104 lines
3.3 KiB
Plaintext
104 lines
3.3 KiB
Plaintext
|
{
|
||
|
|
"cells": [
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"id": "718d4e6d-b90a-4955-90ee-c1518246c07c",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [
|
||
|
|
{
|
||
|
|
"name": "stdin",
|
||
|
|
"output_type": "stream",
|
||
|
|
"text": [
|
||
|
|
"Choisissez le type de compagnie : sport ? musique ? musee ? sport\n"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"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"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"source": [
|
||
|
|
"import pandas as pd\n",
|
||
|
|
"import numpy as np\n",
|
||
|
|
"import os\n",
|
||
|
|
"import s3fs\n",
|
||
|
|
"import re\n",
|
||
|
|
"import warnings\n",
|
||
|
|
"\n",
|
||
|
|
"# Ignore warning\n",
|
||
|
|
"warnings.filterwarnings('ignore')\n",
|
||
|
|
"\n",
|
||
|
|
"exec(open('../0_KPI_functions.py').read())\n",
|
||
|
|
"exec(open('plot.py').read())\n",
|
||
|
|
"\n",
|
||
|
|
"# Create filesystem object\n",
|
||
|
|
"S3_ENDPOINT_URL = \"https://\" + os.environ[\"AWS_S3_ENDPOINT\"]\n",
|
||
|
|
"fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})\n",
|
||
|
|
"\n",
|
||
|
|
"companies = {'musee' : ['1', '2', '3', '4'], # , '101'\n",
|
||
|
|
" 'sport': ['5', '6'],\n",
|
||
|
|
" 'musique' : ['10', '11', '12', '13', '14']}\n",
|
||
|
|
"\n",
|
||
|
|
"\n",
|
||
|
|
"type_of_activity = input('Choisissez le type de compagnie : sport ? musique ? musee ?')\n",
|
||
|
|
"list_of_comp = companies[type_of_activity] \n",
|
||
|
|
"\n",
|
||
|
|
"# Load files\n",
|
||
|
|
"customer, campaigns_kpi, campaigns_brut, tickets, products = load_files(list_of_comp)"
|
||
|
|
]
|
||
|
|
},
|
||
|
|
{
|
||
|
|
"cell_type": "code",
|
||
|
|
"execution_count": null,
|
||
|
|
"id": "b967f70a-e3ae-423e-9fb0-edfc00ddf826",
|
||
|
|
"metadata": {},
|
||
|
|
"outputs": [],
|
||
|
|
"source": [
|
||
|
|
"# Identify anonymous customer for each company and remove them from our datasets\n",
|
||
|
|
"outlier_list = outlier_detection(tickets, list_of_comp)\n",
|
||
|
|
"\n",
|
||
|
|
"# Identify valid customer (customer who bought tickets after starting date or received mails after starting date)\n",
|
||
|
|
"customer_valid_list = valid_customer_detection(products, campaigns_brut)\n",
|
||
|
|
"\n",
|
||
|
|
"# Identify customer who bought during the period of y\n",
|
||
|
|
"consumer_target_period = identify_purchase_during_target_periode(products)\n",
|
||
|
|
"\n",
|
||
|
|
"databases = [customer, campaigns_kpi, campaigns_brut, tickets, products]\n",
|
||
|
|
"\n",
|
||
|
|
"for dataset in databases:\n",
|
||
|
|
" dataset['customer_id'] = dataset['customer_id'].apply(lambda x: remove_elements(x, outlier_list))# remove outlier\n",
|
||
|
|
" dataset['customer_id'] = dataset['customer_id'].isin(customer_valid_list) # keep only valid customer\n",
|
||
|
|
" dataset['has_purchased_target_period'] = np.where(dataset['customer_id'].isin(customer_valid_list), 1, 0)"
|
||
|
|
]
|
||
|
|
}
|
||
|
|
],
|
||
|
|
"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
|
||
|
|
}
|