ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
acf7621d9a
BDC-team-1/Sport/Modelization/CA_segment_sport.ipynb

4227 lines
194 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "markdown",
"id": "84b6e27e-4bda-4d38-8689-ec7fc0da1848",
"metadata": {},
"source": [
"# Define segment and predict sales associated"
]
},
{
"cell_type": "markdown",
"id": "ec059482-45d3-4ae6-99bc-9b4ced115db3",
"metadata": {},
"source": [
"## Importations of packages "
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "9771bf29-d08e-4674-8c23-9a2672fbef8f",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"from pandas import DataFrame\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",
"from sklearn.naive_bayes import GaussianNB\n",
"from scipy.optimize import fsolve\n",
"import io\n",
"\n",
"import pickle\n",
"import warnings"
]
},
{
"cell_type": "markdown",
"id": "048fcd7c-800a-4a6b-b725-faf8410f924a",
"metadata": {},
"source": [
"## load databases"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "539ccbdf-f29f-4f04-99c1-8c88d0efe514",
"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": "d6017ed0-6233-4888-85a7-05dec50a255b",
"metadata": {},
"outputs": [],
"source": [
"type_of_activity = \"sport\""
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "0c3a6ddc-9345-4a42-b6bf-a20a95de3028",
"metadata": {},
"outputs": [],
"source": [
"def load_train_test(type_of_activity):\n",
" # BUCKET = f\"projet-bdc2324-team1/Generalization/{type_of_activity}\"\n",
" BUCKET = f\"projet-bdc2324-team1/1_Temp/1_0_Modelling_Datasets/{type_of_activity}\"\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": 8,
"id": "2831d546-b365-498b-8248-c618bd9c3057",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_427/290017524.py:8: DtypeWarning: Columns (10,24) 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_427/290017524.py:12: DtypeWarning: Columns (10,24) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" dataset_test = pd.read_csv(file_in, sep=\",\")\n"
]
},
{
"data": {
"text/plain": [
"customer_id 0\n",
"street_id 0\n",
"structure_id 222819\n",
"mcp_contact_id 70845\n",
"fidelity 0\n",
" ... \n",
"purchases_8_2021 0\n",
"purchases_8_2022 0\n",
"purchases_9_2021 0\n",
"purchases_9_2022 0\n",
"y_has_purchased 0\n",
"Length: 87, dtype: int64"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"dataset_train, dataset_test = load_train_test(type_of_activity)\n",
"dataset_train.isna().sum()"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "b8827f7b-b304-4f51-9814-c7a98ed88cf0",
"metadata": {},
"outputs": [],
"source": [
"def features_target_split(dataset_train, dataset_test):\n",
" \n",
" features_l = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'purchase_date_min', 'purchase_date_max', \n",
" 'time_between_purchase', 'fidelity', 'is_email_true', 'opt_in', #'is_partner', 'nb_tickets_internet',, 'vente_internet_max'\n",
" 'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']\n",
"\n",
" # we suppress fidelity, time between purchase, and gender other (colinearity issue)\n",
" \"\"\"\n",
" features_l = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', \n",
" 'purchase_date_min', 'purchase_date_max', 'nb_tickets_internet', 'is_email_true', \n",
" 'opt_in', 'gender_female', 'gender_male', 'nb_campaigns', 'nb_campaigns_opened']\n",
" \"\"\"\n",
" \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": 10,
"id": "c18195fc-ed40-4e39-a59e-c9ecc5a8e6c3",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Shape train : (224213, 87)\n",
"Shape test : (96096, 87)\n"
]
}
],
"source": [
"X_train, X_test, y_train, y_test = features_target_split(dataset_train, dataset_test)\n",
"print(\"Shape train : \", X_train.shape)\n",
"print(\"Shape test : \", X_test.shape)"
]
},
{
"cell_type": "markdown",
"id": "74eda066-5e01-43aa-b0cf-cc6d9bbf770e",
"metadata": {},
"source": [
"## get results from the logit cross validated model"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "7c81390e-598c-4f02-bd56-dd03b00dcb33",
"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>customer_id</th>\n",
" <th>street_id</th>\n",
" <th>structure_id</th>\n",
" <th>mcp_contact_id</th>\n",
" <th>fidelity</th>\n",
" <th>tenant_id</th>\n",
" <th>is_partner</th>\n",
" <th>deleted_at</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>...</th>\n",
" <th>purchases_5_2022</th>\n",
" <th>purchases_6_2021</th>\n",
" <th>purchases_6_2022</th>\n",
" <th>purchases_7_2021</th>\n",
" <th>purchases_7_2022</th>\n",
" <th>purchases_8_2021</th>\n",
" <th>purchases_8_2022</th>\n",
" <th>purchases_9_2021</th>\n",
" <th>purchases_9_2022</th>\n",
" <th>y_has_purchased</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5_4317407</td>\n",
" <td>969908</td>\n",
" <td>NaN</td>\n",
" <td>6156473.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5_477635</td>\n",
" <td>109121</td>\n",
" <td>NaN</td>\n",
" <td>6213652.0</td>\n",
" <td>2</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5_411639</td>\n",
" <td>92929</td>\n",
" <td>NaN</td>\n",
" <td>6160271.0</td>\n",
" <td>4</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5_326623</td>\n",
" <td>79862</td>\n",
" <td>NaN</td>\n",
" <td>6140109.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5_383915</td>\n",
" <td>85421</td>\n",
" <td>NaN</td>\n",
" <td>6149409.0</td>\n",
" <td>2</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96091</th>\n",
" <td>9_91205</td>\n",
" <td>76215</td>\n",
" <td>NaN</td>\n",
" <td>47280.0</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96092</th>\n",
" <td>9_369887</td>\n",
" <td>815891</td>\n",
" <td>NaN</td>\n",
" <td>30764537.0</td>\n",
" <td>4</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96093</th>\n",
" <td>9_1007562</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96094</th>\n",
" <td>9_15037</td>\n",
" <td>12992</td>\n",
" <td>NaN</td>\n",
" <td>2213448.0</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96095</th>\n",
" <td>9_135370</td>\n",
" <td>76215</td>\n",
" <td>NaN</td>\n",
" <td>2164740.0</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>96096 rows × 87 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id street_id structure_id mcp_contact_id fidelity \\\n",
"0 5_4317407 969908 NaN 6156473.0 1 \n",
"1 5_477635 109121 NaN 6213652.0 2 \n",
"2 5_411639 92929 NaN 6160271.0 4 \n",
"3 5_326623 79862 NaN 6140109.0 1 \n",
"4 5_383915 85421 NaN 6149409.0 2 \n",
"... ... ... ... ... ... \n",
"96091 9_91205 76215 NaN 47280.0 0 \n",
"96092 9_369887 815891 NaN 30764537.0 4 \n",
"96093 9_1007562 1 NaN NaN 0 \n",
"96094 9_15037 12992 NaN 2213448.0 0 \n",
"96095 9_135370 76215 NaN 2164740.0 0 \n",
"\n",
" tenant_id is_partner deleted_at is_email_true opt_in ... \\\n",
"0 1771 False NaN True 0 ... \n",
"1 1771 False NaN True 0 ... \n",
"2 1771 False NaN True 0 ... \n",
"3 1771 False NaN True 1 ... \n",
"4 1771 False NaN True 1 ... \n",
"... ... ... ... ... ... ... \n",
"96091 1490 False NaN True 1 ... \n",
"96092 1490 False NaN True 0 ... \n",
"96093 1490 False NaN True 0 ... \n",
"96094 1490 False NaN True 1 ... \n",
"96095 1490 False NaN True 1 ... \n",
"\n",
" purchases_5_2022 purchases_6_2021 purchases_6_2022 purchases_7_2021 \\\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",
"96091 0.0 0.0 0.0 0.0 \n",
"96092 0.0 0.0 0.0 0.0 \n",
"96093 0.0 0.0 0.0 0.0 \n",
"96094 0.0 0.0 0.0 0.0 \n",
"96095 0.0 0.0 0.0 0.0 \n",
"\n",
" purchases_7_2022 purchases_8_2021 purchases_8_2022 purchases_9_2021 \\\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 1.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"... ... ... ... ... \n",
"96091 0.0 0.0 0.0 0.0 \n",
"96092 0.0 0.0 0.0 0.0 \n",
"96093 0.0 0.0 0.0 0.0 \n",
"96094 0.0 0.0 0.0 0.0 \n",
"96095 0.0 0.0 0.0 0.0 \n",
"\n",
" purchases_9_2022 y_has_purchased \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",
"96091 0.0 0.0 \n",
"96092 0.0 1.0 \n",
"96093 0.0 0.0 \n",
"96094 0.0 0.0 \n",
"96095 0.0 0.0 \n",
"\n",
"[96096 rows x 87 columns]"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test"
]
},
{
"cell_type": "code",
"execution_count": 12,
"id": "c708f439-bb75-4688-bf4f-4c04e13deaae",
"metadata": {},
"outputs": [],
"source": [
"def load_model(type_of_activity, model):\n",
" # BUCKET = f\"projet-bdc2324-team1/Output_model/{type_of_activity}/{model}/\"\n",
" BUCKET = f\"projet-bdc2324-team1/basique/{type_of_activity}/{model}/\"\n",
" filename = model + '.pkl'\n",
" file_path = BUCKET + filename\n",
" with fs.open(file_path, mode=\"rb\") as f:\n",
" model_bytes = f.read()\n",
"\n",
" model = pickle.loads(model_bytes)\n",
" return model"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "5261a803-05b8-41a0-968c-dc7bde48ddd3",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<style>#sk-container-id-1 {\n",
" /* Definition of color scheme common for light and dark mode */\n",
" --sklearn-color-text: black;\n",
" --sklearn-color-line: gray;\n",
" /* Definition of color scheme for unfitted estimators */\n",
" --sklearn-color-unfitted-level-0: #fff5e6;\n",
" --sklearn-color-unfitted-level-1: #f6e4d2;\n",
" --sklearn-color-unfitted-level-2: #ffe0b3;\n",
" --sklearn-color-unfitted-level-3: chocolate;\n",
" /* Definition of color scheme for fitted estimators */\n",
" --sklearn-color-fitted-level-0: #f0f8ff;\n",
" --sklearn-color-fitted-level-1: #d4ebff;\n",
" --sklearn-color-fitted-level-2: #b3dbfd;\n",
" --sklearn-color-fitted-level-3: cornflowerblue;\n",
"\n",
" /* Specific color for light theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
" --sklearn-color-icon: #696969;\n",
"\n",
" @media (prefers-color-scheme: dark) {\n",
" /* Redefinition of color scheme for dark theme */\n",
" --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
" --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
" --sklearn-color-icon: #878787;\n",
" }\n",
"}\n",
"\n",
"#sk-container-id-1 {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"#sk-container-id-1 pre {\n",
" padding: 0;\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-hidden--visually {\n",
" border: 0;\n",
" clip: rect(1px 1px 1px 1px);\n",
" clip: rect(1px, 1px, 1px, 1px);\n",
" height: 1px;\n",
" margin: -1px;\n",
" overflow: hidden;\n",
" padding: 0;\n",
" position: absolute;\n",
" width: 1px;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-dashed-wrapped {\n",
" border: 1px dashed var(--sklearn-color-line);\n",
" margin: 0 0.4em 0.5em 0.4em;\n",
" box-sizing: border-box;\n",
" padding-bottom: 0.4em;\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-container {\n",
" /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
" but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
" so we also need the `!important` here to be able to override the\n",
" default hidden behavior on the sphinx rendered scikit-learn.org.\n",
" See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
" display: inline-block !important;\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-text-repr-fallback {\n",
" display: none;\n",
"}\n",
"\n",
"div.sk-parallel-item,\n",
"div.sk-serial,\n",
"div.sk-item {\n",
" /* draw centered vertical line to link estimators */\n",
" background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
" background-size: 2px 100%;\n",
" background-repeat: no-repeat;\n",
" background-position: center center;\n",
"}\n",
"\n",
"/* Parallel-specific style estimator block */\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item::after {\n",
" content: \"\";\n",
" width: 100%;\n",
" border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
" flex-grow: 1;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel {\n",
" display: flex;\n",
" align-items: stretch;\n",
" justify-content: center;\n",
" background-color: var(--sklearn-color-background);\n",
" position: relative;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item {\n",
" display: flex;\n",
" flex-direction: column;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
" align-self: flex-end;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
" align-self: flex-start;\n",
" width: 50%;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
" width: 0;\n",
"}\n",
"\n",
"/* Serial-specific style estimator block */\n",
"\n",
"#sk-container-id-1 div.sk-serial {\n",
" display: flex;\n",
" flex-direction: column;\n",
" align-items: center;\n",
" background-color: var(--sklearn-color-background);\n",
" padding-right: 1em;\n",
" padding-left: 1em;\n",
"}\n",
"\n",
"\n",
"/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
"clickable and can be expanded/collapsed.\n",
"- Pipeline and ColumnTransformer use this feature and define the default style\n",
"- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
"*/\n",
"\n",
"/* Pipeline and ColumnTransformer style (default) */\n",
"\n",
"#sk-container-id-1 div.sk-toggleable {\n",
" /* Default theme specific background. It is overwritten whether we have a\n",
" specific estimator or a Pipeline/ColumnTransformer */\n",
" background-color: var(--sklearn-color-background);\n",
"}\n",
"\n",
"/* Toggleable label */\n",
"#sk-container-id-1 label.sk-toggleable__label {\n",
" cursor: pointer;\n",
" display: block;\n",
" width: 100%;\n",
" margin-bottom: 0;\n",
" padding: 0.5em;\n",
" box-sizing: border-box;\n",
" text-align: center;\n",
"}\n",
"\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
" /* Arrow on the left of the label */\n",
" content: \"▸\";\n",
" float: left;\n",
" margin-right: 0.25em;\n",
" color: var(--sklearn-color-icon);\n",
"}\n",
"\n",
"#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
" color: var(--sklearn-color-text);\n",
"}\n",
"\n",
"/* Toggleable content - dropdown */\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content {\n",
" max-height: 0;\n",
" max-width: 0;\n",
" overflow: hidden;\n",
" text-align: left;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content pre {\n",
" margin: 0.2em;\n",
" border-radius: 0.25em;\n",
" color: var(--sklearn-color-text);\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
" /* Expand drop-down */\n",
" max-height: 200px;\n",
" max-width: 100%;\n",
" overflow: auto;\n",
"}\n",
"\n",
"#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
" content: \"▾\";\n",
"}\n",
"\n",
"/* Pipeline/ColumnTransformer-specific style */\n",
"\n",
"#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator-specific style */\n",
"\n",
"/* Colorize estimator box */\n",
"#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
"#sk-container-id-1 div.sk-label label {\n",
" /* The background is the default theme color */\n",
" color: var(--sklearn-color-text-on-default-background);\n",
"}\n",
"\n",
"/* On hover, darken the color of the background */\n",
"#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"/* Label box, darken color on hover, fitted */\n",
"#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
" color: var(--sklearn-color-text);\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Estimator label */\n",
"\n",
"#sk-container-id-1 div.sk-label label {\n",
" font-family: monospace;\n",
" font-weight: bold;\n",
" display: inline-block;\n",
" line-height: 1.2em;\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-label-container {\n",
" text-align: center;\n",
"}\n",
"\n",
"/* Estimator-specific */\n",
"#sk-container-id-1 div.sk-estimator {\n",
" font-family: monospace;\n",
" border: 1px dotted var(--sklearn-color-border-box);\n",
" border-radius: 0.25em;\n",
" box-sizing: border-box;\n",
" margin-bottom: 0.5em;\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-0);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-0);\n",
"}\n",
"\n",
"/* on hover */\n",
"#sk-container-id-1 div.sk-estimator:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-2);\n",
"}\n",
"\n",
"#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-2);\n",
"}\n",
"\n",
"/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
"\n",
"/* Common style for \"i\" and \"?\" */\n",
"\n",
".sk-estimator-doc-link,\n",
"a:link.sk-estimator-doc-link,\n",
"a:visited.sk-estimator-doc-link {\n",
" float: right;\n",
" font-size: smaller;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1em;\n",
" height: 1em;\n",
" width: 1em;\n",
" text-decoration: none !important;\n",
" margin-left: 1ex;\n",
" /* unfitted */\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted,\n",
"a:link.sk-estimator-doc-link.fitted,\n",
"a:visited.sk-estimator-doc-link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
".sk-estimator-doc-link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover,\n",
"div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
".sk-estimator-doc-link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"/* Span, style for the box shown on hovering the info icon */\n",
".sk-estimator-doc-link span {\n",
" display: none;\n",
" z-index: 9999;\n",
" position: relative;\n",
" font-weight: normal;\n",
" right: .2ex;\n",
" padding: .5ex;\n",
" margin: .5ex;\n",
" width: min-content;\n",
" min-width: 20ex;\n",
" max-width: 50ex;\n",
" color: var(--sklearn-color-text);\n",
" box-shadow: 2pt 2pt 4pt #999;\n",
" /* unfitted */\n",
" background: var(--sklearn-color-unfitted-level-0);\n",
" border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link.fitted span {\n",
" /* fitted */\n",
" background: var(--sklearn-color-fitted-level-0);\n",
" border: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"\n",
".sk-estimator-doc-link:hover span {\n",
" display: block;\n",
"}\n",
"\n",
"/* \"?\"-specific style due to the `<a>` HTML tag */\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link {\n",
" float: right;\n",
" font-size: 1rem;\n",
" line-height: 1em;\n",
" font-family: monospace;\n",
" background-color: var(--sklearn-color-background);\n",
" border-radius: 1rem;\n",
" height: 1rem;\n",
" width: 1rem;\n",
" text-decoration: none;\n",
" /* unfitted */\n",
" color: var(--sklearn-color-unfitted-level-1);\n",
" border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
"}\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link.fitted {\n",
" /* fitted */\n",
" border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
" color: var(--sklearn-color-fitted-level-1);\n",
"}\n",
"\n",
"/* On hover */\n",
"#sk-container-id-1 a.estimator_doc_link:hover {\n",
" /* unfitted */\n",
" background-color: var(--sklearn-color-unfitted-level-3);\n",
" color: var(--sklearn-color-background);\n",
" text-decoration: none;\n",
"}\n",
"\n",
"#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
" /* fitted */\n",
" background-color: var(--sklearn-color-fitted-level-3);\n",
"}\n",
"</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>GridSearchCV(cv=3, error_score=&#x27;raise&#x27;,\n",
" estimator=Pipeline(steps=[(&#x27;preprocessor&#x27;,\n",
" ColumnTransformer(transformers=[(&#x27;num&#x27;,\n",
" Pipeline(steps=[(&#x27;imputer&#x27;,\n",
" SimpleImputer(fill_value=0,\n",
" strategy=&#x27;constant&#x27;)),\n",
" (&#x27;scaler&#x27;,\n",
" StandardScaler())]),\n",
" [&#x27;nb_campaigns&#x27;,\n",
" &#x27;taux_ouverture_mail&#x27;,\n",
" &#x27;prop_purchases_internet&#x27;,\n",
" &#x27;nb_tickets&#x27;,\n",
" &#x27;nb_purchases&#x27;,\n",
" &#x27;total_amount&#x27;,\n",
" &#x27;nb_suppliers&#x27;,\n",
" &#x27;pu...\n",
" 1.562500e-02, 3.125000e-02, 6.250000e-02, 1.250000e-01,\n",
" 2.500000e-01, 5.000000e-01, 1.000000e+00, 2.000000e+00,\n",
" 4.000000e+00, 8.000000e+00, 1.600000e+01, 3.200000e+01,\n",
" 6.400000e+01]),\n",
" &#x27;LogisticRegression_cv__class_weight&#x27;: [&#x27;balanced&#x27;,\n",
" {0.0: 0.5834990214856762,\n",
" 1.0: 3.49404706249026}],\n",
" &#x27;LogisticRegression_cv__penalty&#x27;: [&#x27;l1&#x27;, &#x27;l2&#x27;]},\n",
" scoring=make_scorer(recall_score, response_method=&#x27;predict&#x27;))</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;GridSearchCV<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.model_selection.GridSearchCV.html\">?<span>Documentation for GridSearchCV</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>GridSearchCV(cv=3, error_score=&#x27;raise&#x27;,\n",
" estimator=Pipeline(steps=[(&#x27;preprocessor&#x27;,\n",
" ColumnTransformer(transformers=[(&#x27;num&#x27;,\n",
" Pipeline(steps=[(&#x27;imputer&#x27;,\n",
" SimpleImputer(fill_value=0,\n",
" strategy=&#x27;constant&#x27;)),\n",
" (&#x27;scaler&#x27;,\n",
" StandardScaler())]),\n",
" [&#x27;nb_campaigns&#x27;,\n",
" &#x27;taux_ouverture_mail&#x27;,\n",
" &#x27;prop_purchases_internet&#x27;,\n",
" &#x27;nb_tickets&#x27;,\n",
" &#x27;nb_purchases&#x27;,\n",
" &#x27;total_amount&#x27;,\n",
" &#x27;nb_suppliers&#x27;,\n",
" &#x27;pu...\n",
" 1.562500e-02, 3.125000e-02, 6.250000e-02, 1.250000e-01,\n",
" 2.500000e-01, 5.000000e-01, 1.000000e+00, 2.000000e+00,\n",
" 4.000000e+00, 8.000000e+00, 1.600000e+01, 3.200000e+01,\n",
" 6.400000e+01]),\n",
" &#x27;LogisticRegression_cv__class_weight&#x27;: [&#x27;balanced&#x27;,\n",
" {0.0: 0.5834990214856762,\n",
" 1.0: 3.49404706249026}],\n",
" &#x27;LogisticRegression_cv__penalty&#x27;: [&#x27;l1&#x27;, &#x27;l2&#x27;]},\n",
" scoring=make_scorer(recall_score, response_method=&#x27;predict&#x27;))</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: Pipeline</label><div class=\"sk-toggleable__content fitted\"><pre>Pipeline(steps=[(&#x27;preprocessor&#x27;,\n",
" ColumnTransformer(transformers=[(&#x27;num&#x27;,\n",
" Pipeline(steps=[(&#x27;imputer&#x27;,\n",
" SimpleImputer(fill_value=0,\n",
" strategy=&#x27;constant&#x27;)),\n",
" (&#x27;scaler&#x27;,\n",
" StandardScaler())]),\n",
" [&#x27;nb_campaigns&#x27;,\n",
" &#x27;taux_ouverture_mail&#x27;,\n",
" &#x27;prop_purchases_internet&#x27;,\n",
" &#x27;nb_tickets&#x27;, &#x27;nb_purchases&#x27;,\n",
" &#x27;total_amount&#x27;,\n",
" &#x27;nb_suppliers&#x27;,\n",
" &#x27;purchases_10_2021&#x27;,\n",
" &#x27;purchases_10_2022&#x27;,\n",
" &#x27;purchases_...\n",
" &#x27;categorie_age_0_10&#x27;,\n",
" &#x27;categorie_age_10_20&#x27;,\n",
" &#x27;categorie_age_20_30&#x27;,\n",
" &#x27;categorie_age_30_40&#x27;,\n",
" &#x27;categorie_age_40_50&#x27;,\n",
" &#x27;categorie_age_50_60&#x27;,\n",
" &#x27;categorie_age_60_70&#x27;,\n",
" &#x27;categorie_age_70_80&#x27;,\n",
" &#x27;categorie_age_plus_80&#x27;,\n",
" &#x27;categorie_age_inconnue&#x27;,\n",
" &#x27;country_fr&#x27;,\n",
" &#x27;is_profession_known&#x27;,\n",
" &#x27;is_zipcode_known&#x27;,\n",
" &#x27;opt_in&#x27;])])),\n",
" (&#x27;LogisticRegression_cv&#x27;,\n",
" LogisticRegression(max_iter=5000, solver=&#x27;saga&#x27;))])</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;preprocessor: ColumnTransformer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.compose.ColumnTransformer.html\">?<span>Documentation for preprocessor: ColumnTransformer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>ColumnTransformer(transformers=[(&#x27;num&#x27;,\n",
" Pipeline(steps=[(&#x27;imputer&#x27;,\n",
" SimpleImputer(fill_value=0,\n",
" strategy=&#x27;constant&#x27;)),\n",
" (&#x27;scaler&#x27;, StandardScaler())]),\n",
" [&#x27;nb_campaigns&#x27;, &#x27;taux_ouverture_mail&#x27;,\n",
" &#x27;prop_purchases_internet&#x27;, &#x27;nb_tickets&#x27;,\n",
" &#x27;nb_purchases&#x27;, &#x27;total_amount&#x27;,\n",
" &#x27;nb_suppliers&#x27;, &#x27;purchases_10_2021&#x27;,\n",
" &#x27;purchases_10_2022&#x27;, &#x27;purchases_11_2021&#x27;,\n",
" &#x27;purchases_12_2021&#x27;, &#x27;pu...\n",
" SimpleImputer(strategy=&#x27;most_frequent&#x27;))]),\n",
" [&#x27;gender_female&#x27;, &#x27;gender_male&#x27;,\n",
" &#x27;achat_internet&#x27;, &#x27;categorie_age_0_10&#x27;,\n",
" &#x27;categorie_age_10_20&#x27;, &#x27;categorie_age_20_30&#x27;,\n",
" &#x27;categorie_age_30_40&#x27;, &#x27;categorie_age_40_50&#x27;,\n",
" &#x27;categorie_age_50_60&#x27;, &#x27;categorie_age_60_70&#x27;,\n",
" &#x27;categorie_age_70_80&#x27;,\n",
" &#x27;categorie_age_plus_80&#x27;,\n",
" &#x27;categorie_age_inconnue&#x27;, &#x27;country_fr&#x27;,\n",
" &#x27;is_profession_known&#x27;, &#x27;is_zipcode_known&#x27;,\n",
" &#x27;opt_in&#x27;])])</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-4\" type=\"checkbox\" ><label for=\"sk-estimator-id-4\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">num</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;nb_campaigns&#x27;, &#x27;taux_ouverture_mail&#x27;, &#x27;prop_purchases_internet&#x27;, &#x27;nb_tickets&#x27;, &#x27;nb_purchases&#x27;, &#x27;total_amount&#x27;, &#x27;nb_suppliers&#x27;, &#x27;purchases_10_2021&#x27;, &#x27;purchases_10_2022&#x27;, &#x27;purchases_11_2021&#x27;, &#x27;purchases_12_2021&#x27;, &#x27;purchases_1_2022&#x27;, &#x27;purchases_2_2022&#x27;, &#x27;purchases_3_2022&#x27;, &#x27;purchases_4_2022&#x27;, &#x27;purchases_5_2021&#x27;, &#x27;purchases_5_2022&#x27;, &#x27;purchases_6_2021&#x27;, &#x27;purchases_6_2022&#x27;, &#x27;purchases_7_2021&#x27;, &#x27;purchases_7_2022&#x27;, &#x27;purchases_8_2021&#x27;, &#x27;purchases_8_2022&#x27;, &#x27;purchases_9_2021&#x27;, &#x27;purchases_9_2022&#x27;, &#x27;purchase_date_min&#x27;, &#x27;purchase_date_max&#x27;, &#x27;nb_targets&#x27;, &#x27;time_to_open&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-5\" type=\"checkbox\" ><label for=\"sk-estimator-id-5\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SimpleImputer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.impute.SimpleImputer.html\">?<span>Documentation for SimpleImputer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SimpleImputer(fill_value=0, strategy=&#x27;constant&#x27;)</pre></div> </div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-6\" type=\"checkbox\" ><label for=\"sk-estimator-id-6\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;StandardScaler<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.preprocessing.StandardScaler.html\">?<span>Documentation for StandardScaler</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>StandardScaler()</pre></div> </div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-7\" type=\"checkbox\" ><label for=\"sk-estimator-id-7\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">bin</label><div class=\"sk-toggleable__content fitted\"><pre>[&#x27;gender_female&#x27;, &#x27;gender_male&#x27;, &#x27;achat_internet&#x27;, &#x27;categorie_age_0_10&#x27;, &#x27;categorie_age_10_20&#x27;, &#x27;categorie_age_20_30&#x27;, &#x27;categorie_age_30_40&#x27;, &#x27;categorie_age_40_50&#x27;, &#x27;categorie_age_50_60&#x27;, &#x27;categorie_age_60_70&#x27;, &#x27;categorie_age_70_80&#x27;, &#x27;categorie_age_plus_80&#x27;, &#x27;categorie_age_inconnue&#x27;, &#x27;country_fr&#x27;, &#x27;is_profession_known&#x27;, &#x27;is_zipcode_known&#x27;, &#x27;opt_in&#x27;]</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-8\" type=\"checkbox\" ><label for=\"sk-estimator-id-8\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SimpleImputer<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.impute.SimpleImputer.html\">?<span>Documentation for SimpleImputer</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SimpleImputer(strategy=&#x27;most_frequent&#x27;)</pre></div> </div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-9\" type=\"checkbox\" ><label for=\"sk-estimator-id-9\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;LogisticRegression<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.4/modules/generated/sklearn.linear_model.LogisticRegression.html\">?<span>Documentation for LogisticRegression</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>LogisticRegression(max_iter=5000, solver=&#x27;saga&#x27;)</pre></div> </div></div></div></div></div></div></div></div></div></div></div>"
],
"text/plain": [
"GridSearchCV(cv=3, error_score='raise',\n",
" estimator=Pipeline(steps=[('preprocessor',\n",
" ColumnTransformer(transformers=[('num',\n",
" Pipeline(steps=[('imputer',\n",
" SimpleImputer(fill_value=0,\n",
" strategy='constant')),\n",
" ('scaler',\n",
" StandardScaler())]),\n",
" ['nb_campaigns',\n",
" 'taux_ouverture_mail',\n",
" 'prop_purchases_internet',\n",
" 'nb_tickets',\n",
" 'nb_purchases',\n",
" 'total_amount',\n",
" 'nb_suppliers',\n",
" 'pu...\n",
" 1.562500e-02, 3.125000e-02, 6.250000e-02, 1.250000e-01,\n",
" 2.500000e-01, 5.000000e-01, 1.000000e+00, 2.000000e+00,\n",
" 4.000000e+00, 8.000000e+00, 1.600000e+01, 3.200000e+01,\n",
" 6.400000e+01]),\n",
" 'LogisticRegression_cv__class_weight': ['balanced',\n",
" {0.0: 0.5834990214856762,\n",
" 1.0: 3.49404706249026}],\n",
" 'LogisticRegression_cv__penalty': ['l1', 'l2']},\n",
" scoring=make_scorer(recall_score, response_method='predict'))"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#model = load_model(type_of_activity, \"LogisticRegression_Benchmark\")\n",
"# model = load_model(type_of_activity, \"randomF_cv\")\n",
"model = load_model(type_of_activity, \"LogisticRegression_cv\")\n",
"model"
]
},
{
"cell_type": "markdown",
"id": "006819e7-e9c5-48d9-85ee-aa43d5e4c9c2",
"metadata": {},
"source": [
"## Quartile clustering"
]
},
{
"cell_type": "code",
"execution_count": 14,
"id": "018d8ff4-3436-4eec-8507-d1a265cbabf1",
"metadata": {},
"outputs": [],
"source": [
"y_pred = model.predict(X_test)\n",
"y_pred_prob = model.predict_proba(X_test)[:, 1]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "846f53b9-73c2-4a8b-9d9e-f11bf59ce9ba",
"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>customer_id</th>\n",
" <th>street_id</th>\n",
" <th>structure_id</th>\n",
" <th>mcp_contact_id</th>\n",
" <th>fidelity</th>\n",
" <th>tenant_id</th>\n",
" <th>is_partner</th>\n",
" <th>deleted_at</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>...</th>\n",
" <th>purchases_7_2022</th>\n",
" <th>purchases_8_2021</th>\n",
" <th>purchases_8_2022</th>\n",
" <th>purchases_9_2021</th>\n",
" <th>purchases_9_2022</th>\n",
" <th>y_has_purchased</th>\n",
" <th>has_purchased</th>\n",
" <th>has_purchased_estim</th>\n",
" <th>score</th>\n",
" <th>quartile</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5_4317407</td>\n",
" <td>969908</td>\n",
" <td>NaN</td>\n",
" <td>6156473.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.445019</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5_477635</td>\n",
" <td>109121</td>\n",
" <td>NaN</td>\n",
" <td>6213652.0</td>\n",
" <td>2</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.382586</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5_411639</td>\n",
" <td>92929</td>\n",
" <td>NaN</td>\n",
" <td>6160271.0</td>\n",
" <td>4</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.916747</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5_326623</td>\n",
" <td>79862</td>\n",
" <td>NaN</td>\n",
" <td>6140109.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.090534</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5_383915</td>\n",
" <td>85421</td>\n",
" <td>NaN</td>\n",
" <td>6149409.0</td>\n",
" <td>2</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.346571</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>5_233172</td>\n",
" <td>141401</td>\n",
" <td>NaN</td>\n",
" <td>3324.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.924684</td>\n",
" <td>4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>5_389999</td>\n",
" <td>95759</td>\n",
" <td>NaN</td>\n",
" <td>6151025.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.569031</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>5_4292211</td>\n",
" <td>78897</td>\n",
" <td>NaN</td>\n",
" <td>4729841.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.125622</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>5_353553</td>\n",
" <td>84189</td>\n",
" <td>NaN</td>\n",
" <td>6146995.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.229432</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>5_401296</td>\n",
" <td>3491</td>\n",
" <td>NaN</td>\n",
" <td>6155457.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\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>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.503987</td>\n",
" <td>3</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>10 rows × 91 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id street_id structure_id mcp_contact_id fidelity tenant_id \\\n",
"0 5_4317407 969908 NaN 6156473.0 1 1771 \n",
"1 5_477635 109121 NaN 6213652.0 2 1771 \n",
"2 5_411639 92929 NaN 6160271.0 4 1771 \n",
"3 5_326623 79862 NaN 6140109.0 1 1771 \n",
"4 5_383915 85421 NaN 6149409.0 2 1771 \n",
"5 5_233172 141401 NaN 3324.0 1 1771 \n",
"6 5_389999 95759 NaN 6151025.0 1 1771 \n",
"7 5_4292211 78897 NaN 4729841.0 1 1771 \n",
"8 5_353553 84189 NaN 6146995.0 1 1771 \n",
"9 5_401296 3491 NaN 6155457.0 1 1771 \n",
"\n",
" is_partner deleted_at is_email_true opt_in ... purchases_7_2022 \\\n",
"0 False NaN True 0 ... 0.0 \n",
"1 False NaN True 0 ... 0.0 \n",
"2 False NaN True 0 ... 0.0 \n",
"3 False NaN True 1 ... 0.0 \n",
"4 False NaN True 1 ... 0.0 \n",
"5 False NaN True 1 ... 0.0 \n",
"6 False NaN True 0 ... 0.0 \n",
"7 False NaN True 1 ... 0.0 \n",
"8 False NaN True 1 ... 0.0 \n",
"9 False NaN True 0 ... 0.0 \n",
"\n",
" purchases_8_2021 purchases_8_2022 purchases_9_2021 purchases_9_2022 \\\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 1.0 0.0 \n",
"4 0.0 0.0 0.0 0.0 \n",
"5 0.0 0.0 0.0 1.0 \n",
"6 0.0 0.0 0.0 0.0 \n",
"7 0.0 0.0 0.0 0.0 \n",
"8 0.0 0.0 0.0 0.0 \n",
"9 0.0 0.0 0.0 0.0 \n",
"\n",
" y_has_purchased has_purchased has_purchased_estim score quartile \n",
"0 0.0 0.0 0.0 0.445019 2 \n",
"1 0.0 0.0 0.0 0.382586 2 \n",
"2 0.0 0.0 1.0 0.916747 4 \n",
"3 0.0 0.0 0.0 0.090534 1 \n",
"4 0.0 0.0 0.0 0.346571 2 \n",
"5 0.0 0.0 1.0 0.924684 4 \n",
"6 0.0 0.0 1.0 0.569031 3 \n",
"7 0.0 0.0 0.0 0.125622 1 \n",
"8 0.0 0.0 0.0 0.229432 1 \n",
"9 0.0 0.0 1.0 0.503987 3 \n",
"\n",
"[10 rows x 91 columns]"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment = X_test\n",
"\n",
"X_test_segment[\"has_purchased\"] = y_test\n",
"X_test_segment[\"has_purchased_estim\"] = y_pred\n",
"X_test_segment[\"score\"] = y_pred_prob\n",
"X_test_segment[\"quartile\"] = np.where(X_test['score']<0.25, '1',\n",
" np.where(X_test['score']<0.5, '2',\n",
" np.where(X_test['score']<0.75, '3', '4')))\n",
"X_test_segment.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "fb592fe3-ea40-4e83-8fe9-c52b9ee42f2a",
"metadata": {},
"outputs": [],
"source": [
"def df_segment(df, y, model) :\n",
"\n",
" y_pred = model.predict(df)\n",
" y_pred_prob = model.predict_proba(df)[:, 1]\n",
"\n",
" df_segment = df\n",
"\n",
" df_segment[\"has_purchased\"] = y\n",
" df_segment[\"has_purchased_estim\"] = y_pred\n",
" df_segment[\"score\"] = y_pred_prob\n",
" df_segment[\"quartile\"] = np.where(df_segment['score']<0.25, '1',\n",
" np.where(df_segment['score']<0.5, '2',\n",
" np.where(df_segment['score']<0.75, '3', '4')))\n",
"\n",
" return df_segment"
]
},
{
"cell_type": "code",
"execution_count": 88,
"id": "968645d5-58cc-485a-bd8b-99f4cfc26fec",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_1080/2624515794.py:8: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_segment[\"has_purchased\"] = y\n",
"/tmp/ipykernel_1080/2624515794.py:9: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_segment[\"has_purchased_estim\"] = y_pred\n",
"/tmp/ipykernel_1080/2624515794.py:10: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_segment[\"score\"] = y_pred_prob\n",
"/tmp/ipykernel_1080/2624515794.py:11: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" df_segment[\"quartile\"] = np.where(df_segment['score']<0.25, '1',\n"
]
},
{
"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>...</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",
" <th>has_purchased</th>\n",
" <th>has_purchased_estim</th>\n",
" <th>score</th>\n",
" <th>quartile</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>100.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>5.177187</td>\n",
" <td>5.177187</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.006066</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>55.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>426.265613</td>\n",
" <td>426.265613</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.288847</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>17.0</td>\n",
" <td>1.0</td>\n",
" <td>80.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>436.033437</td>\n",
" <td>436.033437</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.103264</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4.0</td>\n",
" <td>1.0</td>\n",
" <td>120.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>5.196412</td>\n",
" <td>5.196412</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.008928</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>34.0</td>\n",
" <td>2.0</td>\n",
" <td>416.00</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>478.693148</td>\n",
" <td>115.631470</td>\n",
" <td>363.061678</td>\n",
" <td>0.0</td>\n",
" <td>4</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.992809</td>\n",
" <td>4</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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96091</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>67.31</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>278.442257</td>\n",
" <td>278.442257</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>2</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>15.0</td>\n",
" <td>5.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.351762</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96092</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>61.41</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>189.207373</td>\n",
" <td>189.207373</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>12.0</td>\n",
" <td>9.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.567814</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96093</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</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>...</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>29.0</td>\n",
" <td>3.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.004652</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96094</th>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>79.43</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>279.312905</td>\n",
" <td>279.312905</td>\n",
" <td>0.000000</td>\n",
" <td>1.0</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>20.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.293042</td>\n",
" <td>2</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96095</th>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.00</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>2</td>\n",
" <td>...</td>\n",
" <td>False</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>31.0</td>\n",
" <td>4.0</td>\n",
" <td>0.0</td>\n",
" <td>1.0</td>\n",
" <td>0.787852</td>\n",
" <td>4</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>96096 rows × 21 columns</p>\n",
"</div>"
],
"text/plain": [
" nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 4.0 1.0 100.00 1.0 \n",
"1 1.0 1.0 55.00 1.0 \n",
"2 17.0 1.0 80.00 1.0 \n",
"3 4.0 1.0 120.00 1.0 \n",
"4 34.0 2.0 416.00 1.0 \n",
"... ... ... ... ... \n",
"96091 1.0 1.0 67.31 1.0 \n",
"96092 1.0 1.0 61.41 1.0 \n",
"96093 0.0 0.0 0.00 0.0 \n",
"96094 1.0 1.0 79.43 1.0 \n",
"96095 0.0 0.0 0.00 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 5.177187 5.177187 \n",
"1 0.0 426.265613 426.265613 \n",
"2 0.0 436.033437 436.033437 \n",
"3 0.0 5.196412 5.196412 \n",
"4 0.0 478.693148 115.631470 \n",
"... ... ... ... \n",
"96091 1.0 278.442257 278.442257 \n",
"96092 1.0 189.207373 189.207373 \n",
"96093 0.0 550.000000 550.000000 \n",
"96094 1.0 279.312905 279.312905 \n",
"96095 0.0 550.000000 550.000000 \n",
"\n",
" time_between_purchase nb_tickets_internet fidelity ... opt_in \\\n",
"0 0.000000 0.0 1 ... False \n",
"1 0.000000 0.0 2 ... True \n",
"2 0.000000 0.0 2 ... True \n",
"3 0.000000 0.0 1 ... False \n",
"4 363.061678 0.0 4 ... False \n",
"... ... ... ... ... ... \n",
"96091 0.000000 1.0 2 ... False \n",
"96092 0.000000 1.0 1 ... False \n",
"96093 -1.000000 0.0 1 ... True \n",
"96094 0.000000 1.0 1 ... False \n",
"96095 -1.000000 0.0 2 ... False \n",
"\n",
" gender_female gender_male gender_other nb_campaigns \\\n",
"0 1 0 0 0.0 \n",
"1 0 1 0 0.0 \n",
"2 1 0 0 0.0 \n",
"3 1 0 0 0.0 \n",
"4 1 0 0 0.0 \n",
"... ... ... ... ... \n",
"96091 0 1 0 15.0 \n",
"96092 0 1 0 12.0 \n",
"96093 1 0 0 29.0 \n",
"96094 0 1 0 20.0 \n",
"96095 0 1 0 31.0 \n",
"\n",
" nb_campaigns_opened has_purchased has_purchased_estim score \\\n",
"0 0.0 0.0 0.0 0.006066 \n",
"1 0.0 1.0 0.0 0.288847 \n",
"2 0.0 0.0 0.0 0.103264 \n",
"3 0.0 0.0 0.0 0.008928 \n",
"4 0.0 1.0 1.0 0.992809 \n",
"... ... ... ... ... \n",
"96091 5.0 1.0 0.0 0.351762 \n",
"96092 9.0 0.0 1.0 0.567814 \n",
"96093 3.0 0.0 0.0 0.004652 \n",
"96094 4.0 0.0 0.0 0.293042 \n",
"96095 4.0 0.0 1.0 0.787852 \n",
"\n",
" quartile \n",
"0 1 \n",
"1 2 \n",
"2 1 \n",
"3 1 \n",
"4 4 \n",
"... ... \n",
"96091 2 \n",
"96092 3 \n",
"96093 1 \n",
"96094 2 \n",
"96095 4 \n",
"\n",
"[96096 rows x 21 columns]"
]
},
"execution_count": 88,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_segment(X_test, y_test, model)"
]
},
{
"cell_type": "markdown",
"id": "ad16b8ab-7e01-404b-971e-866e9b9d5aa4",
"metadata": {},
"source": [
"## definition of functions to compute the bias of scores and adjust it \n",
"\n",
"Le biais est calculé de la façon suivante. \n",
"En notant $\\hat{p(x_i)}$ le score calculé (estimé par la modélisation) et $p(x_i)$ le vrai score (sans biais), et $\\beta$ le logarithme du biais, on a : \\\n",
"$\\ln{\\frac{\\hat{p(x_i)}}{1-\\hat{p(x_i)}}} = \\beta + \\ln{\\frac{p(x_i)}{1-p(x_i)}}$ \\\n",
"$ \\frac{\\hat{p(x_i)}}{1-\\hat{p(x_i)}} = \\exp(\\beta) . \\frac{p(x_i)}{1-p(x_i)} $ , soit : \\\n",
"$p(x_i) = {\\frac{\\frac{\\hat{p(x_i)}}{1-\\hat{p(x_i)}}}{B+\\frac{\\hat{p(x_i)}}{1-\\hat{p(x_i)}}}}$ \\\n",
"Ce qu'on appelle biais et qu'on estime dans le code par la suite est : $B=\\exp(\\beta) $. Les probabilités ne sont donc pas biaisées si $B=1$. Il y a surestimation si $B>1$. \n",
"\n",
"On cherche le B qui permette d'ajuster les probabilités de telle sorte que la somme des scores soit égale à la somme des y_has_purchased. Cela revient à résoudre : \n",
"\n",
"\\begin{equation}\n",
"\\sum_{i}{\\frac{\\frac{\\hat{p(x_i)}}{1-\\hat{p(x_i)}}}{B+\\frac{\\hat{p(x_i)}}{1-\\hat{p(x_i)}}}} = \\sum_{i}{Y_i}\n",
"\\end{equation}\n",
"\n",
"C'est ce que fait la fonction find_bias. \n",
"\n",
"Note sur les notations : \\\n",
"$\\hat{p(x_i)}$ correspond à ce qu'on appelle le score et $p(x_i)$ à ce qu'on appellera le score adjusted"
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "f0379536-a6c5-4b16-bde5-d0319ec1b140",
"metadata": {},
"outputs": [],
"source": [
"# compute adjusted score from odd ratios (cf formula above)\n",
"def adjusted_score(odd_ratio, bias) :\n",
" adjusted_score = odd_ratio/(bias+odd_ratio)\n",
" return adjusted_score"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "32a0dfd0-f49d-4785-a56f-706d381bfe41",
"metadata": {},
"outputs": [],
"source": [
"# when the score is 1 we cannot compute the odd ratio, so we adjust scores equal to 1\n",
"# we set the second best score instead\n",
"\n",
"def adjust_score_1(score) :\n",
" second_best_score = np.array([element for element in score if element !=1]).max()\n",
" new_score = np.array([element if element!=1 else second_best_score for element in score]) \n",
" return new_score"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "2dff1def-02df-413e-afce-b4aeaf7752b6",
"metadata": {},
"outputs": [],
"source": [
"def odd_ratio(score) :\n",
" return score / (1 - score)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "683d71fc-7442-4028-869c-49c57592d6e9",
"metadata": {},
"outputs": [],
"source": [
"# definition of a function that automatically detects the bias\n",
"\n",
"def find_bias(odd_ratios, y_objective, initial_guess=6) :\n",
" \"\"\"\n",
" results = minimize(lambda bias : (sum([adjusted_score(element, bias) for element in list(odd_ratios)]) - y_objective)**2 ,\n",
" initial_guess , method = \"BFGS\")\n",
"\n",
" estimated_bias = results.x[0]\n",
" \"\"\"\n",
"\n",
" # faster method\n",
" bias_estimated = fsolve(lambda bias : sum([adjusted_score(element, bias) for element in list(odd_ratios)]) - y_objective, x0=6)\n",
" \n",
" return bias_estimated[0]"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "f17dc6ca-7a48-441b-8c04-11c47b8b9741",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.31861289893787315 0.14317973692973693\n"
]
},
{
"data": {
"text/plain": [
"0.14310053386734936"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"print(X_test_segment[\"score\"].mean(), y_test[\"y_has_purchased\"].mean())\n",
"y_train[\"y_has_purchased\"].mean()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "781b0d40-c954-4c54-830a-e709c8667328",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"5.939748066330849"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# computation with the function defined\n",
"\n",
"bias_test_set = find_bias(odd_ratios = odd_ratio(adjust_score_1(X_test_segment[\"score\"])), \n",
" y_objective = y_test[\"y_has_purchased\"].sum(),\n",
" initial_guess=6)\n",
"bias_test_set"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "248cb862-418e-4767-9933-70c4885ecf40",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"6.01952986090399"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# comparison with bias of the train set\n",
"X_train_score = model.predict_proba(X_train)[:, 1]\n",
"\n",
"bias_train_set = find_bias(odd_ratios = odd_ratio(adjust_score_1(X_train_score)), \n",
" y_objective = y_train[\"y_has_purchased\"].sum(),\n",
" initial_guess=10)\n",
"bias_train_set"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "fff6cbe6-7bb3-4732-9b81-b9ac5383bbcf",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"betâ test - betâ train = -0.013342440676233564\n"
]
}
],
"source": [
"print(\"betâ test - betâ train = \",np.log(bias_test_set/bias_train_set))"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "f506870d-4a8a-4b2c-8f0b-e0789080b20c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"mean absolute erreur 0.0009061459618344602\n"
]
}
],
"source": [
"# impact of considering a bias computed on train set instead of test set - totally neglectable\n",
"\n",
"score_adjusted_test = adjusted_score(odd_ratio(adjust_score_1(X_test_segment[\"score\"])), bias = bias_test_set)\n",
"score_adjusted_train = adjusted_score(odd_ratio(adjust_score_1(X_test_segment[\"score\"])), bias = bias_train_set)\n",
"\n",
"print(\"mean absolute erreur\",abs(score_adjusted_test-score_adjusted_train).mean())"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "8213d0e4-063b-49fa-90b7-677fc34f4c01",
"metadata": {},
"outputs": [],
"source": [
"# adjust scores accordingly \n",
"\n",
"# X_test_segment[\"score_adjusted\"] = adjusted_score(odd_ratio(adjust_score_1(X_test_segment[\"score\"])), bias = bias_test_set)\n",
"\n",
"# actually, we are not supposed to have X_test, so the biais is estimated on X_train\n",
"# X_test_segment[\"score_adjusted\"] = adjusted_score(odd_ratio(adjust_score_1(X_test_segment[\"score\"])), bias = bias_train_set)\n",
"X_test_segment[\"score_adjusted\"] = score_adjusted_train"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "834d3723-2e72-4c65-9c62-e2d595c69461",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"MSE for score : 0.11809894130837426\n",
"MSE for ajusted score : 0.07434720017843571\n",
"sum of y_has_purchased : 13759.0\n",
"sum of adjusted scores : 13671.922997651252\n"
]
}
],
"source": [
"# check \n",
"\n",
"MSE_score = ((X_test_segment[\"score\"]-X_test_segment[\"has_purchased\"])**2).mean()\n",
"MSE_ajusted_score = ((X_test_segment[\"score_adjusted\"]-X_test_segment[\"has_purchased\"])**2).mean()\n",
"print(f\"MSE for score : {MSE_score}\")\n",
"print(f\"MSE for ajusted score : {MSE_ajusted_score}\")\n",
"\n",
"print(\"sum of y_has_purchased :\",y_test[\"y_has_purchased\"].sum())\n",
"print(\"sum of adjusted scores :\", X_test_segment[\"score_adjusted\"].sum())"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "9f30a4dd-a9d8-405a-a7d5-5324ae88cf70",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"MAE for score : 0.24742788848313355\n",
"MAE for adjusted score : 0.14205672428104504\n"
]
}
],
"source": [
"# mean absolute error - divided by 2 with out method\n",
"\n",
"MAE_score = abs(X_test_segment[\"score\"]-X_test_segment[\"has_purchased\"]).mean()\n",
"MAE_ajusted_score = abs(X_test_segment[\"score_adjusted\"]-X_test_segment[\"has_purchased\"]).mean()\n",
"print(f\"MAE for score : {MAE_score}\")\n",
"print(f\"MAE for adjusted score : {MAE_ajusted_score}\")"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "6f9396db-e213-408c-a596-eaeec3bc79f3",
"metadata": {},
"outputs": [],
"source": [
"# visualization\n",
"\n",
"# histogramme des probas et des probas ajustées\n",
"\n",
"def plot_hist_scores(df, score, score_adjusted, type_of_activity) :\n",
"\n",
" plt.figure()\n",
" plt.hist(df[score], label = \"score\", alpha=0.6)\n",
" plt.hist(df[score_adjusted], label=\"adjusted score\", alpha=0.6)\n",
" plt.legend()\n",
" plt.xlabel(\"probability of a future purchase\")\n",
" plt.ylabel(\"count\")\n",
" plt.title(f\"Comparison between score and adjusted score for {type_of_activity} companies\")\n",
" # plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "def64c16-f4dd-493c-909c-d886d7f53947",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'projet-bdc2324-team1/Output_expected_CA/sport/hist_score_adjustedsport.png'"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"PATH + file_name + type_of_activity + \".png\""
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "b478d40d-9677-4204-87bd-16fb0bc1fe9a",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plot_hist_scores(X_test_segment, score = \"score\", score_adjusted = \"score_adjusted\", type_of_activity = type_of_activity)"
]
},
{
"cell_type": "code",
"execution_count": 40,
"id": "add631d7-0757-45a5-bb5b-f7f4b4baa961",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"projet-bdc2324-team1/Output_expected_CA/sport/\n"
]
}
],
"source": [
"# define path so save graphics\n",
"\n",
"# define type of activity \n",
"type_of_activity = \"sport\"\n",
"PATH = f\"projet-bdc2324-team1/Output_expected_CA/{type_of_activity}/\"\n",
"print(PATH)"
]
},
{
"cell_type": "code",
"execution_count": 68,
"id": "3a5b5bd9-e033-4436-8c56-bf5fb61df87f",
"metadata": {},
"outputs": [],
"source": [
"# export png \n",
"\n",
"# plot adjusted scores and save (to be tested)\n",
"plot_hist_scores(X_test_segment, score = \"score\", score_adjusted = \"score_adjusted\", type_of_activity = type_of_activity)\n",
"\n",
"image_buffer = io.BytesIO()\n",
"plt.savefig(image_buffer, format='png')\n",
"image_buffer.seek(0)\n",
"file_name = \"hist_score_adjusted_\"\n",
"FILE_PATH_OUT_S3 = PATH + file_name + type_of_activity + \".png\"\n",
"with fs.open(FILE_PATH_OUT_S3, 'wb') as s3_file:\n",
" s3_file.write(image_buffer.read())\n",
"plt.close()"
]
},
{
"cell_type": "markdown",
"id": "e6fae260-fab8-4f51-90dc-9b6d7314c77b",
"metadata": {},
"source": [
"## Compute number of tickets and CA by segment with the recalibrated score"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "90c4c2b5-0ede-4001-889f-749cfbd9df04",
"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>quartile</th>\n",
" <th>score (%)</th>\n",
" <th>score adjusted (%)</th>\n",
" <th>has purchased (%)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>10.20</td>\n",
" <td>1.94</td>\n",
" <td>1.19</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>37.08</td>\n",
" <td>9.12</td>\n",
" <td>10.62</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>62.07</td>\n",
" <td>22.00</td>\n",
" <td>28.67</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>90.35</td>\n",
" <td>67.16</td>\n",
" <td>63.09</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" quartile score (%) score adjusted (%) has purchased (%)\n",
"0 1 10.20 1.94 1.19\n",
"1 2 37.08 9.12 10.62\n",
"2 3 62.07 22.00 28.67\n",
"3 4 90.35 67.16 63.09"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_table_adjusted_scores = (100 * X_test_segment.groupby(\"quartile\")[[\"score\",\"score_adjusted\", \"has_purchased\"]].mean()).round(2).reset_index()\n",
"X_test_table_adjusted_scores = X_test_table_adjusted_scores.rename(columns = {col : f\"{col.replace('_', ' ')} (%)\" for col in X_test_table_adjusted_scores.columns if col in [\"score\",\"score_adjusted\", \"has_purchased\"]})\n",
"X_test_table_adjusted_scores"
]
},
{
"cell_type": "code",
"execution_count": 162,
"id": "d0b8740c-cf48-4a3e-83cb-23d95059f62f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\\\begin{tabular}{lrrr}\\n\\\\toprule\\nquartile & score (%) & score adjusted (%) & has purchased (%) \\\\\\\\\\n\\\\midrule\\n1 & 13.250000 & 2.510000 & 1.570000 \\\\\\\\\\n2 & 33.890000 & 8.000000 & 9.850000 \\\\\\\\\\n3 & 63.060000 & 22.580000 & 21.470000 \\\\\\\\\\n4 & 90.520000 & 66.200000 & 65.010000 \\\\\\\\\\n\\\\bottomrule\\n\\\\end{tabular}\\n'"
]
},
"execution_count": 162,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_table_adjusted_scores.to_latex(index=False)"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "d6a04d3e-c454-43e4-ae4c-0746e928575b",
"metadata": {},
"outputs": [],
"source": [
"# comparison between score and adjusted score - export csv associated\n",
"\n",
"file_name = \"table_adjusted_score_\"\n",
"FILE_PATH_OUT_S3 = PATH + file_name + type_of_activity + \".csv\"\n",
"with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:\n",
" X_test_table_adjusted_scores.to_csv(file_out, index = False)"
]
},
{
"cell_type": "code",
"execution_count": 129,
"id": "a974589f-7952-4db2-bebf-7b69c6b09372",
"metadata": {},
"outputs": [],
"source": [
"def project_tickets_CA (df, nb_purchases, nb_tickets, total_amount, score_adjusted, duration_ref, duration_projection) :\n",
" \n",
" duration_ratio = duration_ref/duration_projection\n",
"\n",
" df_output = df\n",
" \n",
" # project number of tickets : at least 1 ticket purchased if the customer purchased\n",
" df_output.loc[:,\"nb_tickets_projected\"] = df_output.loc[:,nb_tickets].apply(lambda x : max(1, x /duration_ratio))\n",
"\n",
" # project amount : if the customer buys a ticket, we expect the amount to be at least the average price of tickets \n",
" # for customers purchasing exactly one ticket\n",
" if df_output.loc[df_output[nb_tickets]==1].shape[0] > 0 :\n",
" avg_price = df_output.loc[df_output[nb_tickets]==1][total_amount].mean()\n",
" else :\n",
" avg_price = df_output[total_amount].mean()\n",
" # df_output.loc[:,\"total_amount_projected\"] = df_output.loc[:,total_amount] / duration_ratio\n",
" # df_output.loc[:,\"total_amount_projected\"] = df_output.loc[:,total_amount].apply(lambda x : max(avg_ticket_price, x/duration_ratio))\n",
"\n",
" # we compute the avg price of ticket for each customer\n",
" df_output[\"avg_ticket_price\"] = df_output[total_amount]/df_output[nb_tickets]\n",
"\n",
" # correct negatives total amounts\n",
" df_output.loc[:,\"total_amount_corrected\"] = np.where(df_output[total_amount] < 0, \n",
" avg_price * df_output[nb_tickets],\n",
" df_output[total_amount])\n",
" \n",
" df_output.loc[:,\"total_amount_projected\"] = np.where(\n",
" # if no ticket bought in the past, we take the average price\n",
" df_output[nb_tickets]==0, avg_price,\n",
" # if avg prices of tickets are negative, we recompute the expected amount based on the avg price of a ticket\n",
" # observed on the whole population\n",
" np.where(X_test_segment[\"avg_ticket_price\"] < 0, avg_price * df_output.loc[:,\"nb_tickets_projected\"],\n",
" # else, the amount projected is the average price of tickets bought by the customer * nb tickets projected\n",
" df_output[\"avg_ticket_price\"] * df_output.loc[:,\"nb_tickets_projected\"])\n",
" )\n",
" \n",
" df_output.loc[:,\"nb_tickets_expected\"] = df_output.loc[:,score_adjusted] * df_output.loc[:,\"nb_tickets_projected\"]\n",
" df_output.loc[:,\"total_amount_expected\"] = df_output.loc[:,score_adjusted] * df_output.loc[:,\"total_amount_projected\"]\n",
"\n",
" df_output.loc[:,\"pace_purchase\"] = (duration_ref/df_output.loc[:,nb_purchases]).apply(lambda x : np.nan if x==np.inf else x)\n",
" \n",
" return df_output\n"
]
},
{
"cell_type": "code",
"execution_count": 120,
"id": "87fb8e1c-3567-46df-9e98-197b7ca3becd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([25., 92., 45., ..., 0., 0., 0.])"
]
},
"execution_count": 120,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.where(X_test_segment[\"total_amount\"] < 0, avg_price * X_test_segment[\"nb_tickets\"],\n",
" X_test_segment[\"total_amount\"]\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 121,
"id": "dc0cdf9c-c55c-4085-80a6-c2131bb22ad4",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 25.00\n",
"1 92.00\n",
"2 45.00\n",
"3 10.00\n",
"4 127.00\n",
" ... \n",
"96091 0.00\n",
"96092 100.89\n",
"96093 0.00\n",
"96094 0.00\n",
"96095 0.00\n",
"Name: total_amount, Length: 96096, dtype: float64"
]
},
"execution_count": 121,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
" X_test_segment[\"total_amount\"]"
]
},
{
"cell_type": "code",
"execution_count": 105,
"id": "51455654-e6de-4608-8fbe-594d7fcd5b53",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(0, 98)"
]
},
"execution_count": 105,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment.loc[X_test_segment[\"nb_tickets\"]==-1].shape[0°"
]
},
{
"cell_type": "code",
"execution_count": 71,
"id": "a0d08a46-93d0-425a-9a56-28cf8bfd93e9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 4.410500e+04\n",
"mean 4.640310e+02\n",
"std 1.049793e+04\n",
"min -2.064700e+04\n",
"25% 3.000000e+01\n",
"50% 6.900000e+01\n",
"75% 1.339900e+02\n",
"max 1.209751e+06\n",
"Name: total_amount, dtype: float64"
]
},
"execution_count": 71,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"duration_ratio = 17/12\n",
"X_test_segment.loc[X_test_segment[\"nb_tickets\"]>0][\"total_amount\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": 74,
"id": "dc7de319-6d22-44f0-9e58-492088b0dd5f",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 183.851977\n",
"std 5021.379770\n",
"min 48.713098\n",
"25% 48.713098\n",
"50% 48.713098\n",
"75% 48.713098\n",
"max 853942.164706\n",
"Name: total_amount, dtype: float64"
]
},
"execution_count": 74,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"avg_price = X_test_segment.loc[X_test_segment[\"nb_tickets\"]==1][\"total_amount\"].mean()\n",
"X_test_segment[\"total_amount\"].apply(lambda x : max(avg_price, x/duration_ratio)).describe()"
]
},
{
"cell_type": "code",
"execution_count": 76,
"id": "8aa50962-067b-493a-8766-258547da8bcd",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 150.335598\n",
"std 5022.896337\n",
"min -14574.352941\n",
"25% 0.000000\n",
"50% 0.000000\n",
"75% 42.352941\n",
"max 853942.164706\n",
"Name: total_amount, dtype: float64"
]
},
"execution_count": 76,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[\"total_amount\"].apply(lambda x : x/duration_ratio).describe()"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "f2f04205-7b8b-4978-9b4f-1c83034628fe",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 1.411765\n",
"1 1.411765\n",
"2 2.117647\n",
"3 0.705882\n",
"4 5.647059\n",
" ... \n",
"96091 0.000000\n",
"96092 1.411765\n",
"96093 0.000000\n",
"96094 0.000000\n",
"96095 0.000000\n",
"Name: nb_tickets, Length: 96096, dtype: float64"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment.loc[:,\"nb_tickets\"]/duration_ratio"
]
},
{
"cell_type": "code",
"execution_count": 81,
"id": "140e09b9-f6b8-4075-b380-86851e1596f1",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 176.690937\n",
"std 5022.166115\n",
"min -14574.352941\n",
"25% 48.713098\n",
"50% 48.713098\n",
"75% 48.713098\n",
"max 853942.164706\n",
"dtype: float64"
]
},
"execution_count": 81,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.Series(np.where(X_test_segment[\"nb_tickets\"]==0, avg_price, X_test_segment[\"nb_tickets_projected\"] * X_test_segment[\"total_amount\"]/X_test_segment[\"nb_tickets\"])).describe()"
]
},
{
"cell_type": "code",
"execution_count": 87,
"id": "b2c8c7dd-9cd2-40b8-945f-0daf27b3b66b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 162.000000\n",
"mean 51.283951\n",
"std 135.183724\n",
"min 1.000000\n",
"25% 2.000000\n",
"50% 6.000000\n",
"75% 31.500000\n",
"max 1038.000000\n",
"Name: nb_tickets, dtype: float64"
]
},
"execution_count": 87,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[X_test_segment[\"total_amount\"]<0][\"nb_tickets\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": 89,
"id": "44ce62e3-fae6-4192-b8dd-386fd84fed22",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 44105.000000\n",
"mean 35.661188\n",
"std 71.477667\n",
"min -216.368182\n",
"25% 10.000000\n",
"50% 25.000000\n",
"75% 48.720000\n",
"max 4000.000000\n",
"Name: avg_ticket_price, dtype: float64"
]
},
"execution_count": 89,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# code pr projet revenue\n",
"\n",
"X_test_segment[\"avg_ticket_price\"] = X_test_segment[\"total_amount\"]/X_test_segment[\"nb_tickets\"]\n",
"X_test_segment[\"avg_ticket_price\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": 97,
"id": "e1c0671a-2b5f-48bf-b964-6bee8a4223ac",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 180.394197\n",
"std 5025.591726\n",
"min 0.000000\n",
"25% 48.713098\n",
"50% 48.713098\n",
"75% 48.713098\n",
"max 853942.164706\n",
"dtype: float64"
]
},
"execution_count": 97,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.Series(\n",
" np.where(X_test_segment[\"nb_tickets\"]==0, avg_price,\n",
" \n",
" np.where(X_test_segment[\"avg_ticket_price\"] < 0, avg_price * X_test_segment[\"nb_tickets\"] / duration_ratio,\n",
" X_test_segment[\"avg_ticket_price\"] * X_test_segment[\"nb_tickets\"] / duration_ratio)\n",
" )\n",
").describe()"
]
},
{
"cell_type": "code",
"execution_count": 100,
"id": "6c1e0649-3be1-4754-a86c-24b46a12d523",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 5058.000000\n",
"mean 13.671807\n",
"std 155.341970\n",
"min 1.000000\n",
"25% 1.000000\n",
"50% 2.000000\n",
"75% 4.000000\n",
"max 8250.000000\n",
"Name: nb_tickets, dtype: float64"
]
},
"execution_count": 100,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[X_test_segment[\"avg_ticket_price\"] == 0][\"nb_tickets\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2a4d1b0a-fe16-49e7-9b61-d822d2ed062a",
"metadata": {},
"outputs": [],
"source": [
"df['colonne2'] = np.where(df['colonne1'] > seuil2, df['colonne2'] * 2, # Si colonne1 > seuil2\n",
" np.where(df['colonne1'] > seuil1, df['colonne2'] + 1, df['colonne2'])) "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fa87726a-dee2-4b15-af2d-b22583a9eb53",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 132,
"id": "dd8a52e1-d06e-4790-8687-8e58e3e6b84e",
"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>customer_id</th>\n",
" <th>street_id</th>\n",
" <th>structure_id</th>\n",
" <th>mcp_contact_id</th>\n",
" <th>fidelity</th>\n",
" <th>tenant_id</th>\n",
" <th>is_partner</th>\n",
" <th>deleted_at</th>\n",
" <th>is_email_true</th>\n",
" <th>opt_in</th>\n",
" <th>...</th>\n",
" <th>score</th>\n",
" <th>quartile</th>\n",
" <th>score_adjusted</th>\n",
" <th>nb_tickets_projected</th>\n",
" <th>total_amount_projected</th>\n",
" <th>nb_tickets_expected</th>\n",
" <th>total_amount_expected</th>\n",
" <th>pace_purchase</th>\n",
" <th>avg_ticket_price</th>\n",
" <th>total_amount_corrected</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>5_4317407</td>\n",
" <td>969908</td>\n",
" <td>NaN</td>\n",
" <td>6156473.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.445019</td>\n",
" <td>2</td>\n",
" <td>0.117551</td>\n",
" <td>1.411765</td>\n",
" <td>17.647059</td>\n",
" <td>0.165955</td>\n",
" <td>2.074432</td>\n",
" <td>17.000000</td>\n",
" <td>12.500</td>\n",
" <td>25.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5_477635</td>\n",
" <td>109121</td>\n",
" <td>NaN</td>\n",
" <td>6213652.0</td>\n",
" <td>2</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.382586</td>\n",
" <td>2</td>\n",
" <td>0.093333</td>\n",
" <td>1.411765</td>\n",
" <td>64.941176</td>\n",
" <td>0.131765</td>\n",
" <td>6.061181</td>\n",
" <td>8.500000</td>\n",
" <td>46.000</td>\n",
" <td>92.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>5_411639</td>\n",
" <td>92929</td>\n",
" <td>NaN</td>\n",
" <td>6160271.0</td>\n",
" <td>4</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.916747</td>\n",
" <td>4</td>\n",
" <td>0.646556</td>\n",
" <td>2.117647</td>\n",
" <td>31.764706</td>\n",
" <td>1.369178</td>\n",
" <td>20.537670</td>\n",
" <td>5.666667</td>\n",
" <td>15.000</td>\n",
" <td>45.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>5_326623</td>\n",
" <td>79862</td>\n",
" <td>NaN</td>\n",
" <td>6140109.0</td>\n",
" <td>1</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.090534</td>\n",
" <td>1</td>\n",
" <td>0.016268</td>\n",
" <td>1.000000</td>\n",
" <td>10.000000</td>\n",
" <td>0.016268</td>\n",
" <td>0.162683</td>\n",
" <td>17.000000</td>\n",
" <td>10.000</td>\n",
" <td>10.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5_383915</td>\n",
" <td>85421</td>\n",
" <td>NaN</td>\n",
" <td>6149409.0</td>\n",
" <td>2</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.346571</td>\n",
" <td>2</td>\n",
" <td>0.080976</td>\n",
" <td>5.647059</td>\n",
" <td>89.647059</td>\n",
" <td>0.457279</td>\n",
" <td>7.259298</td>\n",
" <td>8.500000</td>\n",
" <td>15.875</td>\n",
" <td>127.00</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",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96091</th>\n",
" <td>9_91205</td>\n",
" <td>76215</td>\n",
" <td>NaN</td>\n",
" <td>47280.0</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.014966</td>\n",
" <td>1</td>\n",
" <td>0.002518</td>\n",
" <td>1.000000</td>\n",
" <td>48.713098</td>\n",
" <td>0.002518</td>\n",
" <td>0.122642</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96092</th>\n",
" <td>9_369887</td>\n",
" <td>815891</td>\n",
" <td>NaN</td>\n",
" <td>30764537.0</td>\n",
" <td>4</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.834257</td>\n",
" <td>4</td>\n",
" <td>0.455392</td>\n",
" <td>1.411765</td>\n",
" <td>71.216471</td>\n",
" <td>0.642906</td>\n",
" <td>32.431379</td>\n",
" <td>8.500000</td>\n",
" <td>50.445</td>\n",
" <td>100.89</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96093</th>\n",
" <td>9_1007562</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>0</td>\n",
" <td>...</td>\n",
" <td>0.062886</td>\n",
" <td>1</td>\n",
" <td>0.011025</td>\n",
" <td>1.000000</td>\n",
" <td>48.713098</td>\n",
" <td>0.011025</td>\n",
" <td>0.537071</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96094</th>\n",
" <td>9_15037</td>\n",
" <td>12992</td>\n",
" <td>NaN</td>\n",
" <td>2213448.0</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.068998</td>\n",
" <td>1</td>\n",
" <td>0.012162</td>\n",
" <td>1.000000</td>\n",
" <td>48.713098</td>\n",
" <td>0.012162</td>\n",
" <td>0.592451</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>96095</th>\n",
" <td>9_135370</td>\n",
" <td>76215</td>\n",
" <td>NaN</td>\n",
" <td>2164740.0</td>\n",
" <td>0</td>\n",
" <td>1490</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>True</td>\n",
" <td>1</td>\n",
" <td>...</td>\n",
" <td>0.018486</td>\n",
" <td>1</td>\n",
" <td>0.003119</td>\n",
" <td>1.000000</td>\n",
" <td>48.713098</td>\n",
" <td>0.003119</td>\n",
" <td>0.151938</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>96096 rows × 99 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id street_id structure_id mcp_contact_id fidelity \\\n",
"0 5_4317407 969908 NaN 6156473.0 1 \n",
"1 5_477635 109121 NaN 6213652.0 2 \n",
"2 5_411639 92929 NaN 6160271.0 4 \n",
"3 5_326623 79862 NaN 6140109.0 1 \n",
"4 5_383915 85421 NaN 6149409.0 2 \n",
"... ... ... ... ... ... \n",
"96091 9_91205 76215 NaN 47280.0 0 \n",
"96092 9_369887 815891 NaN 30764537.0 4 \n",
"96093 9_1007562 1 NaN NaN 0 \n",
"96094 9_15037 12992 NaN 2213448.0 0 \n",
"96095 9_135370 76215 NaN 2164740.0 0 \n",
"\n",
" tenant_id is_partner deleted_at is_email_true opt_in ... \\\n",
"0 1771 False NaN True 0 ... \n",
"1 1771 False NaN True 0 ... \n",
"2 1771 False NaN True 0 ... \n",
"3 1771 False NaN True 1 ... \n",
"4 1771 False NaN True 1 ... \n",
"... ... ... ... ... ... ... \n",
"96091 1490 False NaN True 1 ... \n",
"96092 1490 False NaN True 0 ... \n",
"96093 1490 False NaN True 0 ... \n",
"96094 1490 False NaN True 1 ... \n",
"96095 1490 False NaN True 1 ... \n",
"\n",
" score quartile score_adjusted nb_tickets_projected \\\n",
"0 0.445019 2 0.117551 1.411765 \n",
"1 0.382586 2 0.093333 1.411765 \n",
"2 0.916747 4 0.646556 2.117647 \n",
"3 0.090534 1 0.016268 1.000000 \n",
"4 0.346571 2 0.080976 5.647059 \n",
"... ... ... ... ... \n",
"96091 0.014966 1 0.002518 1.000000 \n",
"96092 0.834257 4 0.455392 1.411765 \n",
"96093 0.062886 1 0.011025 1.000000 \n",
"96094 0.068998 1 0.012162 1.000000 \n",
"96095 0.018486 1 0.003119 1.000000 \n",
"\n",
" total_amount_projected nb_tickets_expected total_amount_expected \\\n",
"0 17.647059 0.165955 2.074432 \n",
"1 64.941176 0.131765 6.061181 \n",
"2 31.764706 1.369178 20.537670 \n",
"3 10.000000 0.016268 0.162683 \n",
"4 89.647059 0.457279 7.259298 \n",
"... ... ... ... \n",
"96091 48.713098 0.002518 0.122642 \n",
"96092 71.216471 0.642906 32.431379 \n",
"96093 48.713098 0.011025 0.537071 \n",
"96094 48.713098 0.012162 0.592451 \n",
"96095 48.713098 0.003119 0.151938 \n",
"\n",
" pace_purchase avg_ticket_price total_amount_corrected \n",
"0 17.000000 12.500 25.00 \n",
"1 8.500000 46.000 92.00 \n",
"2 5.666667 15.000 45.00 \n",
"3 17.000000 10.000 10.00 \n",
"4 8.500000 15.875 127.00 \n",
"... ... ... ... \n",
"96091 NaN NaN 0.00 \n",
"96092 8.500000 50.445 100.89 \n",
"96093 NaN NaN 0.00 \n",
"96094 NaN NaN 0.00 \n",
"96095 NaN NaN 0.00 \n",
"\n",
"[96096 rows x 99 columns]"
]
},
"execution_count": 132,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# project nb tickets and CA\n",
"\n",
"X_test_segment = project_tickets_CA (X_test_segment, \"nb_purchases\", \"nb_tickets\", \"total_amount\", \"score_adjusted\", \n",
" duration_ref=17, duration_projection=12)\n",
"X_test_segment"
]
},
{
"cell_type": "code",
"execution_count": 124,
"id": "22222709-218e-43b5-815f-714dfb776230",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 9.609600e+04\n",
"mean 2.182217e+02\n",
"std 7.120650e+03\n",
"min 0.000000e+00\n",
"25% 0.000000e+00\n",
"50% 0.000000e+00\n",
"75% 6.100000e+01\n",
"max 1.209751e+06\n",
"Name: total_amount_corrected, dtype: float64"
]
},
"execution_count": 124,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[\"total_amount_corrected\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": 111,
"id": "73404bdd-e2f2-40e0-8bde-224c460426c5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 44105.000000\n",
"mean 35.661188\n",
"std 71.477667\n",
"min -216.368182\n",
"25% 10.000000\n",
"50% 25.000000\n",
"75% 48.720000\n",
"max 4000.000000\n",
"Name: avg_ticket_price, dtype: float64"
]
},
"execution_count": 111,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[\"avg_ticket_price\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": 113,
"id": "f96536d3-fff7-4ccf-be3d-34e671852cd8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.052634865134865136"
]
},
"execution_count": 113,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(X_test_segment[\"total_amount_projected\"]==0).mean()"
]
},
{
"cell_type": "code",
"execution_count": 115,
"id": "884416e8-edec-4f6b-a40f-1a7c5d653160",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 4.442483\n",
"std 64.952589\n",
"min 1.000000\n",
"25% 1.000000\n",
"50% 1.000000\n",
"75% 1.411765\n",
"max 11472.000000\n",
"Name: nb_tickets_projected, dtype: float64"
]
},
"execution_count": 115,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[\"nb_tickets_projected\"].describe()"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "cb66a8ea-65f7-460f-b3fc-ba76a3b91faa",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"quartile\n",
"1 15.330011\n",
"2 15.314322\n",
"3 14.031588\n",
"4 8.562546\n",
"Name: pace_purchase, dtype: float64"
]
},
"execution_count": 35,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment.groupby(\"quartile\")[\"pace_purchase\"].mean()"
]
},
{
"cell_type": "code",
"execution_count": 128,
"id": "8a4eec5c-8a4d-4a2b-9afb-1d49c77f78ea",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 162.000000\n",
"mean 3112.018089\n",
"std 8392.717823\n",
"min 51.843098\n",
"25% 161.889295\n",
"50% 395.635139\n",
"75% 2141.696184\n",
"max 69988.895986\n",
"dtype: float64"
]
},
"execution_count": 128,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"(X_test[((X_test[\"total_amount_corrected\"] - X_test[\"total_amount\"])>0)][\"total_amount_corrected\"]\n",
" -X_test[((X_test[\"total_amount_corrected\"] - X_test[\"total_amount\"])>0)][\"total_amount\"]) .describe()"
]
},
{
"cell_type": "code",
"execution_count": 118,
"id": "f58f9151-2f91-45df-abb7-1ddcf0652adc",
"metadata": {},
"outputs": [],
"source": [
"# generalization with a function\n",
"\n",
"def summary_expected_CA(df, segment, nb_tickets_expected, total_amount_expected, total_amount, pace_purchase,\n",
" duration_ref=17, duration_projection=12) :\n",
" \n",
" # compute nb tickets estimated and total amount expected\n",
" df_expected_CA = df.groupby(segment)[[nb_tickets_expected, total_amount_expected]].sum().reset_index()\n",
" \n",
" # number of customers by segment\n",
" df_expected_CA.insert(1, \"size\", df.groupby(segment).size().values)\n",
" \n",
" # size in percent of all customers\n",
" df_expected_CA.insert(2, \"size_perct\", 100 * df_expected_CA[\"size\"]/df_expected_CA[\"size\"].sum())\n",
" \n",
" # compute share of CA recovered\n",
" duration_ratio=duration_ref/duration_projection\n",
" \n",
" df_expected_CA[\"revenue_recovered_perct\"] = 100 * duration_ratio * df_expected_CA[total_amount_expected] / \\\n",
" df.groupby(segment)[total_amount].sum().values\n",
"\n",
" df_expected_CA[\"share_future_revenue_perct\"] = 100 * duration_ratio * df_expected_CA[total_amount_expected] / \\\n",
" df[total_amount].sum()\n",
"\n",
" df_drop_null_pace = df.dropna(subset=[pace_purchase])\n",
" df_expected_CA[\"pace_purchase\"] = df_drop_null_pace.groupby(segment)[pace_purchase].mean().values\n",
" \n",
" return df_expected_CA"
]
},
{
"cell_type": "code",
"execution_count": 133,
"id": "c8df6c80-43e8-4f00-9cd3-eb9022744313",
"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>quartile</th>\n",
" <th>size</th>\n",
" <th>size_perct</th>\n",
" <th>nb_tickets_expected</th>\n",
" <th>total_amount_expected</th>\n",
" <th>revenue_recovered_perct</th>\n",
" <th>share_future_revenue_perct</th>\n",
" <th>pace_purchase</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>54123</td>\n",
" <td>56.32</td>\n",
" <td>1480.36</td>\n",
" <td>55345.21</td>\n",
" <td>11.99</td>\n",
" <td>0.37</td>\n",
" <td>15.33</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>18181</td>\n",
" <td>18.92</td>\n",
" <td>4381.84</td>\n",
" <td>130503.26</td>\n",
" <td>11.65</td>\n",
" <td>0.88</td>\n",
" <td>15.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>11111</td>\n",
" <td>11.56</td>\n",
" <td>8827.97</td>\n",
" <td>285945.50</td>\n",
" <td>24.00</td>\n",
" <td>1.93</td>\n",
" <td>14.03</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>12681</td>\n",
" <td>13.20</td>\n",
" <td>239758.61</td>\n",
" <td>10313321.91</td>\n",
" <td>85.74</td>\n",
" <td>69.67</td>\n",
" <td>8.56</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" quartile size size_perct nb_tickets_expected total_amount_expected \\\n",
"0 1 54123 56.32 1480.36 55345.21 \n",
"1 2 18181 18.92 4381.84 130503.26 \n",
"2 3 11111 11.56 8827.97 285945.50 \n",
"3 4 12681 13.20 239758.61 10313321.91 \n",
"\n",
" revenue_recovered_perct share_future_revenue_perct pace_purchase \n",
"0 11.99 0.37 15.33 \n",
"1 11.65 0.88 15.31 \n",
"2 24.00 1.93 14.03 \n",
"3 85.74 69.67 8.56 "
]
},
"execution_count": 133,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\"\"\"\n",
"X_test_expected_CA = round(summary_expected_CA(df=X_test_segment, segment=\"quartile\", \n",
" nb_tickets_expected=\"nb_tickets_expected\", total_amount_expected=\"total_amount_expected\", \n",
" total_amount=\"total_amount\", pace_purchase=\"pace_purchase\"),2)\n",
" \"\"\"\n",
"X_test_expected_CA = round(summary_expected_CA(df=X_test_segment, segment=\"quartile\", \n",
" nb_tickets_expected=\"nb_tickets_expected\", total_amount_expected=\"total_amount_expected\", \n",
" total_amount=\"total_amount_corrected\", pace_purchase=\"pace_purchase\"),2)\n",
"X_test_expected_CA"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dd25c898-9991-4cc4-8e69-160b61fea0c4",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": 116,
"id": "63369c2a-a842-4b03-aa11-230287cb3b69",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"count 96096.000000\n",
"mean 4.442483\n",
"std 64.952589\n",
"min 1.000000\n",
"25% 1.000000\n",
"50% 1.000000\n",
"75% 1.411765\n",
"max 11472.000000\n",
"Name: nb_tickets_projected, dtype: float64\n"
]
},
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 2.647860\n",
"std 59.108910\n",
"min 0.001335\n",
"25% 0.015281\n",
"50% 0.044399\n",
"75% 0.230742\n",
"max 11450.589975\n",
"Name: nb_tickets_expected, dtype: float64"
]
},
"execution_count": 116,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"print(X_test_segment[\"nb_tickets_projected\"].describe())\n",
"X_test_segment[\"nb_tickets_expected\"].describe()\n"
]
},
{
"cell_type": "code",
"execution_count": 117,
"id": "72af97dc-8558-4591-adcf-ad404c9cb3f2",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"quartile\n",
"1 0.029070\n",
"2 0.074526\n",
"3 0.078737\n",
"4 0.817668\n",
"Name: total_amount, dtype: float64"
]
},
"execution_count": 117,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# we can recover share future revenue by multipling the share of amount by quartile * revenue recovered\n",
"X_test_segment.groupby(\"quartile\")[\"total_amount\"].sum()/X_test_segment[\"total_amount\"].sum()"
]
},
{
"cell_type": "code",
"execution_count": 64,
"id": "ac706ed7-defa-4df1-82e1-06f12fc1b6ad",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'\\\\begin{tabular}{lrrrrrr}\\n\\\\toprule\\nquartile & size & size (%) & nb tickets expected & total amount expected & revenue recovered (%) & pace purchase \\\\\\\\\\n\\\\midrule\\n1 & 53626 & 35.310000 & 398.260000 & 13949.330000 & 2.350000 & 16.480000 \\\\\\\\\\n2 & 55974 & 36.860000 & 3113.770000 & 101639.450000 & 6.240000 & 16.470000 \\\\\\\\\\n3 & 30435 & 20.040000 & 6214.350000 & 208267.220000 & 14.270000 & 15.710000 \\\\\\\\\\n4 & 11839 & 7.800000 & 72929.460000 & 1835702.430000 & 75.380000 & 11.480000 \\\\\\\\\\n\\\\bottomrule\\n\\\\end{tabular}\\n'"
]
},
"execution_count": 64,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Création du dictionnaire de mapping pour les noms de colonnes\n",
"mapping_dict = {col: col.replace(\"perct\", \"(%)\").replace(\"_\", \" \") for col in X_test_expected_CA.columns}\n",
"\n",
"X_test_expected_CA.rename(columns=mapping_dict).to_latex(index=False)"
]
},
{
"cell_type": "code",
"execution_count": 122,
"id": "771da0cf-c49f-4e7e-b52f-ebcfb0fb2df3",
"metadata": {},
"outputs": [],
"source": [
"# export summary table to the MinIO storage\n",
"\n",
"file_name = \"table_expected_CA_\"\n",
"FILE_PATH_OUT_S3 = PATH + file_name + type_of_activity + \".csv\"\n",
"with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:\n",
" X_test_expected_CA.to_csv(file_out, index = False)"
]
},
{
"cell_type": "code",
"execution_count": 53,
"id": "c805dc10-4d07-4f7d-a677-5461a92845d7",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'projet-bdc2324-team1/Output_expected_CA/musique/table_expected_CA_musique.csv'"
]
},
"execution_count": 53,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"PATH = f\"projet-bdc2324-team1/Output_expected_CA/{type_of_activity}/\"\n",
"file_name = \"table_expected_CA_\"\n",
"FILE_PATH_OUT_S3 = PATH + file_name + type_of_activity + \".csv\"\n",
"FILE_PATH_OUT_S3"
]
},
{
"cell_type": "markdown",
"id": "e35ccfff-1845-41f0-9bde-f09b09b67877",
"metadata": {},
"source": [
"## Test : vizu tables saved"
]
},
{
"cell_type": "code",
"execution_count": 66,
"id": "4e9e88e4-ea10-41f4-9bf1-20b55269a20d",
"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>quartile</th>\n",
" <th>score (%)</th>\n",
" <th>score adjusted (%)</th>\n",
" <th>has purchased (%)</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>13.25</td>\n",
" <td>2.51</td>\n",
" <td>1.57</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>33.89</td>\n",
" <td>8.00</td>\n",
" <td>9.85</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>63.06</td>\n",
" <td>22.58</td>\n",
" <td>21.47</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>90.52</td>\n",
" <td>66.20</td>\n",
" <td>65.01</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" quartile score (%) score adjusted (%) has purchased (%)\n",
"0 1 13.25 2.51 1.57\n",
"1 2 33.89 8.00 9.85\n",
"2 3 63.06 22.58 21.47\n",
"3 4 90.52 66.20 65.01"
]
},
"execution_count": 66,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"path = 'projet-bdc2324-team1/Output_expected_CA/sport/table_adjusted_scoresport.csv'\n",
"\n",
"with fs.open( path, mode=\"rb\") as file_in:\n",
" df = pd.read_csv(file_in, sep=\",\")\n",
"df"
]
},
{
"cell_type": "markdown",
"id": "9c471bdd-25c2-420a-a8a1-3add9f003cbc",
"metadata": {},
"source": [
"## Just to try, same computation with score instead of score adjusted\n",
"\n",
"seems overestimated : if only 14% of customers come back, how can we recover 22% of the revenue from the segment that is least likely to buy ?? ..."
]
},
{
"cell_type": "code",
"execution_count": 80,
"id": "53684a24-1809-465f-8e21-b9295e34582a",
"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>quartile</th>\n",
" <th>size</th>\n",
" <th>size_perct</th>\n",
" <th>nb_tickets_expected</th>\n",
" <th>total_amount_expected</th>\n",
" <th>perct_revenue_recovered</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>37410</td>\n",
" <td>38.93</td>\n",
" <td>419.76</td>\n",
" <td>9245.08</td>\n",
" <td>21.71</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>29517</td>\n",
" <td>30.72</td>\n",
" <td>11549.06</td>\n",
" <td>296522.02</td>\n",
" <td>39.24</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>20137</td>\n",
" <td>20.96</td>\n",
" <td>29997.85</td>\n",
" <td>954751.91</td>\n",
" <td>63.34</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>9032</td>\n",
" <td>9.40</td>\n",
" <td>244655.82</td>\n",
" <td>10736011.95</td>\n",
" <td>97.72</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" quartile size size_perct nb_tickets_expected total_amount_expected \\\n",
"0 1 37410 38.93 419.76 9245.08 \n",
"1 2 29517 30.72 11549.06 296522.02 \n",
"2 3 20137 20.96 29997.85 954751.91 \n",
"3 4 9032 9.40 244655.82 10736011.95 \n",
"\n",
" perct_revenue_recovered \n",
"0 21.71 \n",
"1 39.24 \n",
"2 63.34 \n",
"3 97.72 "
]
},
"execution_count": 80,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment_bis = project_tickets_CA (X_test_segment, \"nb_tickets\", \"total_amount\", \"score\", duration_ref=1.5, duration_projection=1)\n",
"\n",
"X_test_expected_CA_bis = round(summary_expected_CA(df=X_test_segment_bis, segment=\"quartile\", nb_tickets_expected=\"nb_tickets_expected\", \n",
" total_amount_expected=\"total_amount_expected\", total_amount=\"total_amount\"),2)\n",
"\n",
"X_test_expected_CA_bis"
]
},
{
"cell_type": "code",
"execution_count": 81,
"id": "7dc66d1e-da03-4513-96e4-d9a43ac0a2c8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"overall share of revenue recovered : 90.26 %\n"
]
}
],
"source": [
"print(\"overall share of revenue recovered : \", round(100 * duration_ratio * X_test_expected_CA_bis[\"total_amount_expected\"].sum() / \\\n",
"X_test_segment_bis[\"total_amount\"].sum(),2), \"%\")"
]
},
{
"cell_type": "markdown",
"id": "673f2969-7b9a-44c1-abf5-5679fca877ce",
"metadata": {},
"source": [
"## Last pieces of analysis"
]
},
{
"cell_type": "code",
"execution_count": 161,
"id": "2365bb13-0f3f-49d5-bf91-52c92abebcee",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"overall share of revenue recovered : 77.64%\n"
]
}
],
"source": [
"# global revenue recovered\n",
"global_revenue_recovered = round(100 * duration_ratio * X_test_expected_CA[\"total_amount_expected\"].sum() / \\\n",
"X_test_segment[\"total_amount\"].sum(),2)\n",
"print(f\"overall share of revenue recovered : {global_revenue_recovered}%\")"
]
},
{
"cell_type": "code",
"execution_count": 163,
"id": "16b17f35-57dd-459a-8989-129143dc0952",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 0.018093\n",
"1 0.721519\n",
"2 3.336101\n",
"3 95.924287\n",
"Name: total_amount_expected, dtype: float64"
]
},
"execution_count": 163,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"100 * X_test_expected_CA[\"total_amount_expected\"]/X_test_expected_CA[\"total_amount_expected\"].sum()"
]
},
{
"cell_type": "code",
"execution_count": 166,
"id": "dee4a200-eefe-4377-8e80-59ad33edd3c0",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"quartile\n",
"1 0.320407\n",
"2 5.685020\n",
"3 11.339715\n",
"4 82.654858\n",
"Name: total_amount, dtype: float64"
]
},
"execution_count": 166,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# le segment 4 représente 83% du CA actuel et 96% du CA lié aux anciens clients pour l'année prochaine\n",
"100 * X_test_segment.groupby(\"quartile\")[\"total_amount\"].sum()/X_test_segment[\"total_amount\"].sum()"
]
},
{
"cell_type": "code",
"execution_count": 177,
"id": "c1e6f020-ef18-40b4-bfc1-19f98cb2796e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"count 96096.000000\n",
"mean 207.475735\n",
"std 4720.046248\n",
"min -48831.800000\n",
"25% 0.000000\n",
"50% 0.000000\n",
"75% 60.000000\n",
"max 624890.000000\n",
"Name: total_amount, dtype: float64"
]
},
"execution_count": 177,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_test_segment[\"total_amount\"].describe() # total amount négatif ???\n"
]
},
{
"cell_type": "code",
"execution_count": 184,
"id": "d301a50e-7c68-40f0-9245-a4eea64c387b",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0 -4.883180e+04\n",
"1 -6.483180e+04\n",
"2 -7.683860e+04\n",
"3 -8.683860e+04\n",
"4 -9.683860e+04\n",
" ... \n",
"96091 1.802247e+07\n",
"96092 1.839238e+07\n",
"96093 1.877219e+07\n",
"96094 1.931270e+07\n",
"96095 1.993759e+07\n",
"Name: total_amount, Length: 96096, dtype: float64"
]
},
"execution_count": 184,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"np.cumsum(X_test_segment[\"total_amount\"].sort_values()).reset_index()[\"total_amount\"]"
]
}
],
"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
}
Reference in New Issue View Git Blame Copy Permalink