0_2_Dataset_construction.py

@@ -146,13 +146,22 @@ BUCKET_OUT = f'projet-bdc2324-team1/Generalization/{type_of_comp}'
 
 # Create test dataset and train dataset for sport companies
 
+<<<<<<< HEAD
 #start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_features = 0.7)
+=======
+# start_date, end_of_features, final_date = df_coverage_modelization(list_of_comp, coverage_train = 0.7)
+>>>>>>> main
 start_date = "2021-05-01"
 end_of_features = "2022-11-01"
 final_date = "2023-11-01"
 
+<<<<<<< HEAD
 anonymous_customer = {'1' : 1_1, '2' : 2_12184, '3' : 3_1, '4' : 4_2, '101' : 101_1,
                       '5' : 5_191835, '6' : 6_591412, '7' : 7_49632, '8' : 8_1942, '9' : 9_19683}
+=======
+anonymous_customer = {'1' : 1, '2' : 12184, '3' : 1, '4' : 2, '101' : 1,
+                      '5' : 191835, '6' : 591412, '7' : 49632, '8' : 1942, '9' : 19683}
+>>>>>>> main
 
 for company in list_of_comp:
     dataset = dataset_construction(min_date = start_date, end_features_date = end_of_features,
@@ -161,6 +170,7 @@ for company in list_of_comp:
     # On retire le client anonyme
     dataset = dataset[dataset['customer_id'] != anonymous_customer[company]]
 
+<<<<<<< HEAD
     #train test set
     np.random.seed(42)
     
@@ -170,6 +180,10 @@ for company in list_of_comp:
     dataset = dataset.sample(frac=1).reset_index(drop=True)
     dataset_train = dataset.iloc[:split_index]
     dataset_test = dataset.iloc[split_index:]
+=======
+    # On retire le client anonyme
+    dataset_test = dataset_test[dataset_test['customer_id'] != anonymous_customer[company]]
+>>>>>>> main
     
     # Exportation
     FILE_KEY_OUT_S3 = "dataset_test" + company +  ".csv"

0_KPI_functions.py

@@ -90,6 +90,11 @@ def tickets_kpi_function(tickets_information = None):
 
     # tickets_kpi = tickets_kpi.merge(avg_amount, how='left', on= 'event_type_id')
 
+    #Taux de ticket payé par internet selon les compagnies
+
+  #tickets_kpi["Taux_ticket_internet"] = tickets_kpi["nb_tickets_internet"]*100 / tickets_kpi["nb_tickets"]
+  #tickets_kpi['Taux_ticket_internet'] = tickets_kpi['Taux_ticket_internet'].fillna(0)
+
     return tickets_kpi
 
 def customerplus_kpi_function(customerplus_clean = None):