2024-01-10 19:19:51 +01:00
{
"cells": [
{
"cell_type": "markdown",
2024-02-10 22:46:56 +01:00
"id": "5bf5c226",
2024-01-10 19:19:51 +01:00
"metadata": {},
"source": [
"# Business Data Challenge - Team 1"
]
},
{
"cell_type": "code",
2024-03-27 19:55:11 +01:00
"execution_count": 22,
2024-02-10 22:46:56 +01:00
"id": "b1a5b9d3",
2024-01-10 19:19:51 +01:00
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
2024-01-13 10:38:10 +01:00
"import numpy as np\n",
"import os\n",
"import s3fs\n",
2024-02-25 23:53:10 +01:00
"import re\n",
2024-03-27 19:55:11 +01:00
"import warnings\n",
"import io\n",
"import matplotlib.pyplot as plt\n"
2024-01-10 19:19:51 +01:00
]
},
{
"cell_type": "markdown",
2024-02-10 22:46:56 +01:00
"id": "ecfa2219",
2024-01-10 19:19:51 +01:00
"metadata": {},
"source": [
"Configuration de l'accès aux données"
]
},
{
"cell_type": "code",
2024-02-26 22:47:36 +01:00
"execution_count": 2,
2024-02-10 22:46:56 +01:00
"id": "1a094277",
2024-01-10 19:19:51 +01:00
"metadata": {},
"outputs": [],
"source": [
"# Create filesystem object\n",
"S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
2024-01-13 10:38:10 +01:00
"fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})"
2024-01-10 19:19:51 +01:00
]
},
2024-02-25 18:33:24 +01:00
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": 3,
2024-02-25 18:33:24 +01:00
"id": "30d77451-2df6-4c07-8b15-66e0e990ff03",
"metadata": {},
"outputs": [],
"source": [
"# Import cleaning and merge functions\n",
2024-03-13 23:24:38 +01:00
"\n",
"exec(open('0_Cleaning_and_merge_functions.py').read())\n",
"\n",
2024-02-25 18:33:24 +01:00
"exec(open('0_KPI_functions.py').read())\n",
"\n",
"# Ignore warning\n",
"warnings.filterwarnings('ignore')\n"
]
},
{
"cell_type": "code",
2024-02-26 22:47:36 +01:00
"execution_count": 4,
2024-02-25 18:33:24 +01:00
"id": "f1b44d3e-76bb-4860-b9db-a2840db7cf39",
"metadata": {},
"outputs": [],
"source": [
"def load_dataset_2(directory_path, file_name):\n",
" \"\"\"\n",
" This function loads csv file\n",
" \"\"\"\n",
" file_path = \"bdc2324-data\" + \"/\" + directory_path + \"/\" + directory_path + file_name + \".csv\"\n",
" with fs.open(file_path, mode=\"rb\") as file_in:\n",
" df = pd.read_csv(file_in, sep=\",\")\n",
"\n",
" # drop na :\n",
" #df = df.dropna(axis=1, thresh=len(df))\n",
" # if identifier in table : delete it\n",
" if 'identifier' in df.columns:\n",
" df = df.drop(columns = 'identifier')\n",
" return df"
]
},
{
2024-03-13 23:24:38 +01:00
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": 5,
2024-03-13 23:24:38 +01:00
"id": "31ab76f0-fbb1-46f6-b359-97228620c207",
2024-03-04 23:30:25 +01:00
"metadata": {},
2024-03-13 23:24:38 +01:00
"outputs": [],
2024-02-25 18:33:24 +01:00
"source": [
2024-03-13 23:24:38 +01:00
"def export_in_temporary(df, output_name):\n",
" print('Export of dataset :', output_name)\n",
2024-03-23 12:51:18 +01:00
" FILE_PATH_OUT_S3 = \"ajoubrel-ensae/Temporary\" + \"/\" + output_name + '.csv'\n",
2024-03-13 23:24:38 +01:00
" with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:\n",
" df.to_csv(file_out, index = False)"
2024-02-25 18:33:24 +01:00
]
},
2024-03-27 19:55:11 +01:00
{
"cell_type": "code",
"execution_count": 15,
"id": "108fc5ef-c56a-4f03-a867-943d9d6492fd",
"metadata": {},
"outputs": [],
"source": [
"def save_file_s3(File_name, type_of_activity):\n",
" image_buffer = io.BytesIO()\n",
" plt.savefig(image_buffer, format='png')\n",
" image_buffer.seek(0)\n",
" FILE_PATH = f\"projet-bdc2324-team1/stat_desc/{type_of_activity}/\"\n",
" FILE_PATH_OUT_S3 = FILE_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()"
]
},
2024-03-27 23:21:26 +01:00
{
"cell_type": "code",
"execution_count": 37,
"id": "c99b9cb7-00ab-41cf-bde7-38676f5a3d02",
"metadata": {},
"outputs": [],
"source": [
"def taux_partner(campany_nb) :\n",
"\n",
" is_partner = load_dataset_2(campany_nb, 'customersplus')[['is_partner']].astype(int)\n",
" percentage_partner = (is_partner['is_partner'].mean()) * 100\n",
" \n",
" return percentage_partner\n",
" \n"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "6facc27e-f95d-49c5-afe0-8c34b3a0cb94",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.0\n"
]
}
],
"source": [
"a = 0\n",
"for nb in [\"1\", \"2\", \"3\", \"4\", \"5\", \"6\", \"7\", \"8\", \"9\", \"10\", \"11\", \"12\", \"13\", \"14\"]:\n",
" a += taux_partner(nb)\n",
"\n",
"print(a/14)"
]
},
2024-02-25 18:33:24 +01:00
{
2024-03-13 23:24:38 +01:00
"cell_type": "markdown",
"id": "ccf597b0-b459-4ea5-baf0-5ba8c90915e4",
2024-03-26 11:51:02 +01:00
"metadata": {},
2024-02-25 18:33:24 +01:00
"source": [
2024-03-13 23:24:38 +01:00
"# Cleaning target area and tags"
2024-02-25 18:33:24 +01:00
]
},
{
"cell_type": "code",
2024-03-23 12:51:18 +01:00
"execution_count": 14,
"id": "fd88e294-e038-4cec-ad94-2bbbc10a4059",
2024-02-25 18:33:24 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-25 18:33:24 +01:00
"source": [
2024-03-23 12:51:18 +01:00
"def concatenate_names(names):\n",
" return ', '.join(names)\n",
"\n",
"def targets_KPI(df_target = None):\n",
" \n",
" df_target['target_name'] = df_target['target_name'].fillna('').str.lower()\n",
"\n",
" # Target name cotegory musees / \n",
" df_target['target_jeune'] = df_target['target_name'].str.contains('|'.join(['jeune', 'pass_culture', 'etudiant', '12-25 ans', 'student', 'jeunesse']), case=False).astype(int)\n",
" df_target['target_optin'] = df_target['target_name'].str.contains('|'.join(['optin' ,'opt-in']), case=False).astype(int)\n",
" df_target['target_optout'] = df_target['target_name'].str.contains('|'.join(['optout', 'unsubscribed']), case=False).astype(int)\n",
" df_target['target_scolaire'] = df_target['target_name'].str.contains('|'.join(['scolaire' , 'enseignant', 'chercheur', 'schulen', 'école']), case=False).astype(int)\n",
" df_target['target_entreprise'] = df_target['target_name'].str.contains('|'.join(['b2b', 'btob', 'cse']), case=False).astype(int)\n",
" df_target['target_famille'] = df_target['target_name'].str.contains('|'.join(['famille', 'enfants', 'family']), case=False).astype(int)\n",
" df_target['target_newsletter'] = df_target['target_name'].str.contains('|'.join(['nl', 'newsletter']), case=False).astype(int)\n",
" \n",
" # Target name category for sport compagnies\n",
" df_target['target_abonne'] = ((\n",
" df_target['target_name']\n",
" .str.contains('|'.join(['abo', 'adh']), case=False)\n",
" & ~df_target['target_name'].str.contains('|'.join(['hors abo', 'anciens abo']), case=False)\n",
" ).astype(int))\n",
" \n",
" df_target_categorie = df_target.groupby('customer_id')[['target_jeune', 'target_optin', 'target_optout', 'target_scolaire', 'target_entreprise', 'target_famille', 'target_newsletter', 'target_abonne']].max()\n",
" \n",
" target_agg = df_target.groupby('customer_id').agg(\n",
" nb_targets=('target_name', 'nunique') # Utilisation de tuples pour spécifier les noms de colonnes\n",
" # all_targets=('target_name', concatenate_names),\n",
" # all_target_types=('target_type_name', concatenate_names)\n",
" ).reset_index()\n",
"\n",
" target_agg['nb_targets'] = (target_agg['nb_targets'] - (target_agg['nb_targets'].mean())) / (target_agg['nb_targets'].std())\n",
" \n",
" target_agg = pd.merge(target_agg, df_target_categorie, how='left', on='customer_id')\n",
" \n",
" return target_agg"
2024-02-25 18:33:24 +01:00
]
},
{
"cell_type": "code",
2024-03-23 12:51:18 +01:00
"execution_count": 15,
"id": "1b124018-9637-463e-b512-15743ec9480b",
2024-02-25 18:33:24 +01:00
"metadata": {},
2024-03-13 23:24:38 +01:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-03-23 12:51:18 +01:00
"File path : projet-bdc2324-team1/0_Input/Company_5/target_information.csv\n"
2024-03-13 23:24:38 +01:00
]
},
{
"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",
2024-03-23 12:51:18 +01:00
" <th>customer_id</th>\n",
" <th>nb_targets</th>\n",
2024-03-23 10:48:47 +01:00
" <th>target_jeune</th>\n",
" <th>target_optin</th>\n",
" <th>target_optout</th>\n",
" <th>target_scolaire</th>\n",
" <th>target_entreprise</th>\n",
" <th>target_famille</th>\n",
" <th>target_newsletter</th>\n",
2024-03-23 12:51:18 +01:00
" <th>target_abonne</th>\n",
2024-03-13 23:24:38 +01:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
2024-03-23 12:51:18 +01:00
" <th>0</th>\n",
" <td>160516</td>\n",
" <td>6.938264</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>160517</td>\n",
" <td>10.357387</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
2024-03-13 23:24:38 +01:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
2024-03-23 12:51:18 +01:00
" <td>160518</td>\n",
" <td>5.228703</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>160519</td>\n",
" <td>6.083483</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
2024-03-13 23:24:38 +01:00
" </tr>\n",
" <tr>\n",
2024-03-23 12:51:18 +01:00
" <th>4</th>\n",
" <td>160520</td>\n",
" <td>2.949288</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
2024-03-13 23:24:38 +01:00
" </tr>\n",
" <tr>\n",
2024-03-23 12:51:18 +01:00
" <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",
" </tr>\n",
" <tr>\n",
" <th>471205</th>\n",
" <td>6405875</td>\n",
" <td>-0.754762</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>471206</th>\n",
" <td>6405905</td>\n",
" <td>-0.469835</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-13 23:24:38 +01:00
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>471207</th>\n",
" <td>6405909</td>\n",
" <td>-0.754762</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-13 23:24:38 +01:00
" <td>1</td>\n",
2024-03-23 10:48:47 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-13 23:24:38 +01:00
" </tr>\n",
" <tr>\n",
2024-03-23 12:51:18 +01:00
" <th>471208</th>\n",
" <td>6405917</td>\n",
" <td>-0.754762</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
2024-03-23 12:51:18 +01:00
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>471209</th>\n",
" <td>6405963</td>\n",
" <td>-0.754762</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-23 10:48:47 +01:00
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
2024-03-13 23:24:38 +01:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
2024-03-23 12:51:18 +01:00
"<p>471210 rows ×
2024-03-13 23:24:38 +01:00
"</div>"
],
"text/plain": [
2024-03-23 12:51:18 +01:00
" customer_id nb_targets target_jeune target_optin target_optout \\\n",
"0 160516 6.938264 0 1 0 \n",
"1 160517 10.357387 0 1 1 \n",
"2 160518 5.228703 0 1 1 \n",
"3 160519 6.083483 0 1 1 \n",
"4 160520 2.949288 0 1 0 \n",
"... ... ... ... ... ... \n",
"471205 6405875 -0.754762 0 0 1 \n",
"471206 6405905 -0.469835 0 0 1 \n",
"471207 6405909 -0.754762 0 0 1 \n",
"471208 6405917 -0.754762 0 0 1 \n",
"471209 6405963 -0.754762 0 0 1 \n",
"\n",
" target_scolaire target_entreprise target_famille target_newsletter \\\n",
"0 0 1 0 0 \n",
"1 0 0 0 0 \n",
"2 0 0 0 0 \n",
"3 0 0 1 0 \n",
"4 0 0 0 0 \n",
"... ... ... ... ... \n",
"471205 0 0 0 0 \n",
"471206 0 0 0 0 \n",
"471207 0 0 0 0 \n",
"471208 0 0 0 0 \n",
"471209 0 0 0 0 \n",
2024-03-13 23:24:38 +01:00
"\n",
2024-03-23 12:51:18 +01:00
" target_abonne \n",
"0 1 \n",
"1 1 \n",
"2 1 \n",
"3 1 \n",
"4 1 \n",
"... ... \n",
"471205 0 \n",
"471206 0 \n",
"471207 0 \n",
"471208 0 \n",
"471209 0 \n",
"\n",
"[471210 rows x 10 columns]"
2024-03-13 23:24:38 +01:00
]
},
2024-03-23 12:51:18 +01:00
"execution_count": 15,
2024-03-13 23:24:38 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
2024-02-25 18:33:24 +01:00
"source": [
2024-03-23 12:51:18 +01:00
"targets_KPI(display_input_databases('5', file_name = \"target_information\"))"
2024-02-25 18:33:24 +01:00
]
},
2024-03-26 23:01:33 +01:00
{
"cell_type": "code",
"execution_count": 35,
"id": "7bbca184-1ec1-43b5-ba50-c5e8343d52e7",
"metadata": {},
"outputs": [],
"source": [
"def targets_name_category(df_target=None):\n",
" if df_target is None:\n",
" return None\n",
" \n",
" df_target['target_name'] = df_target['target_name'].fillna('').str.lower()\n",
"\n",
" # Target name category for museums\n",
" df_target['target_jeune'] = df_target['target_name'].str.contains('|'.join(['jeune', 'pass_culture', 'etudiant', '12-25 ans', 'student', 'jeunesse']), case=False).astype(int)\n",
" df_target['target_optin'] = df_target['target_name'].str.contains('|'.join(['optin', 'opt-in']), case=False).astype(int)\n",
" df_target['target_optout'] = df_target['target_name'].str.contains('|'.join(['optout', 'unsubscribed']), case=False).astype(int)\n",
" df_target['target_scolaire'] = df_target['target_name'].str.contains('|'.join(['scolaire', 'enseignant', 'chercheur', 'schulen', 'école']), case=False).astype(int)\n",
" df_target['target_entreprise'] = df_target['target_name'].str.contains('|'.join(['b2b', 'btob', 'cse']), case=False).astype(int)\n",
" df_target['target_famille'] = df_target['target_name'].str.contains('|'.join(['famille', 'enfants', 'family']), case=False).astype(int)\n",
" df_target['target_newsletter'] = df_target['target_name'].str.contains('|'.join(['nl', 'newsletter']), case=False).astype(int)\n",
" \n",
" # Target name category for sport companies\n",
" df_target['target_abonne'] = ((df_target['target_name']\n",
" .str.contains('|'.join(['abo', 'adh']), case=False)\n",
" & ~df_target['target_name'].str.contains('|'.join(['hors abo', 'anciens abo']), case=False))\n",
" .astype(int))\n",
"\n",
" list_target_jeune = df_target[df_target['target_jeune'] == 1]['target_name'].unique()\n",
" list_target_optin = df_target[df_target['target_optin'] == 1]['target_name'].unique()\n",
" list_target_optout = df_target[df_target['target_optout'] == 1]['target_name'].unique()\n",
" list_target_scolaire = df_target[df_target['target_scolaire'] == 1]['target_name'].unique()\n",
" list_target_entreprise = df_target[df_target['target_entreprise'] == 1]['target_name'].unique()\n",
" list_target_famille = df_target[df_target['target_famille'] == 1]['target_name'].unique()\n",
" list_target_newsletter = df_target[df_target['target_newsletter'] == 1]['target_name'].unique()\n",
" list_target_abonne = df_target[df_target['target_abonne'] == 1]['target_name'].unique()\n",
"\n",
" list_all = [list_target_jeune, list_target_optin, list_target_optout, list_target_scolaire,\n",
" list_target_entreprise, list_target_famille, list_target_newsletter, list_target_abonne]\n",
"\n",
" category_name = ['target_jeune', 'target_optin', 'target_optout', 'target_scolaire',\n",
" 'target_entreprise', 'target_famille', 'target_newsletter', 'target_abonne']\n",
" \n",
" liste_category = pd.DataFrame({'category_name': category_name,\n",
" 'list_target_name': list_all})\n",
" \n",
" return liste_category\n"
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "fbabcf4d-3ee6-4441-b231-d7ef24b7f160",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"File path : projet-bdc2324-team1/0_Input/Company_7/target_information.csv\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>category_name</th>\n",
" <th>list_target_name</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>target_jeune</td>\n",
" <td>[jeunesses vaudoises, etudiant hors ssc 22-23, student supporter club, etudiants hors epfl, student supporter club ehl, etudiants]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>target_optin</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>target_optout</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>target_scolaire</td>\n",
" <td>[]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>target_entreprise</td>\n",
" <td>[prospects b2b, prospects survey b2b, b2b à enlever, prospect b2b fc 06.10, prospect b2b rk 06.10]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>target_famille</td>\n",
" <td>[family corner - 20.11.22, family corner - saison 19-20]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>target_newsletter</td>\n",
" <td>[consentements nl lhc, newsletter 2022, b2b à enlever, abonnés newsletter - saison 21-22]</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>target_abonne</td>\n",
" <td>[abonnés 23/24, non renouvellement abo 23-24 debout (23.06), résas abos debout - 29.06, abonnés - assis, sondage reconduction abos, sondage nouveaux abos, abonnés b2c - relance 1, abonnés b2c - relance 2, relance abos assis, non renouvellement abo 23-24 assis (23.06), résas abos assis - 29.06, abonnés - playoffs, abonnés - debout, abonnés non vip - saison 22-23, avantage abonné - ticket, paiements abos, campagneabosconcours - abonnés 21-22 en attente, campagneabosconcours - abonnés 22-23, nouveaux abonnés - saison 22-23, abonnements - relance 15.04, abonnements - relance 13.04, abonnements - relance 11.04, abonnements - relance 07.04, abonnés newsletter - saison 21-22, abonnés 1-3 ans, abonnés 1-3 ans - relance, abonnés - non-renouvellement 22-23, abonnés - renoncement playoffs 22, abonnés 5 ans - relance, abonnés - version finale]</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" category_name \\\n",
"0 target_jeune \n",
"1 target_optin \n",
"2 target_optout \n",
"3 target_scolaire \n",
"4 target_entreprise \n",
"5 target_famille \n",
"6 target_newsletter \n",
"7 target_abonne \n",
"\n",
" list_target_name \n",
"0 [jeunesses vaudoises, etudiant hors ssc 22-23, student supporter club, etudiants hors epfl, student supporter club ehl, etudiants] \n",
"1 [] \n",
"2 [] \n",
"3 [] \n",
"4 [prospects b2b, prospects survey b2b, b2b à enlever, prospect b2b fc 06.10, prospect b2b rk 06.10] \n",
"5 [family corner - 20.11.22, family corner - saison 19-20] \n",
"6 [consentements nl lhc, newsletter 2022, b2b à enlever, abonnés newsletter - saison 21-22] \n",
"7 [abonnés 23/24, non renouvellement abo 23-24 debout (23.06), résas abos debout - 29.06, abonnés - assis, sondage reconduction abos, sondage nouveaux abos, abonnés b2c - relance 1, abonnés b2c - relance 2, relance abos assis, non renouvellement abo 23-24 assis (23.06), résas abos assis - 29.06, abonnés - playoffs, abonnés - debout, abonnés non vip - saison 22-23, avantage abonné - ticket, paiements abos, campagneabosconcours - abonnés 21-22 en attente, campagneabosconcours - abonnés 22-23, nouveaux abonnés - saison 22-23, abonnements - relance 15.04, abonnements - relance 13.04, abonnements - relance 11.04, abonnements - relance 07.04, abonnés newsletter - saison 21-22, abonnés 1-3 ans, abonnés 1-3 ans - relance, abonnés - non-renouvellement 22-23, abonnés - renoncement playoffs 22, abonnés 5 ans - relance, abonnés - version finale] "
]
},
"execution_count": 36,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pd.set_option('display.max_colwidth', None)\n",
"targets_name_category(display_input_databases('7', file_name = \"target_information\"))"
]
},
2024-02-25 18:33:24 +01:00
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "c75efea3-b5e8-4a7a-bed4-dd64ae9ff9f2",
2024-02-25 18:33:24 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-25 18:33:24 +01:00
"source": [
2024-03-26 11:51:02 +01:00
"#export_inv_temporary(target_agg, 'Target_kpi_concatenate')"
]
},
{
"cell_type": "code",
2024-03-27 23:21:26 +01:00
"execution_count": 47,
2024-03-26 11:51:02 +01:00
"id": "9d224485-3472-4cc7-9825-1a643bc94fef",
"metadata": {},
2024-03-26 23:01:33 +01:00
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
2024-03-27 23:21:26 +01:00
"File path : projet-bdc2324-team1/0_Input/Company_10/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_10/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_11/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_11/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_12/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_12/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_13/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_13/target_information.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_14/customerplus_cleaned.csv\n",
"File path : projet-bdc2324-team1/0_Input/Company_14/target_information.csv\n"
2024-03-26 23:01:33 +01:00
]
}
],
2024-03-26 11:51:02 +01:00
"source": [
2024-03-26 23:01:33 +01:00
"companies = {'musee' : ['1', '2', '3', '4'], # , '101'\n",
" 'sport': ['5', '6', '7', '8', '9'],\n",
" 'musique' : ['10', '11', '12', '13', '14']}\n",
"\n",
2024-03-27 23:21:26 +01:00
"nb_compagnie = companies['musique']\n",
2024-03-26 11:51:02 +01:00
"\n",
"def load_files(nb_compagnie):\n",
" targets = 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_input_databases(directory_path, file_name = \"customerplus_cleaned\")\n",
" df_target_information = display_input_databases(directory_path, file_name = \"target_information\")\n",
" \n",
" df_target_KPI = targets_KPI(df_target = df_target_information)\n",
" df_target_KPI = pd.merge(df_customerplus_clean_0[['customer_id']], df_target_KPI, how = 'left', on = 'customer_id')\n",
"\n",
" targets_columns = list(df_target_KPI.columns)\n",
" targets_columns.remove('customer_id')\n",
" df_target_KPI[targets_columns] = df_target_KPI[targets_columns].fillna(0)\n",
" \n",
" # creation de la colonne Number compagnie, qui permettra d'agréger les résultats\n",
" df_target_KPI[\"number_company\"]=int(directory_path)\n",
" \n",
" # Traitement des index\n",
" df_target_KPI[\"customer_id\"]= directory_path + '_' + df_target_KPI['customer_id'].astype('str')\n",
" \n",
" # Concaténation\n",
" targets = pd.concat([targets, df_target_KPI], ignore_index=True)\n",
" \n",
2024-03-26 23:01:33 +01:00
" return targets\n",
"\n",
"targets = load_files(nb_compagnie)"
2024-03-26 11:51:02 +01:00
]
},
{
"cell_type": "code",
2024-03-27 23:21:26 +01:00
"execution_count": 48,
2024-03-26 11:51:02 +01:00
"id": "3c911274-0ebd-49af-9487-26524ba20e74",
"metadata": {},
"outputs": [],
"source": [
"\n",
2024-03-27 19:55:11 +01:00
"def target_description(targets, type_of_activity):\n",
2024-03-26 11:51:02 +01:00
"\n",
" describe_target = targets.groupby('number_company').agg(\n",
" prop_target_jeune=('target_jeune', lambda x: (x.sum() / x.count())*100),\n",
" prop_target_scolaire=('target_scolaire', lambda x: (x.sum() / x.count())*100),\n",
" prop_target_entreprise=('target_entreprise', lambda x: (x.sum() / x.count())*100),\n",
" prop_target_famille=('target_famille', lambda x: (x.sum() / x.count())*100),\n",
2024-03-26 23:01:33 +01:00
" prop_target_optin=('target_optin', lambda x: (x.sum() / x.count())*100),\n",
" prop_target_optout=('target_optout', lambda x: (x.sum() / x.count())*100),\n",
" prop_target_newsletter=('target_newsletter', lambda x: (x.sum() / x.count())*100),\n",
" prop_target_abonne=('target_abonne', lambda x: (x.sum() / x.count())*100))\n",
2024-03-26 11:51:02 +01:00
"\n",
2024-03-26 23:01:33 +01:00
" plot = describe_target.plot.bar()\n",
2024-03-26 11:51:02 +01:00
" \n",
2024-03-26 23:01:33 +01:00
" # Adding a title\n",
" plot.set_title(\"Distribution of Targets by Category\")\n",
" \n",
" # Adding labels for x and y axes\n",
" plot.set_xlabel(\"Company Number\")\n",
" plot.set_ylabel(\"Target Proportion\")\n",
"\n",
" plot.set_xticklabels(plot.get_xticklabels(), rotation=0, horizontalalignment='center')\n",
"\n",
" \n",
" # Adding a legend\n",
" plot.legend([\"Youth\", \"School\", \"Enterprise\", \"Family\", \"Optin\", \"Optout\", \"Newsletter\", \"Subscriber\"], title=\"Target Category\")\n",
"\n",
2024-03-27 19:55:11 +01:00
" # save_file_s3(\"target_category_proportion_\", type_of_activity)\n",
2024-03-26 11:51:02 +01:00
" return plot"
]
},
{
"cell_type": "code",
2024-03-27 23:21:26 +01:00
"execution_count": 49,
2024-03-26 11:51:02 +01:00
"id": "af62ecef-9120-4107-af3e-512588a96800",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
2024-03-26 23:01:33 +01:00
"<Axes: title={'center': 'Distribution of Targets by Category'}, xlabel='Company Number', ylabel='Target Proportion'>"
2024-03-26 11:51:02 +01:00
]
},
2024-03-27 23:21:26 +01:00
"execution_count": 49,
2024-03-26 11:51:02 +01:00
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
2024-03-27 23:21:26 +01:00
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAjMAAAHFCAYAAAAHcXhbAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAABrr0lEQVR4nO3dd1gUV9sG8HvpvaosSLWgqIA1ikYRFbHEHo0lKjG22HuNCjawo2KNCsTYjRqjiYpdQSJqiIoES8CO2LFRhPP94ce8roCyCiyL9++65opz5syZZ3bW7OM5Z2ZkQggBIiIiIjWloeoAiIiIiD4FkxkiIiJSa0xmiIiISK0xmSEiIiK1xmSGiIiI1BqTGSIiIlJrTGaIiIhIrTGZISIiIrXGZIaIiIjUGpMZUqnQ0FDIZDJp0dPTg1wuh5eXFwICApCcnJxjHz8/P8hkMqWO8/LlS/j5+eHo0aNK7ZfbsRwdHfHVV18p1c6HbNy4EUFBQbluk8lk8PPzK9DjFbRDhw6hdu3aMDQ0hEwmw65du3LUady4scK1zmspbuf6sd+d98n+Xj148KDA2nyf33//HW3atIGVlRV0dHRgYWGBpk2bYsOGDcjIyFC6veXLlyM0NLTgAyX6SFqqDoAIAEJCQlC5cmVkZGQgOTkZJ0+exJw5czB//nxs2bIFzZo1k+r27dsXLVq0UKr9ly9fwt/fH8CbH9X8+phjfYyNGzfi4sWLGDFiRI5tp06dgq2tbaHH8LGEEOjSpQucnZ2xe/duGBoaolKlSjnqLV++HCkpKdL63r17MXPmTOnaZytu5/qx353iQAiBPn36IDQ0FK1atcLChQthZ2eHp0+f4siRIxg0aBAePHiA4cOHK9Xu8uXLUapUKfj6+hZO4ERKYjJDxUK1atVQu3Ztab1Tp04YOXIkvvzyS3Ts2BFXrlyBlZUVgDc/doX9g/fy5UsYGBgUybE+pF69eio9/ofcuXMHjx49QocOHdC0adM861WpUkVh/d9//wWQ89p/rOxrRv8zb948hIaGwt/fH1OnTlXY1qZNG4wbNw5Xr15VUXSF79WrV9DT01O6J5fUD4eZqNiyt7fHggUL8OzZM6xatUoqz23o5/Dhw2jcuDEsLS2hr68Pe3t7dOrUCS9fvkRiYiJKly4NAPD395eGM7L/VZnd3rlz5/D111/D3Nwc5cuXz/NY2Xbu3Ak3Nzfo6emhXLlyWLJkicL27CG0xMREhfKjR49CJpNJwxaNGzfG3r17cf36dYXhlmy5Db1cvHgR7dq1g7m5OfT09FC9enWEhYXlepxNmzZh8uTJsLGxgYmJCZo1a4b4+Pi8P/i3nDx5Ek2bNoWxsTEMDAxQv3597N27V9ru5+cnJXvjx4+HTCaDo6NjvtrOTXh4ONq1awdbW1vo6emhQoUKGDBgQI7hmPdds7S0NIwePRpyuRwGBgZo1KgRzp49C0dHxxw9CUlJSRgwYABsbW2ho6MDJycn+Pv74/Xr1wDwwe/O/fv30b9/f9jZ2UFXVxelS5dGgwYNcPDgwXyd782bN9GxY0eYmJjA1NQU3377Le7fvy9t//7772FhYYGXL1/m2LdJkyaoWrVqnm1nZGRgzpw5qFy5MqZMmZJrHblcji+//FJa9/f3R926dWFhYQETExPUrFkTa9euxdvvI3Z0dERsbCyOHTsmfR5vX/OUlBSMGTMGTk5O0NHRQdmyZTFixAi8ePFC4dhPnjyRzs/IyAitW7fGf//9l+v3/UPfQ+B/f98OHDiAPn36oHTp0jAwMMDJkyelvwfv+vnnnyGTyRAdHZ3n50jqgT0zVKy1atUKmpqaOH78eJ51EhMT0bp1azRs2BDr1q2DmZkZbt++jX379iE9PR3W1tbYt28fWrRoge+//x59+/YFAOlHKlvHjh3RtWtXDBw4MMf/eN8VExODESNGwM/PD3K5HBs2bMDw4cORnp6OMWPGKHWOy5cvR//+/XHt2jXs3Lnzg/Xj4+NRv359lClTBkuWLIGlpSV++eUX+Pr64t69exg3bpxC/UmTJqFBgwZYs2YNUlJSMH78eLRp0wZxcXHQ1NTM8zjHjh2Dt7c33NzcsHbtWujq6mL58uVo06YNNm3ahG+++QZ9+/aFu7s7OnbsiKFDh6J79+7Q1dVV6vzfdu3aNXh4eKBv374wNTVFYmIiFi5ciC+//BIXLlyAtra2Qv3crtl3332HLVu2YNy4cWjSpAkuXbqEDh06KAxxAW8SmS+++AIaGhqYOnUqypcvj1OnTmHmzJlITExESEjIB787PXv2xLlz5zBr1iw4OzvjyZMnOHfuHB4+fJiv8+3QoQO6dOmCgQMHIjY2FlOmTMGlS5fw119/QVtbG8OHD8e6deuwceNG6dgAcOnSJRw5cgTLli3Ls+0zZ87g0aNH6NevX757JhITEzFgwADY29sDAKKiojB06FDcvn1b6tnZuXMnvv76a5iammL58uUAIF3zly9fwtPTE7du3cKkSZPg5uaG2NhYTJ06FRcuXMDBgwchk8mQlZWFNm3a4MyZM/Dz80PNmjVx6tSpXId08/M9fFufPn3QunVrrF+/Hi9evED9+vVRo0YNLFu2DN26dVOoGxwcjDp16qBOnTr5+nyoGBNEKhQSEiIAiOjo6DzrWFlZCRcXF2l92rRp4u2v7vbt2wUAERMTk2cb9+/fFwDEtGnTcmzLbm/q1Kl5bnubg4ODkMlkOY7n7e0tTExMxIsXLxTOLSEhQaHekSNHBABx5MgRqax169bCwcEh19jfjbtr165CV1dX3LhxQ6Fey5YthYGBgXjy5InCcVq1aqVQb+vWrQKAOHXqVK7Hy1avXj1RpkwZ8ezZM6ns9evXolq1asLW1lZkZWUJIYRISEgQAMS8efPe2967PnTts7KyREZGhrh+/boAIH777TdpW17XLDY2VgAQ48ePVyjftGmTACB69+4tlQ0YMEAYGRmJ69evK9SdP3++ACBiY2OFEO//7hgZGYkRI0Yoc9oK8Y8cOVKhfMOGDQKA+OWXX6QyT09PUb16dYV6P/zwgzAxMVG4Nu/avHmzACBWrlypdHxCCJGZmSkyMjLE9OnThaWlpXS9hRCiatWqwtPTM8c+AQEBQkNDI8c1zf47+scffwghhNi7d68AIFasWJFj/3c/6/x+D7O/T7169coRV/a2v//+Wyo7ffq0ACDCwsLy/ZlQ8cVhJir2xFtd3LmpXr06dHR00L9/f4SFheG///77qON06tQp33WrVq0Kd3d3hbLu3bsjJSUF586d+6jj59fhw4fRtGlT2NnZKZT7+vri5cuXOHXqlEJ527ZtFdbd3NwAANevX8/zGC9evMBff/2Fr7/+GkZGRlK5pqYmevbsiVu3buV7qEoZycnJGDhwIOzs7KClpQVtbW04ODgAAOLi4nLUf/eaHTt2DADQpUsXhfKvv/4aWlqKHdF79uyBl5cXbGxs8Pr1a2lp2bKlQlvv88UXXyA0NBQzZ85EVFSU0ncG9ejRQ2G9S5cu0NLSwpEjR6Sy4cOHIyYmBhEREQDeDOOsX78evXv3Vrg2BeHw4cNo1qwZTE1NoampCW1tbUydOhUPHz7M9c7Cd+3ZswfVqlVD9erVFT5THx8fhaHVvK7Tuz0nH/M9zO3vcbdu3VCmTBmFnqylS5eidOnSOXp2SD0xmaFi7cWLF3j48CFsbGzyrFO+fHkcPHgQZcqUweDBg1G+fHmUL18eixcvVupY1tbW+a4rl8vzLMvvEMPHevjwYa6xZn9G7x7f0tJSYT17SODVq1d5HuPx48cQQih1nE+VlZWF5s2bY8eOHRg3bhwOHTqE06dPIyoqKs94340vO6bsyeLZtLS0cnwO9+7dw++//w5tbW2FJXseSn5um96yZQt69+6NNWvWwMPDAxYWFujVqxeSkpLydc7vfo+y43z7s23Xrh0cHR2lH+LQ0FC8ePECgwcPfm/b2UNFCQkJ+Yrl9OnTaN68OQDgp59+QkREBKKjozF58mQA7/++ZLt37x7Onz+f4zM1NjaGEEL6TB8+fAgtLS1YWFgo7P/udfuY72FudXV1dTF
2024-03-26 11:51:02 +01:00
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
2024-03-27 23:21:26 +01:00
"target_description(targets, 'musique')"
2024-02-25 18:33:24 +01:00
]
},
2024-03-14 23:35:25 +01:00
{
2024-03-23 10:48:47 +01:00
"cell_type": "markdown",
"id": "5d91263e-8a97-4cb1-8d94-db8ab0b77cdf",
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
2024-03-14 23:35:25 +01:00
"source": [
2024-03-23 10:48:47 +01:00
"# Brouillon"
2024-03-14 23:35:25 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c5e864b1-adad-4267-b956-3f7ef371d677",
"metadata": {},
"outputs": [],
"source": [
"\n",
"def display_covering_time(df, company, datecover):\n",
" \"\"\"\n",
" This function draws the time coverage of each company\n",
" \"\"\"\n",
" min_date = df['purchase_date'].min().strftime(\"%Y-%m-%d\")\n",
" max_date = df['purchase_date'].max().strftime(\"%Y-%m-%d\")\n",
" datecover[company] = [datetime.strptime(min_date, \"%Y-%m-%d\") + timedelta(days=x) for x in range((datetime.strptime(max_date, \"%Y-%m-%d\") - datetime.strptime(min_date, \"%Y-%m-%d\")).days)]\n",
" print(f'Couverture Company {company} : {min_date} - {max_date}')\n",
" return datecover\n",
"\n",
"\n",
"def compute_time_intersection(datecover):\n",
" \"\"\"\n",
" This function returns the time coverage for all companies\n",
" \"\"\"\n",
" timestamps_sets = [set(timestamps) for timestamps in datecover.values()]\n",
" intersection = set.intersection(*timestamps_sets)\n",
" intersection_list = list(intersection)\n",
" formated_dates = [dt.strftime(\"%Y-%m-%d\") for dt in intersection_list]\n",
" return sorted(formated_dates)\n",
"\n",
"\n",
"def df_coverage_modelization(sport, coverage_features = 0.7):\n",
" \"\"\"\n",
" This function returns start_date, end_of_features and final dates\n",
" that help to construct train and test datasets\n",
" \"\"\"\n",
" datecover = {}\n",
" for company in sport:\n",
" df_products_purchased_reduced = display_input_databases(company, file_name = \"products_purchased_reduced\",\n",
" datetime_col = ['purchase_date'])\n",
" datecover = display_covering_time(df_products_purchased_reduced, company, datecover)\n",
" #print(datecover.keys())\n",
" dt_coverage = compute_time_intersection(datecover)\n",
" start_date = dt_coverage[0]\n",
" end_of_features = dt_coverage[int(0.7 * len(dt_coverage))]\n",
" final_date = dt_coverage[-1]\n",
" return start_date, end_of_features, final_date\n",
" "
]
},
2024-02-25 18:33:24 +01:00
{
"cell_type": "markdown",
2024-03-13 23:24:38 +01:00
"id": "2435097a-95a5-43e1-84d0-7f6b701441ba",
2024-02-26 22:47:36 +01:00
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
2024-02-25 18:33:24 +01:00
"source": [
2024-03-13 23:24:38 +01:00
"# Bases non communes : mise à plat"
2024-02-25 23:53:10 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "f8f988fb-5aab-4b57-80d1-e242f7e5b384",
2024-02-25 23:53:10 +01:00
"metadata": {},
"outputs": [],
"source": [
2024-03-13 23:24:38 +01:00
"companies = {'musee' : ['1', '2', '3', '4'],\n",
" 'sport': ['5', '6', '7', '8', '9'],\n",
" 'musique' : ['10', '11', '12', '13', '14']}\n",
2024-02-25 23:53:10 +01:00
"\n",
2024-03-13 23:24:38 +01:00
"all_companies = ['1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12', '13', '14']"
2024-02-25 23:53:10 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "35ac004f-c191-4f45-a4b1-6d993d9ec38c",
2024-02-25 23:53:10 +01:00
"metadata": {},
"outputs": [],
"source": [
2024-03-13 23:24:38 +01:00
"companies_databases = pd.DataFrame()\n",
2024-02-25 23:53:10 +01:00
"\n",
2024-03-13 23:24:38 +01:00
"for i in all_companies:\n",
" company_databases = pd.DataFrame({'company_number' : [i]})\n",
2024-02-25 23:53:10 +01:00
"\n",
2024-03-13 23:24:38 +01:00
" BUCKET = \"bdc2324-data/\"+i\n",
" for base in fs.ls(BUCKET):\n",
" match = re.search(r'\\/(\\d+)\\/(\\d+)([a-zA-Z_]+)\\.csv$', base)\n",
" if match:\n",
" nom_base = match.group(3)\n",
" company_databases[nom_base] = 1\n",
2024-02-25 23:53:10 +01:00
"\n",
2024-03-13 23:24:38 +01:00
" companies_databases = pd.concat([companies_databases, company_databases])"
2024-02-26 22:47:36 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "8986e477-e6c5-4d6c-83b2-2c90c134b599",
2024-02-26 22:47:36 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-03-13 23:24:38 +01:00
"source": [
"pd.set_option(\"display.max_columns\", None)\n",
"companies_databases\n"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "8fecc3bb-4c03-4144-97c5-615224d9729e",
"metadata": {},
"outputs": [],
"source": [
"pd.reset_option(\"display.max_columns\")"
]
},
{
"cell_type": "markdown",
"id": "0294ce71-840e-458b-8ffa-cadabbc6da21",
"metadata": {},
"source": [
"# Debut Travail 25/02"
]
},
{
"cell_type": "markdown",
"id": "ca2c8b6a-4965-422e-ba7c-66423a464fc1",
2024-03-26 11:51:02 +01:00
"metadata": {},
2024-03-13 23:24:38 +01:00
"source": [
"## Base communes au types Musée"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5080f66e-f779-410a-876d-b4fe2795e17e",
"metadata": {},
"outputs": [],
"source": [
"for i in companies['musique']:\n",
" BUCKET = \"bdc2324-data/\"+i\n",
" liste_base = []\n",
" for base in fs.ls(BUCKET):\n",
" match = re.search(r'\\/(\\d+)\\/(\\d+)([a-zA-Z_]+)\\.csv$', base)\n",
" if match:\n",
" nom_base = match.group(3)\n",
" liste_base.append(nom_base)\n",
" globals()['base_'+i] = liste_base\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "abd477e1-7479-4c88-a5aa-f987af3f5b79",
"metadata": {},
"outputs": [],
"source": [
"# Trouver l'intersection entre les cinq listes\n",
"intersection = set(base_1).intersection(base_2, base_3, base_4, base_101)\n",
"\n",
"# Convertir le résultat en liste si nécessaire\n",
"intersection_liste = list(intersection)\n",
"\n",
"print(intersection_liste)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8d93888f-a511-4ee5-8bc3-d5173a7f119e",
"metadata": {},
"outputs": [],
"source": [
"# Trouver l'intersection entre les cinq listes\n",
"intersection = set(base_10).intersection(base_12, base_13, base_14, base_11)\n",
"\n",
"# Convertir le résultat en liste si nécessaire\n",
"intersection_liste = list(intersection)\n",
"\n",
"print(intersection_liste)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "10e89669-42bb-4652-a4bc-1a3d1caf4d1a",
"metadata": {},
"outputs": [],
"source": [
"len(intersection_liste)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7d058b21-a538-4f59-aefb-ef7966f73fdc",
"metadata": {},
"outputs": [],
"source": [
"df1_tags = load_dataset_2(\"1\", \"tags\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "aa441f99-733c-4675-8676-bed4682d3324",
"metadata": {},
"outputs": [],
"source": [
"df1_structure_tag_mappings = load_dataset_2(\"1\", 'structure_tag_mappings')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6767a750-14a4-4c05-903e-d2f07170825b",
"metadata": {},
"outputs": [],
"source": [
"df1_customersplus = load_dataset_2(\"1\", \"customersplus\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "125e9145-a815-46fd-bdf4-07589508b259",
"metadata": {},
"outputs": [],
"source": [
"df1_customersplus.groupby('structure_id')['id'].count().reset_index().sort_values('id', ascending=False).head(20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c17a6976-792f-474d-bcff-c89396eddb3f",
"metadata": {},
"outputs": [],
"source": [
"df1_customersplus['structure_id'].isna().sum() / len(df1_customersplus['structure_id'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ecfc155a-cb42-46ec-8da5-33fdcd087355",
"metadata": {},
"outputs": [],
"source": [
"len(df1_structure_tag_mappings)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "071410b8-950d-4fcc-b2b9-57415253c286",
"metadata": {},
"outputs": [],
"source": [
"df1_structure_tag_mappings.groupby('tag_id')['structure_id'].count().reset_index().sort_values('structure_id', ascending=False).head(20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f48d27a9-14e4-4bb9-a60a-73e9438b58fc",
"metadata": {},
"outputs": [],
"source": [
"?np.sort_values()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "14eaa0ea-02cc-430b-ab9b-38e6637810c3",
"metadata": {},
"outputs": [],
"source": [
"def info_colonnes_dataframe(df):\n",
" # Créer une liste pour stocker les informations sur chaque colonne\n",
" infos_colonnes = []\n",
"\n",
" # Parcourir les colonnes du DataFrame\n",
" for nom_colonne, serie in df.items(): # Utiliser items() au lieu de iteritems()\n",
" # Calculer le taux de valeurs manquantes\n",
" taux_na = serie.isna().mean() * 100\n",
"\n",
" # Ajouter les informations à la liste\n",
" infos_colonnes.append({\n",
" 'Nom_colonne': nom_colonne,\n",
" 'Type_colonne': str(serie.dtype),\n",
" 'Taux_NA': taux_na\n",
" })\n",
"\n",
" # Créer une nouvelle DataFrame à partir de la liste d'informations\n",
" df_infos_colonnes = pd.DataFrame(infos_colonnes)\n",
"\n",
" return df_infos_colonnes"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "6b031c32-d4c8-42a5-9a71-a7810f9bf8d8",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"info_colonnes_dataframe(df1_tags)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "e1a87f27-c4d4-4832-ac20-0c3c54aa4980",
"metadata": {},
"outputs": [],
"source": [
"info_colonnes_dataframe(df1_structure_tag_mappings)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fa5c65a8-2f74-4f3f-85fc-9ac91e0bb361",
"metadata": {},
"outputs": [],
"source": [
"pd.set_option('display.max_colwidth', None)\n",
"\n",
"print(df1_tags['name'])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a59bf932-5b54-4600-81f5-c55ac93ae510",
"metadata": {},
"outputs": [],
"source": [
"pd.set_option('display.max_rows', None)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a4ab298e-2cae-4865-9f00-4caff5f75ea1",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"print(df1_tags['name'])"
]
},
{
"cell_type": "markdown",
"id": "76bffba1-5f7e-4308-9224-437ca66148f8",
2024-03-26 11:51:02 +01:00
"metadata": {},
2024-03-13 23:24:38 +01:00
"source": [
"## KPI sur target_type"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f6daf22e-6583-4431-a467-660a1dd4e5a4",
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
2024-03-23 12:51:18 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "d91d5895",
"metadata": {},
"outputs": [],
"source": [
"pd.set_option('display.max_colwidth', None)\n"
]
},
{
"cell_type": "markdown",
"id": "c58b17d3",
"metadata": {},
"source": [
"Raisonnement : on prends les target_type qui représente 90% des clients et on fait des catégories dessus."
]
},
{
"cell_type": "code",
2024-03-23 12:51:18 +01:00
"execution_count": null,
2024-03-13 23:24:38 +01:00
"id": "6930bff5",
"metadata": {},
"outputs": [],
"source": [
"def print_main_target(tenant_id, nb_print = 40):\n",
2024-03-23 10:48:47 +01:00
" df_target = display_input_databases(tenant_id, \"target_information\")\n",
2024-03-13 23:24:38 +01:00
"\n",
" print('Nombre de ciblage : ', len(df_target))\n",
" nb_customers = df_target['customer_id'].nunique()\n",
" print('Nombre de client avec étiquette target : ', nb_customers) \n",
"\n",
" nb_custumers_per_target = df_target.groupby(\"target_name\")['customer_id'].count().reset_index().sort_values('customer_id', ascending=False)\n",
" nb_custumers_per_target['cumulative_customers'] = nb_custumers_per_target['customer_id'].cumsum()/len(df_target)\n",
" nb_custumers_per_target['customer_id'] = nb_custumers_per_target['customer_id']/nb_customers\n",
"\n",
" return nb_custumers_per_target.head(nb_print)"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "1e7ee1a0",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"pd.set_option(\"max_colwidth\", None)\n",
"print_main_target('1', 60)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "19f3a2dd-ba3d-4dec-8e10-fed544ab6a53",
"metadata": {},
"outputs": [],
"source": [
"pd.reset_option('display.max_rows')"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b57a28ac",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"print_main_target('2', 25)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9a65991f",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"print_main_target('3', 70)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "5f34b8bf",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"print_main_target('4', 100)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "52b24d66-92ad-4421-a62b-5cba837f1893",
2024-03-13 23:24:38 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
"source": [
"pd.set_option('display.max_rows', None)"
]
},
{
"cell_type": "code",
2024-03-23 12:51:18 +01:00
"execution_count": null,
"id": "40fe3676",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"\n",
"\n",
"print_main_target('5', 100)"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "820d3600-379b-4245-a977-f1f1fa1f1839",
"metadata": {
"scrolled": true
},
2024-03-23 10:48:47 +01:00
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('6', 100)"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "86f64a1b-763a-4e43-9601-a38c80392d47",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('7', 100)"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "fbf2ea42-515a-4cdf-a4c1-50f99c379ed9",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('8', 100)"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "9684045c-4e25-4952-b099-a559baa5d749",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('9', 100)"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "cf8f7816-e7f3-4b7a-a987-8350a76eb140",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('10', 100)"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "76c818a5-3c52-4d97-ac81-b7f3f89092bd",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('11', 100)\n"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "603b11e4-5d76-4699-a1b2-e795929edc04",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('12', 100)\n"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
"execution_count": null,
2024-03-23 12:51:18 +01:00
"id": "fa93aecd-d117-481e-8507-15e49937ce14",
"metadata": {
"scrolled": true
},
2024-03-23 10:48:47 +01:00
"outputs": [],
"source": [
2024-03-23 12:51:18 +01:00
"print_main_target('13', 100)\n"
2024-03-23 10:48:47 +01:00
]
},
{
"cell_type": "code",
2024-03-23 12:51:18 +01:00
"execution_count": null,
"id": "a115ebcf-4488-47f3-9d7e-75a1fca52f0f",
2024-03-23 10:48:47 +01:00
"metadata": {
"scrolled": true
},
2024-03-23 12:51:18 +01:00
"outputs": [],
2024-03-23 10:48:47 +01:00
"source": [
"print_main_target('14', 100)\n"
]
},
{
"cell_type": "markdown",
"id": "605cced5-052f-4a99-ac26-020c5d2ab633",
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
"source": [
"## KPI sur tags"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "916c3e2b-04d3-4877-b894-8f26f10d926e",
"metadata": {},
"outputs": [],
"source": [
"customersplus = load_dataset_2(\"4\", \"customersplus\")[['id', 'structure_id']]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "46847b24-15a4-464e-969f-f16ed3653f1f",
"metadata": {},
"outputs": [],
"source": [
"structure_tag_mappings = load_dataset_2('4', \"structure_tag_mappings\")[['structure_id', 'tag_id']]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3c10c69d-735f-453e-96bf-750697d965d0",
"metadata": {},
"outputs": [],
"source": [
"customersplus[customersplus['structure_id'].notna()]['structure_id'].nunique()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9b0e77b3-5f16-4484-9564-7d3826583418",
"metadata": {},
"outputs": [],
"source": [
"len(customersplus[customersplus['structure_id'].notna()])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dfa27722-37f9-435a-8221-8aa6f9a4a107",
"metadata": {},
"outputs": [],
"source": [
"structure_tag_mappings['structure_id'].nunique()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2daabdd5-31e3-4918-9856-9bbc30cde602",
"metadata": {},
"outputs": [],
"source": [
"def tags_information(tenant_id, first_tags):\n",
"\n",
" customersplus = load_dataset_2(tenant_id, \"customersplus\")[['id', 'structure_id']]\n",
" customersplus.rename(columns = {'id' : 'customer_id'}, inplace = True)\n",
" tags = load_dataset_2(tenant_id, \"tags\")[['id', 'name']]\n",
" tags.rename(columns = {'id' : 'tag_id', 'name' : 'tag_name'}, inplace = True)\n",
" structure_tag_mappings = load_dataset_2(tenant_id, \"structure_tag_mappings\")[['structure_id', 'tag_id']]\n",
" \n",
" customer_tags = pd.merge(customersplus, structure_tag_mappings, on = 'structure_id', how = 'left')\n",
" customer_tags = pd.merge(customer_tags, tags, on = 'tag_id', how = 'inner')\n",
" \n",
" nb_customers_with_tag = customer_tags['customer_id'].nunique()\n",
" \n",
" print('Nombre de client avec tag : ', nb_customers_with_tag)\n",
" print('Proportion de clients avec tags : ', nb_customers_with_tag/len(customersplus))\n",
" print('Moyenne de tags par client : ', len(customer_tags)/nb_customers_with_tag)\n",
" \n",
" info = customer_tags.groupby(['tag_id', 'tag_name'])['customer_id'].count().reset_index().sort_values('customer_id', ascending = False).head(first_tags)\n",
"\n",
" return info"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0b9f5f71-a927-4cc8-bb0c-9538e28d3553",
"metadata": {},
"outputs": [],
"source": [
"tags_information(\"1\", 20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bd5bef41-1774-4601-86b5-b7c1aea8f1d2",
"metadata": {},
"outputs": [],
"source": [
"tags_information(\"2\", 20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "7c2dc3e6-1418-44db-a8c0-4a9d59ec5232",
"metadata": {},
"outputs": [],
"source": [
"load_dataset_2(\"2\", \"tags\")[['id', 'name']]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c7b2c670-7122-4f67-b1aa-8c80a10f16d8",
"metadata": {},
"outputs": [],
"source": [
"tags_information(\"3\", 20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "76639995-252d-4a58-83d8-c0c00900c3a9",
"metadata": {},
"outputs": [],
"source": [
"tags_information(\"4\", 20)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "07e91791-d4d4-42b1-ac18-22d3b0b9f7bd",
"metadata": {},
"outputs": [],
"source": [
"tags_information(\"101\", 20)"
]
},
{
"cell_type": "markdown",
"id": "87d131cd-ead0-4ef4-a8ee-b09022d08ffa",
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
"source": [
"## KPI product"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "26582be9-cfd1-48ea-a0a7-31101fdeb9d1",
"metadata": {},
"outputs": [],
"source": [
"tenant_id = \"1\"\n",
"\n",
"df_product = display_databases(tenant_id, file_name = \"products_purchased_reduced\", datetime_col = ['purchase_date'])\n",
"\n",
"df_product.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "533bf499-dd56-4d29-b261-ca1e4928c9c7",
"metadata": {},
"outputs": [],
2024-02-28 21:57:28 +01:00
"source": [
"nb_tickets_per_events = df_product.groupby(['name_event_types', 'name_events'])['ticket_id'].count().reset_index().sort_values('ticket_id', ascending = False)\n",
"nb_tickets_per_events['prop_tickets'] = round(nb_tickets_per_events['ticket_id']/len(df_product), 3)\n",
"nb_tickets_per_events"
]
},
2024-02-25 18:33:24 +01:00
{
"cell_type": "markdown",
"id": "1ede9eaa-7f0a-4856-9349-b2747d6a4901",
2024-03-13 23:24:38 +01:00
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
2024-02-25 18:33:24 +01:00
"source": [
"# Fin travail 25/02"
]
},
{
"cell_type": "markdown",
"id": "c437eaec",
2024-01-13 10:38:10 +01:00
"metadata": {},
"source": [
2024-03-26 11:49:09 +01:00
"# Exemple sur Company 1"
2024-01-13 10:38:10 +01:00
]
},
2024-02-05 22:04:02 +01:00
{
"cell_type": "markdown",
2024-02-10 22:46:56 +01:00
"id": "e855f403",
2024-03-26 11:49:09 +01:00
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
2024-02-05 22:04:02 +01:00
"source": [
"## customersplus.csv"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "91a8f8c4",
2024-02-05 22:04:02 +01:00
"metadata": {},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-02-05 22:04:02 +01:00
"source": [
"a = pd.DataFrame(df1_customersplus.info())"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "2fda171d",
2024-02-05 22:04:02 +01:00
"metadata": {},
"outputs": [],
"source": [
"def info_colonnes_dataframe(df):\n",
" # Créer une liste pour stocker les informations sur chaque colonne\n",
" infos_colonnes = []\n",
"\n",
" # Parcourir les colonnes du DataFrame\n",
" for nom_colonne, serie in df.items(): # Utiliser items() au lieu de iteritems()\n",
" # Calculer le taux de valeurs manquantes\n",
" taux_na = serie.isna().mean() * 100\n",
"\n",
" # Ajouter les informations à la liste\n",
" infos_colonnes.append({\n",
" 'Nom_colonne': nom_colonne,\n",
" 'Type_colonne': str(serie.dtype),\n",
" 'Taux_NA': taux_na\n",
" })\n",
"\n",
" # Créer une nouvelle DataFrame à partir de la liste d'informations\n",
" df_infos_colonnes = pd.DataFrame(infos_colonnes)\n",
"\n",
" return df_infos_colonnes"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "205eeeab",
2024-02-05 22:04:02 +01:00
"metadata": {},
"outputs": [],
"source": [
"def cleaning_date(df, column_name):\n",
" \"\"\"\n",
" Nettoie la colonne spécifiée du DataFrame en convertissant les valeurs en datetime avec le format ISO8601.\n",
"\n",
" Parameters:\n",
" - df: DataFrame\n",
" Le DataFrame contenant la colonne à nettoyer.\n",
" - column_name: str\n",
" Le nom de la colonne à nettoyer.\n",
"\n",
" Returns:\n",
" - DataFrame\n",
" Le DataFrame modifié avec la colonne nettoyée.\n",
" \"\"\"\n",
" df[column_name] = pd.to_datetime(df[column_name], utc = True, format = 'ISO8601')\n",
" return df"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "634282c5",
2024-02-05 22:04:02 +01:00
"metadata": {},
"outputs": [],
"source": [
"a = info_colonnes_dataframe(df1_customersplus)"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "0e8d4133",
2024-02-05 22:04:02 +01:00
"metadata": {},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-02-05 22:04:02 +01:00
"source": [
"a"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "1268ad5a",
2024-02-05 22:04:02 +01:00
"metadata": {},
"outputs": [],
"source": [
"a = pd.DataFrame(df1_customersplus.isna().sum()/len(df1_customersplus)*100)"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "bd41dc80",
2024-02-05 22:04:02 +01:00
"metadata": {},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-02-05 22:04:02 +01:00
"source": [
"# Selection des variables\n",
"df1_customersplus_clean = df1_customersplus.copy()\n",
"\n",
"cleaning_date(df1_customersplus_clean, 'first_buying_date')\n",
"cleaning_date(df1_customersplus_clean, 'last_visiting_date')\n",
"\n",
"df1_customersplus_clean.drop(['lastname', 'firstname', 'email', 'civility', 'note', 'created_at', 'updated_at', 'deleted_at', 'extra', 'reference', 'extra_field', 'identifier', 'need_reload', 'preferred_category', 'preferred_supplier', 'preferred_formula', 'zipcode', 'last_visiting_date'], axis = 1, inplace=True)\n",
"df1_customersplus_clean.rename(columns = {'id' : 'customer_id'}, inplace = True)\n",
"\n"
]
},
2024-01-13 14:47:24 +01:00
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "2455d2e1",
2024-01-13 14:47:24 +01:00
"metadata": {
"scrolled": true
},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-01-10 19:19:51 +01:00
"source": [
2024-01-13 14:47:24 +01:00
"df1_purchases"
2024-01-10 19:19:51 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "5f9a159d",
2024-01-10 19:19:51 +01:00
"metadata": {},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-01-10 19:19:51 +01:00
"source": [
2024-01-13 14:47:24 +01:00
"df1_purchases.info()"
2024-01-10 19:19:51 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "db201bf7",
2024-01-10 19:19:51 +01:00
"metadata": {},
2024-01-13 14:47:24 +01:00
"outputs": [],
2024-01-10 19:19:51 +01:00
"source": [
2024-01-13 14:47:24 +01:00
"# Nettoyage purchase_date\n",
"df1_purchases['purchase_date'] = pd.to_datetime(df1_purchases['purchase_date'], utc = True)\n",
"df1_purchases['purchase_date'] = pd.to_datetime(df1_purchases['purchase_date'], format = 'ISO8601')"
2024-01-10 19:19:51 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "bd436fca",
2024-01-10 19:19:51 +01:00
"metadata": {},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-01-10 19:19:51 +01:00
"source": [
2024-01-13 14:47:24 +01:00
"df1_purchases.info()"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "83435862",
2024-01-13 14:47:24 +01:00
"metadata": {},
"outputs": [],
"source": [
"# Selection des variables\n",
"df1_purchases_clean = df1_purchases[['id', 'purchase_date', 'customer_id']]"
]
},
2024-01-14 17:38:16 +01:00
{
"cell_type": "markdown",
2024-02-10 22:46:56 +01:00
"id": "637bdb72",
2024-01-14 17:38:16 +01:00
"metadata": {},
"source": [
2024-02-04 16:02:01 +01:00
"# Customer information"
2024-01-14 17:38:16 +01:00
]
},
{
2024-02-04 16:02:01 +01:00
"cell_type": "markdown",
2024-02-10 22:46:56 +01:00
"id": "14c52894",
2024-03-26 11:49:09 +01:00
"metadata": {
"jp-MarkdownHeadingCollapsed": true
},
2024-01-14 17:38:16 +01:00
"source": [
2024-03-26 11:49:09 +01:00
"## Target area - NLP"
2024-01-14 17:38:16 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "d83abfbf",
2024-01-14 17:38:16 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-01-14 17:38:16 +01:00
"source": [
2024-02-04 16:02:01 +01:00
"# Target.csv cleaning\n",
"df1_targets_clean = df1_targets[[\"id\", \"target_type_id\", \"name\"]]\n",
"df1_targets_clean.rename(columns = {'id' : 'target_id' , 'name' : 'target_name'}, inplace = True)\n",
"\n",
"# target_type cleaning\n",
"df1_target_types_clean = df1_target_types[[\"id\",\"is_import\",\"name\"]].add_prefix(\"target_type_\")\n",
"\n",
"#customer_target_mappings cleaning\n",
"df1_customer_target_mappings_clean = df1_customer_target_mappings[[\"id\", \"customer_id\", \"target_id\"]]\n",
"\n",
"# Merge target et target_type\n",
"df1_targets_full = pd.merge(df1_targets_clean, df1_target_types_clean, left_on='target_type_id', right_on='target_type_id', how='inner')\n",
"df1_targets_full.drop(['target_type_id'], axis = 1, inplace=True)\n",
"\n",
"# Merge\n",
"df1_targets_full = pd.merge(df1_customer_target_mappings_clean, df1_targets_full, left_on='target_id', right_on='target_id', how='inner')\n",
"df1_targets_full.drop(['target_id'], axis = 1, inplace=True)"
2024-01-14 17:38:16 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "90d71b2c",
2024-01-14 17:38:16 +01:00
"metadata": {},
2024-02-10 22:46:56 +01:00
"outputs": [],
2024-02-04 16:02:01 +01:00
"source": [
"df1_targets_test = df1_targets_full[['id', 'customer_id']].groupby(['customer_id']).count()\n",
"len(df1_targets_test[df1_targets_test['id'] > 1]) / len(df1_targets_test)\n",
"\n",
"# 99,6% des 151 000 client visés sont catégorisés plusieurs fois et en moyenne 5 fois... \n",
"df1_targets_test.mean()\n"
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "2301de1e",
2024-02-07 23:28:55 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-04 16:02:01 +01:00
"source": [
2024-02-07 23:28:55 +01:00
"df1_targets_full.head()"
2024-02-04 16:02:01 +01:00
]
},
{
2024-02-07 23:28:55 +01:00
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "75fbc2f7",
2024-02-07 23:28:55 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-04 16:02:01 +01:00
"source": [
2024-02-07 23:28:55 +01:00
"# Catégorisation des target_name\n",
"import pandas as pd\n",
"import nltk\n",
"from nltk.tokenize import word_tokenize\n",
"from nltk.corpus import stopwords\n",
"from nltk.stem import WordNetLemmatizer\n",
"from nltk.probability import FreqDist\n",
"\n",
"# Téléchargement des ressources nécessaires\n",
"nltk.download('punkt')\n",
"nltk.download('stopwords')\n",
"nltk.download('wordnet')\n",
"\n"
2024-02-04 16:02:01 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "55cddf92",
2024-02-04 16:02:01 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-04 16:02:01 +01:00
"source": [
2024-02-07 23:28:55 +01:00
"# Définition des fonctions de tokenisation, suppression des mots vides et lemmatisation\n",
"def preprocess_text(texte):\n",
" # Concaténation des éléments de la liste en une seule chaîne de caractères\n",
" texte_concat = ' '.join(texte)\n",
" \n",
" # Tokenisation des mots\n",
" tokens = word_tokenize(texte_concat.lower())\n",
" \n",
" # Suppression des mots vides (stopwords)\n",
" stop_words = set(stopwords.words('french'))\n",
" filtered_tokens = [word for word in tokens if word not in stop_words]\n",
" \n",
" # Lemmatisation des mots\n",
" lemmatizer = WordNetLemmatizer()\n",
" lemmatized_tokens = [lemmatizer.lemmatize(word) for word in filtered_tokens]\n",
" \n",
" return lemmatized_tokens\n",
2024-02-04 16:02:01 +01:00
"\n",
"\n",
2024-02-07 23:28:55 +01:00
"# Appliquer le prétraitement à la colonne de texte\n",
"df1_targets_full['target_name_tokened'] = df1_targets_full['target_name'].apply(preprocess_text)\n",
"\n",
"# Concaténer les listes de mots pour obtenir une liste de tous les mots dans le corpus\n",
"all_words = [word for tokens in df1_targets_full['target_name_tokened'] for word in tokens]\n",
"\n",
"# Calculer la fréquence des mots\n",
"freq_dist = FreqDist(all_words)\n",
"\n",
"\n"
2024-02-04 16:02:01 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "7fd98a85",
2024-02-04 16:02:01 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-04 16:02:01 +01:00
"source": [
2024-02-07 23:28:55 +01:00
"# Affichage des mots les plus fréquents\n",
"print(\"Mots les plus fréquents:\")\n",
"for mot, freq in freq_dist.most_common(15):\n",
" print(f\"{mot}: {freq}\")"
2024-02-04 16:02:01 +01:00
]
},
{
"cell_type": "code",
2024-03-23 10:48:47 +01:00
"execution_count": null,
2024-02-10 22:46:56 +01:00
"id": "cf94bb1d",
2024-02-04 16:02:01 +01:00
"metadata": {},
2024-03-23 10:48:47 +01:00
"outputs": [],
2024-02-07 23:28:55 +01:00
"source": [
"import pandas as pd\n",
"import nltk\n",
"from nltk.tokenize import word_tokenize\n",
"from nltk.corpus import stopwords\n",
"from nltk.stem import WordNetLemmatizer\n",
"\n",
"# Téléchargement des ressources nécessaires\n",
"nltk.download('punkt')\n",
"nltk.download('stopwords')\n",
"nltk.download('wordnet')\n",
"\n",
"# Création de la DataFrame d'exemple\n",
"data = {'texte': [\"Le chat noir mange une souris.\", \"Le chien blanc aboie.\"]}\n",
"df = pd.DataFrame(data)\n",
"\n",
"# Fonction pour prétraiter le texte\n",
"def preprocess_text(texte):\n",
" # Concaténation des éléments de la liste en une seule chaîne de caractères\n",
" texte_concat = ' '.join(texte)\n",
" \n",
" # Tokenisation des mots\n",
" tokens = word_tokenize(texte_concat.lower())\n",
" \n",
" # Suppression des mots vides (stopwords)\n",
" stop_words = set(stopwords.words('french'))\n",
" filtered_tokens = [word for word in tokens if word not in stop_words]\n",
" \n",
" # Lemmatisation des mots\n",
" lemmatizer = WordNetLemmatizer()\n",
" lemmatized_tokens = [lemmatizer.lemmatize(word) for word in filtered_tokens]\n",
" \n",
" return lemmatized_tokens\n",
"\n",
2024-02-10 22:46:56 +01:00
"# Appliquer la fonction de prétraitement à la colonne de texte\n",
"df['texte_preprocessed'] = df['texte'].apply(preprocess_text)\n",
"\n",
"# Afficher le résultat\n",
"print(df)\n"
]
2024-01-10 19:19:51 +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",
2024-02-19 23:11:28 +01:00
"version": "3.11.6"
2024-01-10 19:19:51 +01:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}
