add probability

0_6_Segmentation.py

@@ -11,8 +11,30 @@ import warnings
 exec(open('utils_segmentation.py').read())
 warnings.filterwarnings('ignore')
 
+# Create filesystem object
+S3_ENDPOINT_URL = "https://" + os.environ["AWS_S3_ENDPOINT"]
+fs = s3fs.S3FileSystem(client_kwargs={'endpoint_url': S3_ENDPOINT_URL})
+
+# choose the type of companies for which you want to run the pipeline
+type_of_activity = input('Choisissez le type de compagnie : sport ? musique ? musee ?')
+
+# load test set
+dataset_test = load_test_file(type_of_activity)
+
 # Load Model 
+model = load_model(type_of_activity, 'LogisticRegression_Benchmark')
 
+# Processing
+X_test = dataset_test[['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', 
+            'time_between_purchase', 'nb_tickets_internet',  'is_email_true', 'opt_in', #'is_partner',
+            'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']]
 
+y_test = dataset_test[['y_has_purchased']]
 
-model = load_model(type_of_activity, model)
+# Prediction
+y_pred_prob = model.predict_proba(X_test)[:, 1]
+
+# Add probability to dataset_test
+dataset_test['Probability_to_buy'] = y_pred_prob
+print('probability added to dataset_test')
+print(dataset_test.head())

utils_ml.py

@@ -84,7 +84,7 @@ def compute_recall_companies(dataset_test, y_pred, type_of_activity, model):
 
 def features_target_split(dataset_train, dataset_test):
     features_l = ['nb_tickets', 'nb_purchases', 'total_amount', 'nb_suppliers', 'vente_internet_max', 'purchase_date_min', 'purchase_date_max', 
-            'time_between_purchase', 'nb_tickets_internet', 'fidelity',  'is_email_true', 'opt_in', #'is_partner',
+            'time_between_purchase', 'nb_tickets_internet',  'is_email_true', 'opt_in', #'is_partner',
             'gender_female', 'gender_male', 'gender_other', 'nb_campaigns', 'nb_campaigns_opened']
     X_train = dataset_train[features_l]
     y_train = dataset_train[['y_has_purchased']]

utils_segmentation.py

@@ -18,3 +18,10 @@ def load_model(type_of_activity, model):
     model = pickle.loads(model_bytes)
     return model
 
+
+def load_test_file(type_of_activity):
+    file_path_test = f"projet-bdc2324-team1/Generalization/{type_of_activity}/Test_set.csv"
+    with fs.open(file_path_test, mode="rb") as file_in:
+        dataset_test = pd.read_csv(file_in, sep=",")
+    return dataset_test
+