Ajout dummies pays et genre

0_Cleaning_and_merge.py

@@ -39,16 +39,18 @@ for i in range(len(liste_database)) :
 # Cleaning customerplus
 df1_customerplus_clean = preprocessing_customerplus(df1_customersplus)
 
-# Cleaning ticket area
-df1_ticket_information = preprocessing_tickets_area(tickets = df1_tickets, purchases = df1_purchases, suppliers = df1_suppliers, type_ofs = df1_type_ofs)
-
 # 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)
 
-# Cleaning product area
+## 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'
 
@@ -63,6 +65,14 @@ df1_products_purchased = pd.merge(df1_ticket_information, products_global, left_
 # 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):
@@ -81,10 +91,29 @@ def explanatory_variables(min_date = "2021-09-01", max_date = "2023-09-01", df_c
     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')
     
@@ -97,6 +126,8 @@ def explanatory_variables(min_date = "2021-09-01", max_date = "2023-09-01", df_c
     # 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
@@ -110,6 +141,8 @@ def explained_variable(min_date = "2023-08-01", max_date = "2023-11-01", df_prod
 
     y = df_products_purchased_reduced[['customer_id', 'event_type_id', 'y_has_purchased']].drop_duplicates()
 
+    print("Explained variable construction : SUCCESS")
+    
     return y
 
 ## Exportation
@@ -117,12 +150,14 @@ def explained_variable(min_date = "2023-08-01", max_date = "2023-11-01", df_prod
 # 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
 
@@ -131,12 +166,14 @@ with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
 
 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
 
@@ -146,8 +183,4 @@ with fs.open(FILE_PATH_OUT_S3, 'w') as file_out:
 print("Exportation dataset train : SUCCESS")
 
 
-
+print("FIN DE LA GENERATION DES DATASETS : SUCCESS")
-# # Exportation vers 'projet-bdc2324-team1'
-
-
-print("Exportation base de la base X d'entraînement : SUCCESS")

0_Cleaning_and_merge_functions.py

@@ -27,7 +27,7 @@ def preprocessing_customerplus(customerplus = None):
     cleaning_date(customerplus_copy, 'last_visiting_date')
     
     # Selection des variables
-    customerplus_copy.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)
+    customerplus_copy.drop(['lastname', 'firstname', 'birthdate', 'profession', 'language', 'age', '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)
     customerplus_copy.rename(columns = {'id' : 'customer_id'}, inplace = True)
 
     return customerplus_copy