BDC-team-1/0_Cleaning_and_merge.py
2024-02-13 22:41:52 +00:00

194 lines
8.1 KiB
Python

# Business Data Challenge - Team 1
import pandas as pd
import numpy as np
import os
import s3fs
import re
import warnings
# Import cleaning and merge functions
exec(open('BDC-team-1/0_Cleaning_and_merge_functions.py').read())
exec(open('BDC-team-1/0_KPI_functions.py').read())
# Create filesystem object
S3_ENDPOINT_URL = "https://" + os.environ["AWS_S3_ENDPOINT"]
fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})
# Ignore warning
warnings.filterwarnings('ignore')
# Data loading
BUCKET = "bdc2324-data/1"
liste_database = fs.ls(BUCKET)
# loop to create dataframes from liste
client_number = liste_database[0].split("/")[1]
df_prefix = "df" + str(client_number) + "_"
for i in range(len(liste_database)) :
current_path = liste_database[i]
with fs.open(current_path, mode="rb") as file_in:
df = pd.read_csv(file_in)
# the pattern of the name is df1xxx
nom_dataframe = df_prefix + re.search(r'\/(\d+)\/(\d+)([a-zA-Z_]+)\.csv$', current_path).group(3)
globals()[nom_dataframe] = df
## 1 - Cleaning of the datasets
# Cleaning customerplus
df1_customerplus_clean = preprocessing_customerplus(df1_customersplus)
# Cleaning target area
df1_target_information = preprocessing_target_area(targets = df1_targets, target_types = df1_target_types, customer_target_mappings = df1_customer_target_mappings)
# Cleaning campaign area
df1_campaigns_information = preprocessing_campaigns_area(campaign_stats = df1_campaign_stats, campaigns = df1_campaigns)
# Exportation
BUCKET_OUT = "projet-bdc2324-team1"
FILE_KEY_OUT_S3 = "0_Temp/Company 1 - Campaigns dataset clean.csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/" + FILE_KEY_OUT_S3
with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
df1_campaigns_information.to_csv(file_out, index = False)
## Cleaning product area
# Cleaning ticket area
df1_ticket_information = preprocessing_tickets_area(tickets = df1_tickets, purchases = df1_purchases, suppliers = df1_suppliers, type_ofs = df1_type_ofs)
BUCKET = "bdc2324-data"
directory_path = '1'
products_theme = create_products_table()
events_theme= create_events_table()
representation_theme = create_representations_table()
products_global = uniform_product_df()
# Fusion liée au product
df1_products_purchased = pd.merge(df1_ticket_information, products_global, left_on = 'product_id', right_on = 'id_products', how = 'inner')
# Selection des variables d'intérêts
df1_products_purchased_reduced = df1_products_purchased[['ticket_id', 'customer_id', 'purchase_id' ,'event_type_id', 'supplier_name', 'purchase_date', 'type_of_ticket_name', 'amount', 'children', 'is_full_price', 'name_event_types', 'name_facilities', 'name_categories', 'name_events', 'name_seasons']]
#Exportation
BUCKET_OUT = "projet-bdc2324-team1"
FILE_KEY_OUT_S3 = "0_Temp/Company 1 - Purchases.csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/" + FILE_KEY_OUT_S3
with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
df1_products_purchased_reduced.to_csv(file_out, index = False)
## 2 - Construction of KPIs on a given period
def explanatory_variables(min_date = "2021-09-01", max_date = "2023-09-01", df_campaigns_information = df1_campaigns_information, df_products_purchased_reduced = df1_products_purchased_reduced, df_customerplus_clean = df1_customerplus_clean):
# Filtre de cohérence pour la mise en pratique de notre méthode
max_date = pd.to_datetime(max_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'] <= max_date) & (df_campaigns_information['sent_at'] >= min_date)]
df_campaigns_information['opened_at'][df_campaigns_information['opened_at'] >= max_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'] <= max_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-demographique
## Le genre
df_customerplus_clean["gender_label"] = df_customerplus_clean["gender"].map({
0: 'female',
1: 'male',
2: 'other'
})
gender_dummies = pd.get_dummies(df_customerplus_clean["gender_label"], prefix='gender').astype(int)
df_customerplus_clean = pd.concat([df_customerplus_clean, gender_dummies], axis=1)
## Indicatrice si individue vit en France
df_customerplus_clean["country_fr"] = df_customerplus_clean["country"].apply(lambda x : int(x=="fr") if pd.notna(x) else np.nan)
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")
return df_customer_product
# Fonction pour créer les variables expliquée
def explained_variable(min_date = "2023-08-01", max_date = "2023-11-01", df_products_purchased_reduced = df1_products_purchased_reduced):
# Filtrer la base d'achat
df_products_purchased_reduced = df_products_purchased_reduced[(df_products_purchased_reduced['purchase_date'] <= max_date) & (df_products_purchased_reduced['purchase_date'] > min_date)]
# Indicatrice d'achat
df_products_purchased_reduced['y_has_purchased'] = 1
y = df_products_purchased_reduced[['customer_id', 'event_type_id', 'y_has_purchased']].drop_duplicates()
print("Explained variable construction : SUCCESS")
return y
## Exportation
# Dossier d'exportation
BUCKET_OUT = "projet-bdc2324-team1/1_Output/Logistique Regression databases - First approach"
# Dataset test
X_test = explanatory_variables(min_date = "2021-08-01", max_date = "2023-08-01", df_campaigns_information = df1_campaigns_information, df_products_purchased_reduced = df1_products_purchased_reduced, df_customerplus_clean = df1_customerplus_clean)
y_test = explained_variable(min_date = "2023-08-01", max_date = "2023-11-01", df_products_purchased_reduced = df1_products_purchased_reduced)
dataset_test = pd.merge(X_test, y_test, on = ['customer_id', 'event_type_id'], how = 'left')
# Exportation
FILE_KEY_OUT_S3 = "dataset_test.csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/" + 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
X_train = explanatory_variables(min_date = "2021-05-01", max_date = "2023-05-01", df_campaigns_information = df1_campaigns_information, df_products_purchased_reduced = df1_products_purchased_reduced, df_customerplus_clean = df1_customerplus_clean)
y_train = explained_variable(min_date = "2023-05-01", max_date = "2023-08-01", df_products_purchased_reduced = df1_products_purchased_reduced)
dataset_train = pd.merge(X_train, y_train, on = ['customer_id', 'event_type_id'], how = 'left')
# Exportation
FILE_KEY_OUT_S3 = "dataset_train.csv"
FILE_PATH_OUT_S3 = BUCKET_OUT + "/" + 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 train : SUCCESS")
print("FIN DE LA GENERATION DES DATASETS : SUCCESS")