ajoubrel-ensae/BDC-team-1
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
c7ca8c560e
BDC-team-1/Sport/Descriptive_statistics/stat_desc_sport.ipynb

1435 lines
220 KiB
Plaintext
Raw Normal View History

work on stat desc sport
2024-03-04 16:55:58 +01:00
{
"cells": [
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 6,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "dd143b00-1989-44cf-8558-a30087d17f70",
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import os\n",
"import s3fs\n",
"import warnings\n",
"from datetime import date, timedelta, datetime\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 2,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "08c63120-1b56-4145-9014-18a637b22876",
"metadata": {},
"outputs": [],
"source": [
"exec(open('../../0_KPI_functions.py').read())"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 3,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "f8bd679d-fa76-49d4-9ec1-9f15516f16d3",
"metadata": {},
"outputs": [],
"source": [
"# Ignore warning\n",
"warnings.filterwarnings('ignore')"
]
},
{
"cell_type": "markdown",
"id": "ec9e996d-3eae-4836-8cf5-268e5dc0d672",
"metadata": {},
"source": [
"# Statistiques descriptives : compagnies sport"
]
},
{
"cell_type": "markdown",
"id": "43f81515-fbd0-49c0-b3f8-0e0fb663e2c1",
"metadata": {},
"source": [
"## Importations et chargement des données"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 7,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "945c59bb-05b4-4f21-82f0-0db40d7957b3",
"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",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 5,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "41a67995-0a08-45c0-bbad-6e6cee5474c8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : projet-bdc2324-team1/0_Input/Company_5/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_5/campaigns_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_5/products_purchased_reduced.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_5/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_6/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_6/campaigns_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_6/products_purchased_reduced.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_6/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_7/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_7/campaigns_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_7/products_purchased_reduced.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_7/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_8/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_8/campaigns_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_8/products_purchased_reduced.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_8/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_9/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_9/campaigns_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_9/products_purchased_reduced.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_9/target_information.csv\n"
]
}
],
"source": [
"# création des bases contenant les KPI pour les 5 compagnies de spectacle\n",
"\n",
"# liste des compagnies de spectacle\n",
"nb_compagnie=['5','6','7','8','9']\n",
"\n",
"customer_sport = pd.DataFrame()\n",
"campaigns_sport = pd.DataFrame()\n",
"products_sport = pd.DataFrame()\n",
"tickets_sport = pd.DataFrame()\n",
"\n",
"# début de la boucle permettant de générer des datasets agrégés pour les 5 compagnies de spectacle\n",
"for directory_path in nb_compagnie:\n",
" df_customerplus_clean_0 = display_databases(directory_path, file_name = \"customerplus_cleaned\")\n",
" df_campaigns_information = display_databases(directory_path, file_name = \"campaigns_information\", datetime_col = ['opened_at', 'sent_at', 'campaign_sent_at'])\n",
" df_products_purchased_reduced = display_databases(directory_path, file_name = \"products_purchased_reduced\", datetime_col = ['purchase_date'])\n",
" df_target_information = display_databases(directory_path, file_name = \"target_information\")\n",
" \n",
" df_campaigns_kpi = campaigns_kpi_function(campaigns_information = df_campaigns_information) \n",
" df_tickets_kpi = tickets_kpi_function(tickets_information = df_products_purchased_reduced)\n",
" df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0)\n",
"\n",
" \n",
"# creation de la colonne Number compagnie, qui permettra d'agréger les résultats\n",
" df_tickets_kpi[\"number_company\"]=int(directory_path)\n",
" df_campaigns_kpi[\"number_company\"]=int(directory_path)\n",
" df_customerplus_clean[\"number_company\"]=int(directory_path)\n",
" df_target_information[\"number_company\"]=int(directory_path)\n",
"\n",
"# Traitement des index\n",
" df_tickets_kpi[\"customer_id\"]= directory_path + '_' + df_tickets_kpi['customer_id'].astype('str')\n",
" df_campaigns_kpi[\"customer_id\"]= directory_path + '_' + df_campaigns_kpi['customer_id'].astype('str') \n",
" df_customerplus_clean[\"customer_id\"]= directory_path + '_' + df_customerplus_clean['customer_id'].astype('str') \n",
" df_products_purchased_reduced[\"customer_id\"]= directory_path + '_' + df_products_purchased_reduced['customer_id'].astype('str') \n",
"\n",
"# Concaténation\n",
" customer_sport = pd.concat([customer_sport, df_customerplus_clean], ignore_index=True)\n",
" campaigns_sport = pd.concat([campaigns_sport, df_campaigns_kpi], ignore_index=True)\n",
" tickets_sport = pd.concat([tickets_sport, df_tickets_kpi], ignore_index=True)\n",
" products_sport = pd.concat([products_sport, df_products_purchased_reduced], ignore_index=True)\n",
" "
]
},
{
"cell_type": "markdown",
"id": "62922029-8071-402e-8115-c145a2874a2f",
"metadata": {},
"source": [
"## Statistiques descriptives"
]
},
{
"cell_type": "markdown",
"id": "d347bca9-3041-4414-b18e-19b626998a3e",
"metadata": {},
"source": [
"### 0. Détection du client anonyme (outlier) - utile pour la section 3"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 6,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "c4d4b2ad-8a3c-477b-bc52-dd4860527bfe",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([5, 6, 7, 8, 9])"
]
},
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 6,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"sport_comp = tickets_sport['number_company'].unique()\n",
"sport_comp"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 7,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "97a9e235-1c04-46bf-9f3c-5496e141cc40",
"metadata": {},
"outputs": [],
"source": [
"def outlier_detection(company_list, show_diagram=False):\n",
"\n",
" outlier_list = list()\n",
" \n",
" for company in company_list:\n",
" total_amount_share = tickets_sport[tickets_sport['number_company']==company].groupby('customer_id')['total_amount'].sum().reset_index()\n",
" total_amount_share['CA'] = total_amount_share['total_amount'].sum()\n",
" total_amount_share['share_total_amount'] = total_amount_share['total_amount']/total_amount_share['CA']\n",
" \n",
" total_amount_share_index = total_amount_share.set_index('customer_id')\n",
" df_circulaire = total_amount_share_index['total_amount'].sort_values(axis = 0, ascending = False)\n",
" top = df_circulaire[:1]\n",
" outlier_list.append(top.index[0])\n",
" rest = df_circulaire[1:]\n",
" \n",
" # Calculez la somme du reste\n",
" rest_sum = rest.sum()\n",
" \n",
" # Créez une nouvelle série avec les cinq plus grandes parts et 'Autre'\n",
" new_series = pd.concat([top, pd.Series([rest_sum], index=['Autre'])])\n",
" \n",
" # Créez le graphique circulaire\n",
" if show_diagram:\n",
" plt.figure(figsize=(3, 3))\n",
" plt.pie(new_series, labels=new_series.index, autopct='%1.1f%%', startangle=140, pctdistance=0.5)\n",
" plt.axis('equal') # Assurez-vous que le graphique est un cercle\n",
" plt.title(f'Répartition des montants totaux pour la compagnie {company}')\n",
" plt.show()\n",
" return outlier_list\n",
" "
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 8,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "770cd3fc-bfe2-4a69-89bc-0eb946311130",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['5_191835', '6_591412', '7_49632', '8_1942', '9_19683']"
]
},
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 8,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"outlier_list = outlier_detection(sport_comp)\n",
"outlier_list"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 9,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "70b6e961-c303-465e-93f4-609721d38454",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Suppression Réussie\n"
]
}
],
"source": [
"# On filtre les outliers\n",
"\n",
"def remove_elements(lst, elements_to_remove):\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" return ''.join([x for x in lst if x not in elements_to_remove])\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" \n",
"databases = [customer_sport, campaigns_sport, tickets_sport, products_sport]\n",
"\n",
"for dataset in databases:\n",
" dataset['customer_id'] = dataset['customer_id'].apply(lambda x: remove_elements(x, outlier_list))\n",
"\n",
"# On test\n",
"\n",
"bool = '5_191835' in customer_sport['customer_id']\n",
"if not bool:\n",
" print(\"Suppression Réussie\")"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 10,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "b54b920a-7b46-490f-ba7e-d1859055a4e3",
"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>gender</th>\n",
" <th>is_email_true</th>\n",
" <th>...</th>\n",
work on stat
2024-03-06 11:56:52 +01:00
" <th>total_price</th>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <th>purchase_count</th>\n",
" <th>first_buying_date</th>\n",
" <th>country</th>\n",
" <th>gender_label</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>country_fr</th>\n",
" <th>number_company</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" <td>5_6009745</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>1372685</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
work on stat
2024-03-06 11:56:52 +01:00
" <td>0.0</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>af</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" <td>5_6011228</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>1372685</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
work on stat
2024-03-06 11:56:52 +01:00
" <td>0.0</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>af</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" <td>5_6058950</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>1372685</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
work on stat
2024-03-06 11:56:52 +01:00
" <td>0.0</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>af</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" <td>5_6062404</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>1372685</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>2</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
work on stat
2024-03-06 11:56:52 +01:00
" <td>0.0</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>af</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0.0</td>\n",
" <td>5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" <td>5_250217</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>78785</td>\n",
" <td>NaN</td>\n",
" <td>11035.0</td>\n",
" <td>0</td>\n",
" <td>1771</td>\n",
" <td>False</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
work on stat
2024-03-06 11:56:52 +01:00
" <td>NaN</td>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" <td>0</td>\n",
" <td>NaN</td>\n",
" <td>fr</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>5</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
work on stat
2024-03-06 11:56:52 +01:00
"<p>5 rows × 28 columns</p>\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
"</div>"
],
"text/plain": [
work on stat desc
2024-03-04 19:29:21 +01:00
" customer_id street_id structure_id mcp_contact_id fidelity tenant_id \\\n",
"0 5_6009745 1372685 NaN NaN 0 1771 \n",
"1 5_6011228 1372685 NaN NaN 0 1771 \n",
"2 5_6058950 1372685 NaN NaN 0 1771 \n",
"3 5_6062404 1372685 NaN NaN 0 1771 \n",
"4 5_250217 78785 NaN 11035.0 0 1771 \n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
"\n",
work on stat
2024-03-06 11:56:52 +01:00
" is_partner deleted_at gender is_email_true ... total_price \\\n",
"0 False NaN 2 True ... 0.0 \n",
"1 False NaN 2 True ... 0.0 \n",
"2 False NaN 2 True ... 0.0 \n",
"3 False NaN 2 True ... 0.0 \n",
"4 False NaN 0 True ... NaN \n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
"\n",
work on stat
2024-03-06 11:56:52 +01:00
" purchase_count first_buying_date country gender_label gender_female \\\n",
"0 0 NaN af other 0 \n",
"1 0 NaN af other 0 \n",
"2 0 NaN af other 0 \n",
"3 0 NaN af other 0 \n",
"4 0 NaN fr female 1 \n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
"\n",
work on stat
2024-03-06 11:56:52 +01:00
" gender_male gender_other country_fr number_company \n",
"0 0 1 0.0 5 \n",
"1 0 1 0.0 5 \n",
"2 0 1 0.0 5 \n",
"3 0 1 0.0 5 \n",
"4 0 0 1.0 5 \n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
"\n",
work on stat
2024-03-06 11:56:52 +01:00
"[5 rows x 28 columns]"
work on stat desc sport
2024-03-04 16:55:58 +01:00
]
},
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 10,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"customer_sport.head()"
]
},
{
"cell_type": "markdown",
"id": "d40fe668-e1d7-4544-9db8-02498afe65fe",
"metadata": {},
"source": [
"### 1. customerplus_clean"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 11,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "eec1ac0b-2502-452b-97e6-69ffb77156d6",
"metadata": {},
"outputs": [],
"source": [
"def compute_nb_clients(customer_sport):\n",
" company_nb_clients = customer_sport[customer_sport[\"purchase_count\"]>0].groupby(\"number_company\")[\"customer_id\"].count().reset_index()\n",
" plt.bar(company_nb_clients[\"number_company\"], company_nb_clients[\"customer_id\"]/1000)\n",
"\n",
" # Ajout de titres et d'étiquettes\n",
" plt.xlabel('Company')\n",
" plt.ylabel(\"Nombre de clients (milliers)\")\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" plt.title(\"Nombre de clients de chaque compagnie de sport\")\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" \n",
" # Affichage du barplot\n",
" plt.show()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 12,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "db4494e7-6f65-4f7e-bf8c-8ec321d0b02d",
"metadata": {},
"outputs": [
{
"data": {
work on stat
2024-03-06 11:56:52 +01:00
"image/png": "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
work on stat desc sport
2024-03-04 16:55:58 +01:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"compute_nb_clients(customer_sport)"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 13,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "a12a59a0-edfe-4e52-8037-9b875f823b33",
"metadata": {},
"outputs": [],
"source": [
"def maximum_price_paid(customer_sport):\n",
" company_max_price = customer_sport.groupby(\"number_company\")[\"max_price\"].max().reset_index()\n",
" # Création du barplot\n",
" plt.bar(company_max_price[\"number_company\"], company_max_price[\"max_price\"])\n",
" \n",
" # Ajout de titres et d'étiquettes\n",
" plt.xlabel('Company')\n",
" plt.ylabel(\"Prix maximal d'un billet vendu\")\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" plt.title(\"Prix maximal de vente observé par compagnie de sport\")\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" \n",
" # Affichage du barplot\n",
" plt.show()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 14,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "2c7c2d26-4e35-4163-b771-fa4d3e8ca83e",
"metadata": {},
"outputs": [
{
"data": {
work on stat
2024-03-06 11:56:52 +01:00
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAk0AAAHGCAYAAABpZb/eAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABVsUlEQVR4nO3dd1gUV/828HulSV2KVEXAEhTBniCowYZoAGNJLCgCGo2xPUSJJdFYYteoUR9jmhhLxBQ0KjZiIRrAghpF0ccOKqhBBLEgLOf9Iz/mdQXMrEJ2wftzXXuFOXN25jvjljtnyiqEEAJERERE9Fw1tF0AERERUVXA0EREREQkA0MTERERkQwMTUREREQyMDQRERERycDQRERERCQDQxMRERGRDAxNRERERDIwNBERERHJwNBERKRlH3/8Mezt7XHp0iVtl0JEz8HQpGPWrFkDhUIhPfT19VGnTh1ERETgxo0bspYRHh4OV1fXyi1Ui0r20dWrV//1dV+9ehUKhQJr1qx5oecfOHAACoUCBw4cqNC6tGHHjh2YPn261tZf8jo4duyY1mqoCDt37sSKFSuwfft21K9fX9vlUCVSKBT/ynvG1dUV4eHhlb4ebUlMTMT06dNx7969f33dDE06Kjo6GklJSYiPj8ewYcOwceNGtG/fHg8ePPjH506dOhWbN2/+F6rUjsDAQCQlJcHR0VHbpbzSduzYgRkzZmi7jCotIyMDERER2LRpE15//XVtl0OVLCkpCe+99562y6jyEhMTMWPGDK2EJv1/fY0ki6enJ1q3bg0A6NixI1QqFT777DNs2bIFAwcOLPM5Dx8+hImJSbX/v1VbW1vY2tpquwwiScl7T1POzs7IysqqhIpe3otuE5WvTZs22i6hSnv06BFq1qyp1Ro40lRFlLzZrl27BuDvQ3BmZmY4ffo0unbtCnNzc3Tu3Fma9/ThuZiYGCgUCqxYsUJtmdOmTYOenh7i4+Ofu25XV1cEBQVh+/btaNGiBYyNjdG4cWNs374dwN+HSRo3bgxTU1O88cYbpQ6XHDt2DP3794erqyuMjY3h6uqKAQMGSNsCAEIIvPXWW7CxsUF6errU/vDhQzRp0gSNGzeWRtnKOjzXoUMHeHp6IikpCb6+vtJ6oqOjAQBxcXFo2bIlTExM4OXlhV27dqnVePHiRURERKBhw4YwMTFB7dq1ERwcjNOnTz933zzPuXPn0K1bN5iYmKBWrVoYMWIE7t+/X2bf3377DZ07d4aFhQVMTEzQtm1b7N2797nLv3PnDgwNDTF16tQy161QKLBs2TKpLSsrC++//z7q1KkDQ0NDuLm5YcaMGSgqKpL6lBx+XLRoERYvXgw3NzeYmZnBx8cHycnJUr/w8HD897//BQC1w8kl/yZCCKxcuRLNmzeHsbExrKys8M477+Dy5cuy9t2hQ4fQuXNnmJubw8TEBL6+voiLiyuzb05ODiIiImBtbQ1TU1MEBweXWs+JEycQFBQEOzs7GBkZwcnJCYGBgbh+/brUR27NJa+133//Hb6+vjAxMcGQIUPQs2dPuLi4oLi4uFSN3t7eaNmypcbrKsv06dOhUChw4sQJ9O7dGxYWFlAqlRg0aBDu3Lmj1nfTpk3o2rUrHB0dpfftpEmTSo1YP+/zpDznzp3DgAEDYG9vDyMjI9StWxeDBw9GQUGB1Cc1NRVvv/02rKysULNmTTRv3hzff/+92nJKDln/8MMPmDhxIhwdHWFmZobg4GDcunUL9+/fx/Dhw1GrVi3UqlULERERyM/PV1uGQqHA6NGj8dVXX+G1116DkZERPDw8EBMTo9bvzp07GDlyJDw8PGBmZgY7Ozt06tQJBw8eLLV9169fxzvvvANzc3NYWlpi4MCBOHr0aKnD8yX77uLFi3jrrbdgZmYGZ2dnjB8/Xm1flNT57OE5Oe/L8hQWFmLChAlwcHCAiYkJ2rVrhyNHjpTZ92XWs2/fPnTo0AE2NjYwNjZG3bp10adPHzx8+BDA///cWLBgAWbPno26deuiZs2aaN26dZmfY3Le3yWf83v27MGQIUNga2sLExMTTJ48GR999BEAwM3NTfrs+ddOeRCkU6KjowUAcfToUbX2L774QgAQX3/9tRBCiLCwMGFgYCBcXV3F3Llzxd69e8Xu3buleS4uLmrPHzFihDA0NJSWu3fvXlGjRg0xZcqUf6zJxcVF1KlTR3h6eoqNGzeKHTt2CG9vb2FgYCA+/fRT0bZtWxEbGys2b94sXnvtNWFvby8ePnwoPf+nn34Sn376qdi8ebNISEgQMTExws/PT9ja2oo7d+5I/f766y9Rp04d4e3tLZ48eSJti7GxsTh16lSpfXTlyhWpzc/PT9jY2Ah3d3fx3Xffid27d4ugoCABQMyYMUN4eXlJtbdp00YYGRmJGzduSM9PSEgQ48ePFz///LNISEgQmzdvFj179hTGxsbi3LlzUr8rV64IACI6Ovq5+ywrK0vY2dmJ2rVri+joaLFjxw4xcOBAUbduXQFA7N+/X+q7bt06oVAoRM+ePUVsbKzYtm2bCAoKEnp6euK333577np69eolnJ2dhUqlUmufMGGCMDQ0FH/99ZcQQojMzEzh7OwsXFxcxFdffSV+++038dlnnwkjIyMRHh5eavtcXV1Ft27dxJYtW8SWLVuEl5eXsLKyEvfu3RNCCHHx4kXxzjvvCAAiKSlJejx+/FgIIcSwYcOEgYGBGD9+vNi1a5f44YcfRKNGjYS9vb3Iysp67jYdOHBAGBgYiFatWolNmzaJLVu2iK5duwqFQiFiYmKkfiWvA2dnZzFkyBCxc+dO8fXXXws7Ozvh7OwscnJyhBBC5OfnCxsbG9G6dWvx448/ioSEBLFp0yYxYsQIcfbsWWl5cmv28/MT1tbWwtnZWSxfvlzs379fJCQkiF9//VUAEPHx8Wrbk5aWJgCIZcuWabyuskybNk0AEC4uLuKjjz4Su3fvFosXLxampqaiRYsW0ntHCCE+++wzsWTJEhEXFycOHDggVq1aJdzc3ETHjh3Vlvm8z5OynDx5UpiZmQlXV1exatUqsXfvXrF+/XrRt29fkZeXJ4QQ4ty5c8Lc3FzUr19frF27VsTFxYkBAwYIAGL+/PnSsvbv3y9tT3h4uNi1a5dYtWqVMDMzEx07dhT+/v4iKipK7NmzR8yfP1/o6emJMWPGqNVT8jrw8PAQGzduFFu3bhXdunUTAMRPP/0k9Tt37pz44IMPRExMjDhw4IDYvn27GDp0qKhRo4baezI/P180aNBAWFtbi//+979i9+7d4sMPPxRubm6l3v9hYWHC0NBQNG7cWCxatEj89ttv4tNPPxUKhULMmDGjVJ3Tpk2TpuW+L8sTFhYmFAqF+Oijj8SePXvE4sWLRe3atYWFhYUICwurkPVcuXJF1KxZU/j7+4stW7aIAwcOiA0bNojQ0FDpPVbyueHs7CzatWsnfvnlF/HTTz+J119/XRgYGIjExERpeZq+v2vXri2GDx8udu7cKX7++Wdx9epVMWbMGAFAxMbGSp89ubm5/7i/KgJDk44peaEkJyeLwsJCcf/+fbF9+3Zha2srzM3NpQ/UsLAwAUCsXr261DLKCk2PHz8WLVq0EG5ubuLs2bPC3t5e+Pn5iaKion+sycXFRRgbG4vr169LbSdPnhQAhKOjo3jw4IHUvmXLFgFAbN26tdzlFRUVifz8fGFqaiq++OILtXmHDh0S+vr6IjIyUqxevVoAEN9++22Z++jZ0ARAHDt2TGrLzs4Wenp6wtjYWC0gldT+9JdYWTU+efJENGzYUHz44YdSu9zQNHHiRKFQKMTJkyfV2v39/dVC04MHD4S1tbUIDg5W66dSqUSzZs3EG2+88dz1bN26VQAQe/bsUavdyclJ9OnTR2p7//33hZmZmbh27Zra8xctWiQAiDNnzqhtn5eXl9pr48iRIwKA2Lhxo9Q2atQoUdb/dyUlJQkA4vPPP1drz8jIEMbGxmLChAnP3aY2bdoIOzs7cf/+fbVt8vT0FHXq1BHFxcVCiP//OujVq5fa8//44w8BQMyaNUsIIcSxY8c
work on stat desc sport
2024-03-04 16:55:58 +01:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"maximum_price_paid(customer_sport)"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 15,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "597d4361-8beb-43f4-9224-8f7dc34b187c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Statistiques Descriptives company 5\n",
" average_price average_price_basket average_ticket_basket \\\n",
"count 145390.000000 68869.000000 68869.000000 \n",
"mean 11.070309 65.969693 3.655202 \n",
"std 16.353610 195.462869 13.119612 \n",
"min 0.000000 0.000000 1.000000 \n",
"25% 0.000000 20.000000 1.000000 \n",
"50% 0.000000 45.000000 2.000000 \n",
"75% 20.000000 79.500000 3.000000 \n",
"max 500.000000 24159.405000 2139.833333 \n",
"\n",
" purchase_count total_price \n",
"count 471598.00000 3.950770e+05 \n",
"mean 0.29900 2.608544e+01 \n",
"std 7.22753 2.089636e+03 \n",
"min 0.00000 0.000000e+00 \n",
"25% 0.00000 0.000000e+00 \n",
"50% 0.00000 0.000000e+00 \n",
"75% 0.00000 0.000000e+00 \n",
"max 3532.00000 1.262516e+06 \n",
"Statistiques Descriptives company 6\n",
" average_price average_price_basket average_ticket_basket \\\n",
"count 33779.000000 33779.000000 33779.000000 \n",
"mean 24.033859 56.711279 2.413530 \n",
"std 21.217031 72.841926 3.763809 \n",
"min -52.740000 -1046.666667 1.000000 \n",
"25% 10.000000 19.000000 1.080000 \n",
"50% 19.333333 39.000000 2.000000 \n",
"75% 30.000000 72.990000 3.000000 \n",
"max 199.990000 3922.845361 309.047619 \n",
"\n",
" purchase_count total_price \n",
"count 79938.000000 79938.000000 \n",
"mean 2.842090 102.251041 \n",
"std 74.949889 4290.159858 \n",
"min 0.000000 -3140.000000 \n",
"25% 0.000000 0.000000 \n",
"50% 0.000000 0.000000 \n",
"75% 1.000000 54.980000 \n",
"max 14750.000000 762695.290000 \n",
"Statistiques Descriptives company 7\n",
" average_price average_price_basket average_ticket_basket \\\n",
"count 39524.000000 39524.000000 39524.000000 \n",
"mean 33.110568 155.618778 3.365885 \n",
"std 85.221328 1085.613137 6.283143 \n",
"min 0.000000 0.000000 1.000000 \n",
"25% 17.250000 25.000000 1.800000 \n",
"50% 25.000000 57.676364 2.000000 \n",
"75% 43.054691 115.837500 3.555556 \n",
"max 10770.000000 86160.000000 400.000000 \n",
"\n",
" purchase_count total_price \n",
"count 68800.000000 68800.000000 \n",
"mean 3.290029 944.593729 \n",
"std 88.071870 12118.394731 \n",
"min 0.000000 0.000000 \n",
"25% 0.000000 0.000000 \n",
"50% 1.000000 9.000000 \n",
"75% 2.000000 132.000000 \n",
"max 22934.000000 940874.200000 \n",
"Statistiques Descriptives company 8\n",
" average_price average_price_basket average_ticket_basket \\\n",
"count 129198.000000 129198.000000 129198.000000 \n",
"mean 18.409977 38.492520 2.258036 \n",
"std 19.159059 71.136628 5.270858 \n",
"min -20.000000 -1545.000000 1.000000 \n",
"25% 0.000000 0.000000 1.000000 \n",
"50% 15.000000 20.000000 2.000000 \n",
"75% 28.461538 52.500000 2.000000 \n",
"max 390.000000 7618.227273 750.000000 \n",
"\n",
" purchase_count total_price \n",
"count 197376.000000 197376.000000 \n",
"mean 4.637448 130.336075 \n",
"std 96.228665 2791.899946 \n",
"min 0.000000 -36124.000000 \n",
"25% 0.000000 0.000000 \n",
"50% 1.000000 0.000000 \n",
"75% 2.000000 75.000000 \n",
"max 40272.000000 702080.290000 \n",
"Statistiques Descriptives company 9\n",
" average_price average_price_basket average_ticket_basket \\\n",
"count 102710.000000 102710.000000 102710.000000 \n",
"mean 60.312171 62.384177 1.042402 \n",
"std 50.018101 52.009984 0.268064 \n",
"min -291.670000 -291.670000 1.000000 \n",
"25% 41.500000 42.350000 1.000000 \n",
"50% 59.000000 61.070000 1.000000 \n",
"75% 74.550000 77.710000 1.000000 \n",
"max 1116.500000 1216.950000 23.000000 \n",
"\n",
" purchase_count total_price \n",
"count 181134.000000 181134.000000 \n",
"mean 1.021354 63.476966 \n",
"std 1.805412 129.781944 \n",
"min 0.000000 -291.670000 \n",
"25% 0.000000 0.000000 \n",
"50% 1.000000 0.000000 \n",
"75% 1.000000 80.000000 \n",
"max 273.000000 14343.950000 \n"
]
}
],
"source": [
"for company in sport_comp:\n",
" print(f'Statistiques Descriptives company {company}')\n",
" company_data = customer_sport[customer_sport['number_company'] == company][['average_price', 'average_price_basket',\n",
" 'average_ticket_basket', 'purchase_count', 'total_price']]\n",
" print(company_data.describe())"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 16,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "5058d3c9-73a0-4e01-881e-4d2423f0d291",
"metadata": {},
"outputs": [],
"source": [
"customer_sport[\"already_purchased\"] = customer_sport[\"purchase_count\"] > 0"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 17,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "848963c9-6129-4106-80b5-76bf814b70d1",
"metadata": {},
"outputs": [],
"source": [
"def mailing_consent(customer_sport):\n",
" df_graph = customer_sport.groupby([\"number_company\", \"already_purchased\"])[\"opt_in\"].mean().reset_index()\n",
" # Création du barplot groupé\n",
" fig, ax = plt.subplots(figsize=(10, 6))\n",
" \n",
" categories = df_graph[\"number_company\"].unique()\n",
" bar_width = 0.35\n",
" bar_positions = np.arange(len(categories))\n",
" \n",
" # Grouper les données par label et créer les barres groupées\n",
" for label in df_graph[\"already_purchased\"].unique():\n",
" label_data = df_graph[df_graph['already_purchased'] == label]\n",
" values = [label_data[label_data['number_company'] == category]['opt_in'].values[0]*100 for category in categories]\n",
" \n",
" label_printed = \"purchased\" if label else \"no purchase\"\n",
" ax.bar(bar_positions, values, bar_width, label=label_printed)\n",
" \n",
" # Mise à jour des positions des barres pour le prochain groupe\n",
" bar_positions = [pos + bar_width for pos in bar_positions]\n",
" \n",
" # Ajout des étiquettes, de la légende, etc.\n",
" ax.set_xlabel('Numero de compagnie')\n",
" ax.set_ylabel('Part de consentement (%)')\n",
" ax.set_title('Part de consentement au mailing selon les compagnies')\n",
" ax.set_xticks([pos + bar_width / 2 for pos in np.arange(len(categories))])\n",
" ax.set_xticklabels(categories)\n",
" ax.legend()\n",
" \n",
" # Affichage du plot\n",
" plt.show()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 18,
work on stat desc
2024-03-04 19:29:21 +01:00
"id": "b78ef715-c645-4625-a128-4f5b49e5339d",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 1000x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"mailing_consent(customer_sport)"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 19,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "d8071891-e6f5-4d93-b039-9e99c20ec4b0",
"metadata": {},
"outputs": [],
"source": [
"def gender_bar(customer_sport):\n",
" company_genders = customer_sport.groupby(\"number_company\")[[\"gender_male\", \"gender_female\", \"gender_other\"]].mean().reset_index()\n",
" # Création du barplot\n",
" plt.bar(company_genders[\"number_company\"], company_genders[\"gender_male\"], label = \"Homme\")\n",
" plt.bar(company_genders[\"number_company\"], company_genders[\"gender_female\"], \n",
" bottom = company_genders[\"gender_male\"], label = \"Femme\")\n",
" \n",
" \n",
" # Ajout de titres et d'étiquettes\n",
" plt.xlabel('Company')\n",
" plt.ylabel(\"Part de clients de chaque sexe\")\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" plt.title(\"Sexe des clients de chaque compagnie de sport\")\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" plt.legend()\n",
" \n",
" # Affichage du barplot\n",
" plt.show()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 20,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "2fc30f1d-cf64-4efb-9442-4d97bb50b29f",
"metadata": {},
work on stat desc
2024-03-04 19:29:21 +01:00
"outputs": [
{
"data": {
work on stat
2024-03-06 11:56:52 +01:00
"image/png": "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
work on stat desc
2024-03-04 19:29:21 +01:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
work on stat desc sport
2024-03-04 16:55:58 +01:00
"source": [
work on stat desc
2024-03-04 19:29:21 +01:00
"gender_bar(customer_sport)"
work on stat desc sport
2024-03-04 16:55:58 +01:00
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 21,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "4b3bb641-814b-4679-9a67-4eca87a920a6",
"metadata": {},
"outputs": [],
"source": [
"def country_bar(customer_sport):\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" company_country_fr = customer_sport.groupby(\"number_company\")[\"country_fr\"].mean().reset_index()\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" # Création du barplot\n",
" plt.bar(company_country_fr[\"number_company\"], company_country_fr[\"country_fr\"])\n",
" \n",
" # Ajout de titres et d'étiquettes\n",
" plt.xlabel('Company')\n",
" plt.ylabel(\"Part de clients français\")\n",
work on stat desc
2024-03-04 19:29:21 +01:00
" plt.title(\"Nationalité des clients de chaque compagnie de sport\")\n",
work on stat desc sport
2024-03-04 16:55:58 +01:00
" \n",
" # Affichage du barplot\n",
" plt.show()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 22,
work on stat desc sport
2024-03-04 16:55:58 +01:00
"id": "01258674-6b98-49e4-93f4-f4185964999f",
"metadata": {},
work on stat desc
2024-03-04 19:29:21 +01:00
"outputs": [
{
"data": {
work on stat
2024-03-06 11:56:52 +01:00
"image/png": "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
work on stat desc
2024-03-04 19:29:21 +01:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"country_bar(customer_sport)"
]
},
{
"cell_type": "markdown",
"id": "43d63ea3-75f4-4356-a7e9-35905d86baa5",
"metadata": {},
"source": [
"### 2. campaigns_information"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 23,
work on stat desc
2024-03-04 19:29:21 +01:00
"id": "8d116e34-cdd6-4ef9-8622-474da79f79ef",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Nombre de lignes de la table : 463098\n"
]
},
{
"data": {
"text/plain": [
"customer_id 0\n",
"nb_campaigns 0\n",
"nb_campaigns_opened 0\n",
"time_to_open 178826\n",
"number_company 0\n",
"dtype: int64"
]
},
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 23,
work on stat desc
2024-03-04 19:29:21 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"print(\"Nombre de lignes de la table : \",campaigns_sport.shape[0])\n",
"campaigns_sport.isna().sum()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 24,
work on stat desc
2024-03-04 19:29:21 +01:00
"id": "724d3c33-c219-4212-b8b6-dd78481674cb",
"metadata": {},
work on stat desc sport
2024-03-04 16:55:58 +01:00
"outputs": [],
"source": [
work on stat desc
2024-03-04 19:29:21 +01:00
"campaigns_sport[\"no_campaign_opened\"] = pd.isna(campaigns_sport[\"time_to_open\"])\n",
"company_lazy_customers = campaigns_sport.groupby(\"number_company\")[\"no_campaign_opened\"].mean().reset_index()\n",
"\n",
"def lazy_customer_plot(campaigns_sport):\n",
" company_lazy_customers = campaigns_sport.groupby(\"number_company\")[\"no_campaign_opened\"].mean().reset_index()\n",
" # Création du barplot\n",
" plt.bar(company_lazy_customers[\"number_company\"], company_lazy_customers[\"no_campaign_opened\"])\n",
" \n",
" # Ajout de titres et d'étiquettes\n",
" plt.xlabel('Company')\n",
" plt.ylabel(\"Part de clients n'ayant ouvert aucun mail\")\n",
" plt.title(\"Part de clients n'ayant ouvert aucun mail pour les compagnies de sport\")\n",
" \n",
" # Affichage du barplot\n",
" plt.show()"
]
},
{
"cell_type": "code",
work on stat
2024-03-06 11:56:52 +01:00
"execution_count": 25,
work on stat desc
2024-03-04 19:29:21 +01:00
"id": "e513f308-3a9c-40ed-99d5-ed420bd67384",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"lazy_customer_plot(campaigns_sport)"
work on stat desc sport
2024-03-04 16:55:58 +01:00
]
work on stat
2024-03-06 11:56:52 +01:00
},
{
"cell_type": "code",
"execution_count": null,
"id": "038423ec-d095-4297-8ea8-42d205da510b",
"metadata": {},
"outputs": [],
"source": [
"def "
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "264dd0f3-721b-4ddb-9e7c-0d21c6c0ddeb",
"metadata": {},
"outputs": [],
"source": [
"def display_databases(directory_path, file_name):\n",
" \"\"\"\n",
" This function returns the file from s3 storage \n",
" \"\"\"\n",
" file_path = \"projet-bdc2324-team1\" + \"/Generalization/\" + directory_path + \"/\" + file_name + \".csv\"\n",
" print(\"File path : \", file_path)\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" df = pd.read_csv(file_in, sep=\",\") \n",
" return df "
]
},
{
"cell_type": "code",
"execution_count": 17,
"id": "f0cfdd97-5ba2-4209-b827-d10ef0e80262",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : projet-bdc2324-team1/Generalization/musique/Test_set.csv\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/tmp/ipykernel_439/3124665301.py:8: DtypeWarning: Columns (20,29,39) have mixed types. Specify dtype option on import or set low_memory=False.\n",
" df = pd.read_csv(file_in, sep=\",\")\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>customer_id</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>...</th>\n",
" <th>gender_label</th>\n",
" <th>gender_female</th>\n",
" <th>gender_male</th>\n",
" <th>gender_other</th>\n",
" <th>country_fr</th>\n",
" <th>has_tags</th>\n",
" <th>nb_campaigns</th>\n",
" <th>nb_campaigns_opened</th>\n",
" <th>time_to_open</th>\n",
" <th>y_has_purchased</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>10_1</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>10_2</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>10_3</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>10_4</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>10_5</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>other</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</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>1523683</th>\n",
" <td>14_6884748</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1523684</th>\n",
" <td>14_6884749</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1523685</th>\n",
" <td>14_6884750</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1523686</th>\n",
" <td>14_6884751</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>female</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1523687</th>\n",
" <td>14_6884753</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>male</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1.0</td>\n",
" <td>0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1523688 rows × 41 columns</p>\n",
"</div>"
],
"text/plain": [
" customer_id nb_tickets nb_purchases total_amount nb_suppliers \\\n",
"0 10_1 0.0 0.0 0.0 0.0 \n",
"1 10_2 0.0 0.0 0.0 0.0 \n",
"2 10_3 0.0 0.0 0.0 0.0 \n",
"3 10_4 0.0 0.0 0.0 0.0 \n",
"4 10_5 0.0 0.0 0.0 0.0 \n",
"... ... ... ... ... ... \n",
"1523683 14_6884748 0.0 0.0 0.0 0.0 \n",
"1523684 14_6884749 0.0 0.0 0.0 0.0 \n",
"1523685 14_6884750 0.0 0.0 0.0 0.0 \n",
"1523686 14_6884751 0.0 0.0 0.0 0.0 \n",
"1523687 14_6884753 0.0 0.0 0.0 0.0 \n",
"\n",
" vente_internet_max purchase_date_min purchase_date_max \\\n",
"0 0.0 NaN NaN \n",
"1 0.0 NaN NaN \n",
"2 0.0 NaN NaN \n",
"3 0.0 NaN NaN \n",
"4 0.0 NaN NaN \n",
"... ... ... ... \n",
"1523683 0.0 NaN NaN \n",
"1523684 0.0 NaN NaN \n",
"1523685 0.0 NaN NaN \n",
"1523686 0.0 NaN NaN \n",
"1523687 0.0 NaN NaN \n",
"\n",
" time_between_purchase nb_tickets_internet ... gender_label \\\n",
"0 NaN 0.0 ... other \n",
"1 NaN 0.0 ... other \n",
"2 NaN 0.0 ... other \n",
"3 NaN 0.0 ... other \n",
"4 NaN 0.0 ... other \n",
"... ... ... ... ... \n",
"1523683 NaN 0.0 ... male \n",
"1523684 NaN 0.0 ... male \n",
"1523685 NaN 0.0 ... male \n",
"1523686 NaN 0.0 ... female \n",
"1523687 NaN 0.0 ... male \n",
"\n",
" gender_female gender_male gender_other country_fr has_tags \\\n",
"0 0 0 1 NaN 0 \n",
"1 0 0 1 NaN 0 \n",
"2 0 0 1 NaN 0 \n",
"3 0 0 1 NaN 0 \n",
"4 0 0 1 NaN 0 \n",
"... ... ... ... ... ... \n",
"1523683 0 1 0 1.0 0 \n",
"1523684 0 1 0 1.0 0 \n",
"1523685 0 1 0 1.0 0 \n",
"1523686 1 0 0 1.0 0 \n",
"1523687 0 1 0 1.0 0 \n",
"\n",
" nb_campaigns nb_campaigns_opened time_to_open y_has_purchased \n",
"0 0.0 0.0 NaN NaN \n",
"1 0.0 0.0 NaN NaN \n",
"2 0.0 0.0 NaN NaN \n",
"3 0.0 0.0 NaN NaN \n",
"4 0.0 0.0 NaN NaN \n",
"... ... ... ... ... \n",
"1523683 0.0 0.0 NaN NaN \n",
"1523684 0.0 0.0 NaN NaN \n",
"1523685 0.0 0.0 NaN NaN \n",
"1523686 0.0 0.0 NaN NaN \n",
"1523687 0.0 0.0 NaN NaN \n",
"\n",
"[1523688 rows x 41 columns]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train = display_databases('musique', 'Test_set')\n",
"train"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "b6a6feb7-2557-4932-8038-24cd9b363665",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([nan])"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train['y_has_purchased'].unique()"
]
work on stat desc sport
2024-03-04 16:55:58 +01:00
}
],
"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 Copy Permalink