BDC-team-1/0_2_Dataset_construction.py

# Business Data Challenge - Team 1

import pandas as pd
import numpy as np
import os
import s3fs
import re
import warnings
from datetime import date, timedelta, datetime

# Create filesystem object
S3_ENDPOINT_URL = "https://" + os.environ["AWS_S3_ENDPOINT"]
fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})


# Import KPI construction functions
exec(open('0_KPI_functions.py').read())

# Ignore warning
warnings.filterwarnings('ignore')


def display_covering_time(df, company, datecover):
    """
    This function draws the time coverage of each company
    """
    min_date = df['purchase_date'].min().strftime("%Y-%m-%d")
    max_date = df['purchase_date'].max().strftime("%Y-%m-%d")
    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)]
    print(f'Couverture Company {company} : {min_date} - {max_date}')
    return datecover


def compute_time_intersection(datecover):
    """
    This function returns the time coverage for all companies
    """
    timestamps_sets = [set(timestamps) for timestamps in datecover.values()]
    intersection = set.intersection(*timestamps_sets)
    intersection_list = list(intersection)
    formated_dates = [dt.strftime("%Y-%m-%d") for dt in intersection_list]
    return sorted(formated_dates)


def df_coverage_modelization(sport, coverage_train = 0.7):
    """
    This function returns start_date, end_of_features and final dates
    that help to construct train and test datasets
    """
    datecover = {}
    for company in sport:
        df_products_purchased_reduced = display_databases(company, file_name = "products_purchased_reduced",
                                                          datetime_col = ['purchase_date'])
        datecover = display_covering_time(df_products_purchased_reduced, company, datecover)
    #print(datecover.keys())
    dt_coverage = compute_time_intersection(datecover)
    start_date = dt_coverage[0]
    end_of_features = dt_coverage[int(0.7 * len(dt_coverage))]
    final_date = dt_coverage[-1]
    return start_date, end_of_features, final_date
    

def dataset_construction(min_date, end_features_date, max_date, directory_path):
    
    # Import customerplus
    df_customerplus_clean_0 = display_databases(directory_path, file_name = "customerplus_cleaned")
    df_campaigns_information = display_databases(directory_path, file_name = "campaigns_information", datetime_col = ['opened_at', 'sent_at', 'campaign_sent_at'])
    df_products_purchased_reduced = display_databases(directory_path, file_name = "products_purchased_reduced", datetime_col = ['purchase_date'])

    # if directory_path == "101":
    #     df_products_purchased_reduced_1 = display_databases(directory_path, file_name = "products_purchased_reduced_1", datetime_col = ['purchase_date'])
    #     df_products_purchased_reduced = pd.concat([df_products_purchased_reduced, df_products_purchased_reduced_1])
    
    # Filtre de cohérence pour la mise en pratique de notre méthode
    max_date =  pd.to_datetime(max_date, utc = True, format = 'ISO8601') 
    end_features_date = pd.to_datetime(end_features_date, utc = True, format = 'ISO8601')
    min_date = pd.to_datetime(min_date, utc = True, format = 'ISO8601')

    #Filtre de la base df_campaigns_information
    df_campaigns_information = df_campaigns_information[(df_campaigns_information['sent_at'] <= end_features_date) & (df_campaigns_information['sent_at'] >= min_date)]
    df_campaigns_information['opened_at'][df_campaigns_information['opened_at'] >= end_features_date] = np.datetime64('NaT')
    
    #Filtre de la base df_products_purchased_reduced
    df_products_purchased_reduced = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= end_features_date) & (df_products_purchased_reduced['purchase_date'] >= min_date)]

    print("Data filtering : SUCCESS")
    
    # Fusion de l'ensemble et creation des KPI

    # KPI sur les campagnes publicitaires
    df_campaigns_kpi = campaigns_kpi_function(campaigns_information = df_campaigns_information) 

    # KPI sur le comportement d'achat
    df_tickets_kpi = tickets_kpi_function(tickets_information = df_products_purchased_reduced)

    # KPI sur les données socio-démographiques
    df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0)
    
    print("KPIs construction : SUCCESS")
    
    # Fusion avec KPI liés au customer
    df_customer = pd.merge(df_customerplus_clean, df_campaigns_kpi, on = 'customer_id', how = 'left')
    
    # Fill NaN values
    df_customer[['nb_campaigns', 'nb_campaigns_opened']] = df_customer[['nb_campaigns', 'nb_campaigns_opened']].fillna(0)
    
    # Fusion avec KPI liés au comportement d'achat
    df_customer_product = pd.merge(df_tickets_kpi, df_customer, on = 'customer_id', how = 'outer')
    
    # Fill NaN values
    df_customer_product[['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'nb_tickets_internet']] = df_customer_product[['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'nb_tickets_internet']].fillna(0)

    print("Explanatory variable construction : SUCCESS")

    # 2. Construction of the explained variable 
    df_products_purchased_to_predict = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= max_date) & (df_products_purchased_reduced['purchase_date'] > end_features_date)]

    # Indicatrice d'achat
    df_products_purchased_to_predict['y_has_purchased'] = 1

    y = df_products_purchased_to_predict[['customer_id', 'y_has_purchased']].drop_duplicates()

    print("Explained variable construction : SUCCESS")
    
    # 3. Merge between explained and explanatory variables
    dataset = pd.merge(df_customer_product, y, on = ['customer_id'], how = 'left')

    # 0 if there is no purchase
    dataset[['y_has_purchased']].fillna(0)

    # add id_company prefix to customer_id
    dataset['customer_id'] = directory_path + '_' + dataset['customer_id'].astype('str')
    
    return dataset

## Exportation

companies = {'musee' : ['1', '2', '3', '4'], # , '101'
            'sport': ['5', '6', '7', '8', '9'],
            'musique' : ['10', '11', '12', '13', '14']}

type_of_comp = input('Choisissez le type de compagnie : sport ? musique ? musee ?')
list_of_comp = companies[type_of_comp] 
# Dossier d'exportation
BUCKET_OUT = f'projet-bdc2324-team1/Generalization/{type_of_comp}'

# Create test dataset and train dataset for sport companies

# start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_train = 0.7)
start_date = "2021-05-01"
end_of_features = "2022-11-01"
final_date = "2023-11-01"

anonymous_customer = {'1' : 1, '2' : 12184, '3' : 1, '4' : 2, '101' : 1,
                      '5' : 191835, '6' : 591412, '7' : 49632, '8' : 1942, '9' : 19683}

for company in list_of_comp:
    dataset_test = dataset_construction(min_date = start_date, end_features_date = end_of_features,
                                        max_date = final_date, directory_path = company)    

    # On retire le client anonyme
    dataset_test = dataset_test[dataset_test['customer_id'] != anonymous_customer[company]]
    
    # Exportation
    FILE_KEY_OUT_S3 = "dataset_test" + company +  ".csv"
    FILE_PATH_OUT_S3 = BUCKET_OUT + "/Test_set/" + FILE_KEY_OUT_S3
    
    with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
        dataset_test.to_csv(file_out, index = False)
    
    print("Exportation dataset test : SUCCESS")

# Dataset train
    dataset_train = dataset_construction(min_date = start_date, end_features_date = end_of_features,
                                        max_date = final_date, directory_path = company)
    # Export
    FILE_KEY_OUT_S3 = "dataset_train" + company + ".csv" 
    FILE_PATH_OUT_S3 = BUCKET_OUT + "/Train_test/" + FILE_KEY_OUT_S3
    
    with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
        dataset_train.to_csv(file_out, index = False)
        
    print("Exportation dataset train : SUCCESS")


print("FIN DE LA GENERATION DES DATASETS : SUCCESS")