add function description

utils_ml.py

@@ -49,6 +49,9 @@ def load_train_test(type_of_activity, type_of_model):
 
 
 def save_file_s3(File_name, type_of_activity, type_of_model, model):
+    """
+    save plot into s3 storage
+    """
     image_buffer = io.BytesIO()
     plt.savefig(image_buffer, format='png')
     image_buffer.seek(0)
@@ -60,6 +63,9 @@ def save_file_s3(File_name, type_of_activity, type_of_model, model):
 
 
 def save_result_set_s3(result_set, File_name, type_of_activity, type_of_model, model=None, model_path=False):
+    """
+    save result into s3 storage
+    """
     if model_path:
         FILE_PATH_OUT_S3 = f"projet-bdc2324-team1/2_Output/2_1_Modeling_results/{type_of_model}/{type_of_activity}/{model}/" + File_name + '.csv'
     else:
@@ -69,6 +75,9 @@ def save_result_set_s3(result_set, File_name, type_of_activity, type_of_model, m
 
 
 def save_model_s3(File_name, type_of_activity, type_of_model, model, classifier):
+    """
+    save model into pickle file
+    """
     model_bytes = pickle.dumps(classifier)
     FILE_PATH_OUT_S3 = f"projet-bdc2324-team1/2_Output/2_1_Modeling_results/{type_of_model}/{type_of_activity}/{model}/" + File_name + '.pkl'
     with fs.open(FILE_PATH_OUT_S3, 'wb') as f:
@@ -88,6 +97,9 @@ def compute_recall_companies(dataset_test, y_pred, type_of_activity, model):
 
 
 def features_target_split(dataset_train, dataset_test):
+    """
+    return train and test set
+    """
     features_l = ['nb_campaigns', 'taux_ouverture_mail', 'prop_purchases_internet', 'nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'time_to_open',
                            'purchases_10_2021','purchases_10_2022', 'purchases_11_2021', 'purchases_12_2021','purchases_1_2022', 'purchases_2_2022', 'purchases_3_2022',
                             'purchases_4_2022', 'purchases_5_2021', 'purchases_5_2022', 'purchases_6_2021', 'purchases_6_2022', 'purchases_7_2021', 'purchases_7_2022', 'purchases_8_2021',
@@ -105,7 +117,10 @@ def features_target_split(dataset_train, dataset_test):
 
 
 def preprocess(type_of_model,  type_of_activity):
-
+    """
+    preprocess variables before running machine learning pipeline
+    """
+    
     numeric_features = ['nb_campaigns', 'taux_ouverture_mail', 'prop_purchases_internet', 'nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers',
                            'purchases_10_2021','purchases_10_2022', 'purchases_11_2021', 'purchases_12_2021','purchases_1_2022', 'purchases_2_2022', 'purchases_3_2022',
                             'purchases_4_2022', 'purchases_5_2021', 'purchases_5_2022', 'purchases_6_2021', 'purchases_6_2022', 'purchases_7_2021', 'purchases_7_2022', 'purchases_8_2021',

utils_stat_desc.py

@@ -1,6 +1,10 @@
 
 
 def load_files(nb_compagnie):
+    """
+    load and preprocess dataframes
+    """
+    
     customer = pd.DataFrame()
     campaigns_brut = pd.DataFrame()
     campaigns_kpi = pd.DataFrame()
@@ -8,7 +12,6 @@ def load_files(nb_compagnie):
     tickets = pd.DataFrame()
     targets = pd.DataFrame()
     
-    # début de la boucle permettant de générer des datasets agrégés pour les 5 compagnies de spectacle
     for directory_path in nb_compagnie:
         df_customerplus_clean_0 = display_input_databases(directory_path, file_name = "customerplus_cleaned")
         df_campaigns_brut = display_input_databases(directory_path, file_name = "campaigns_information", datetime_col = ['opened_at', 'sent_at', 'campaign_sent_at'])
@@ -26,7 +29,7 @@ def load_files(nb_compagnie):
         targets_columns.remove('customer_id')
         df_target_KPI[targets_columns] = df_target_KPI[targets_columns].fillna(0)
         
-    # creation de la colonne Number compagnie, qui permettra d'agréger les résultats
+    # Create company identifier
         df_tickets_kpi["number_company"]=int(directory_path)
         df_campaigns_brut["number_company"]=int(directory_path)
         df_campaigns_kpi["number_company"]=int(directory_path)
@@ -34,7 +37,7 @@ def load_files(nb_compagnie):
         df_target_information["number_company"]=int(directory_path)
         df_target_KPI["number_company"]=int(directory_path)
     
-    # Traitement des index
+    # Clean index
         df_tickets_kpi["customer_id"]= directory_path + '_' +  df_tickets_kpi['customer_id'].astype('str')
         df_campaigns_brut["customer_id"]= directory_path + '_' +  df_campaigns_brut['customer_id'].astype('str')
         df_campaigns_kpi["customer_id"]= directory_path + '_' +  df_campaigns_kpi['customer_id'].astype('str') 
@@ -51,7 +54,7 @@ def load_files(nb_compagnie):
         df_target_KPI["customer_id"]= directory_path + '_' +  df_target_KPI['customer_id'].astype('str')
 
     
-    # Concaténation
+    # Concatenation
         customer = pd.concat([customer, df_customerplus_clean], ignore_index=True)
         campaigns_kpi = pd.concat([campaigns_kpi, df_campaigns_kpi], ignore_index=True)
         campaigns_brut = pd.concat([campaigns_brut, df_campaigns_brut], ignore_index=True) 
@@ -73,6 +76,9 @@ def remove_outlier_total_amount(tickets):
     
 
 def save_file_s3(File_name, type_of_activity):
+    """
+    save plots into s3 storage
+    """
     image_buffer = io.BytesIO()
     plt.savefig(image_buffer, format='png', pad_inches=1, bbox_inches="tight", dpi = 150)
     image_buffer.seek(0)
@@ -84,7 +90,9 @@ def save_file_s3(File_name, type_of_activity):
 
 
 def outlier_detection(tickets, company_list, show_diagram=False):
-
+    """
+    detect anonymous customers
+    """
     outlier_list = list()
     
     for company in company_list:
@@ -114,6 +122,9 @@ def outlier_detection(tickets, company_list, show_diagram=False):
 
 
 def valid_customer_detection(products, campaigns_brut):
+    """
+    identify customer that are in our time perimeter
+    """
     products_valid = products[products['purchase_date']>="2021-05-01"]
     consumer_valid_product = products_valid['customer_id'].to_list()
 
@@ -125,6 +136,9 @@ def valid_customer_detection(products, campaigns_brut):
 
 
 def identify_purchase_during_target_periode(products):
+    """
+    identify customer who purchased ticket during the target period
+    """
     products_target_period = products[(products['purchase_date']>="2022-11-01")
     & (products['purchase_date']<="2023-11-01")]
     customer_target_period = products_target_period['customer_id'].to_list()