targets 0.7083 0.010 74.555 0.000 0.690 0.727\n",
|
||||||
|
"gender_female 0.2961 0.038 7.701 0.000 0.221 0.371\n",
|
||||||
|
"gender_male 0.0450 0.040 1.137 0.256 -0.033 0.123\n",
|
||||||
|
"achat_internet 0.1869 0.158 1.186 0.236 -0.122 0.496\n",
|
||||||
|
"categorie_age_0_10 -0.2713 1.65e+06 -1.64e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_10_20 -0.1238 1.65e+06 -7.48e-08 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_20_30 -0.6322 1.65e+06 -3.82e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_30_40 -0.5004 1.65e+06 -3.02e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_40_50 -0.4020 1.65e+06 -2.43e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_50_60 -0.4101 1.65e+06 -2.48e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_60_70 -0.3232 1.65e+06 -1.95e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_70_80 -0.1635 1.65e+06 -9.88e-08 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_plus_80 -0.4677 1.65e+06 -2.83e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"categorie_age_inconnue -0.7737 1.65e+06 -4.68e-07 1.000 -3.24e+06 3.24e+06\n",
|
||||||
|
"country_fr 0.7419 0.065 11.422 0.000 0.615 0.869\n",
|
||||||
|
"is_profession_known -0.5947 0.066 -9.074 0.000 -0.723 -0.466\n",
|
||||||
|
"is_zipcode_known 1.1374 0.027 41.609 0.000 1.084 1.191\n",
|
||||||
|
"opt_in -1.0658 0.030 -35.485 0.000 -1.125 -1.007\n",
|
||||||
|
"target_optin 0.5946 0.034 17.361 0.000 0.527 0.662\n",
|
||||||
|
"target_newsletter -1.0237 0.035 -29.411 0.000 -1.092 -0.955\n",
|
||||||
|
"target_scolaire 0.0428 0.036 1.188 0.235 -0.028 0.113\n",
|
||||||
|
"target_entreprise -0.2645 0.058 -4.589 0.000 -0.377 -0.152\n",
|
||||||
|
"target_famille 0.5035 0.035 14.548 0.000 0.436 0.571\n",
|
||||||
|
"target_jeune -0.6795 0.029 -23.590 0.000 -0.736 -0.623\n",
|
||||||
|
"target_abonne 0.0677 0.037 1.833 0.067 -0.005 0.140\n",
|
||||||
|
"===========================================================================================\n"
|
||||||
|
]
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"source": [
|
||||||
|
"model_logit = sm.Logit(y_train, X_train_scaled)\n",
|
||||||
|
"\n",
|
||||||
|
"result = model_logit.fit(weights=weights)\n",
|
||||||
|
"\n",
|
||||||
|
"print(result.summary())"
|
||||||
|
]
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"cell_type": "code",
|
||||||
|
"execution_count": null,
|
||||||
|
"id": "75dc92c7-cc1e-40f1-bc74-0b04043b7e44",
|
||||||
|
"metadata": {},
|
||||||
|
"outputs": [],
|
||||||
|
"source": []
|
||||||
|
}
|
||||||
|
],
|
||||||
|
"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
|
||||||
|
}
|
||||||
Loading…
Reference in New Issue
Block a user