add kpi function for customerplus

0_2_Dataset_construction.py

@@ -63,7 +63,7 @@ def df_coverage_modelization(sport, coverage_train = 0.7):
 def dataset_construction(min_date, end_features_date, max_date, directory_path):
     
     # Import customerplus
-    df_customerplus_clean = display_databases(directory_path, file_name = "customerplus_cleaned")
+    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'])
     
@@ -89,19 +89,8 @@ def dataset_construction(min_date, end_features_date, max_date, directory_path):
     # 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)
+    # KPI sur les données socio-démographiques
+    df_customerplus_clean = customerplus_kpi_function(customerplus_clean = df_customerplus_clean_0)
     
     print("KPIs construction : SUCCESS")
     

0_KPI_functions.py

@@ -93,5 +93,22 @@ def tickets_kpi_function(tickets_information = None):
 
     return tickets_kpi
 
+def customerplus_kpi_function(customerplus_clean = None):
+    # KPI sur les données socio-demographique    
+    ## Le genre
+    customerplus_clean["gender_label"] = customerplus_clean["gender"].map({
+        0: 'female',
+        1: 'male',
+        2: 'other'
+    })
+    gender_dummies = pd.get_dummies(customerplus_clean["gender_label"], prefix='gender').astype(int)
+    customerplus_clean = pd.concat([customerplus_clean, gender_dummies], axis=1)
 
+    ## Indicatrice si individue vit en France
+    customerplus_clean["country_fr"] = customerplus_clean["country"].apply(lambda x : int(x=="fr") if pd.notna(x) else np.nan)
+
+    # Dummy if the customer has a structure id (tags)
+    customerplus_clean['has_tags'] = customerplus_clean['structure_id'].apply(lambda x: 1 if not pd.isna(x) else 0)
+
+    return customerplus_clean