Update app.py

app.py

@@ -19,14 +19,15 @@ with open("pca_model.pkl", "rb") as file:
 # Dummy data for generating choices
 df = pd.read_csv('synthetic_financial_data.csv')
 
-# Function to group ages
+# Let's create new column from age column
 def group(x):
-    if x < 33:
-        return '18-32'
-    elif x < 60:
-        return '33-60'
-    else:
-        return '60+'
+  if x < 33:
+    a = '18-32'
+  elif x < 60:
+    a = '33-60'
+  elif x >= 60:
+    a = '60+'
+  return a
 
 # Choices for dropdown menus
 card_type_choices = [(val, val) for val in df['card_type'].unique()]
@@ -49,11 +50,7 @@ def predict(transaction_id, customer_id, merchant_id, amount, transaction_time,
         data['Age_group'] = data['customer_age'].apply(lambda x: group(x))
         data = pd.get_dummies(data, columns=['Age_group'], drop_first=True, dtype=float)
 
-        # Define all possible feature columns used during training
-        columns_to_add = ['customer_age', 
-                          'card_type_American Express', 'card_type_Discover', 'card_type_MasterCard', 'card_type_Visa',
-                          'purchase_category_Gas Station', 'purchase_category_Groceries', 'purchase_category_Online Shopping', 'purchase_category_Restaurant', 'purchase_category_Retail', 'purchase_category_Travel',
-                          'Age_group_33-60', 'Age_group_60+']
+        columns_to_add = ['customer_age','card_type_MasterCard','purchase_category_Online Shopping' ,'card_type_Discover', 'card_type_Visa', 'purchase_category_Groceries', 'purchase_category_Restaurant','purchase_category_Retail', 'purchase_category_Travel', 'Age_group_33-60', 'Age_group_60+']
 
         # Add missing columns with default value of 0
         for column in columns_to_add:
@@ -61,31 +58,27 @@ def predict(transaction_id, customer_id, merchant_id, amount, transaction_time,
                 data[column] = 0
 
         for i in data.columns:
-            data[i] = data[i].astype(int)
+          data[i] = data[i].astype(int)
 
         # Perform PCA
         X_pca = pca.transform(data[['purchase_category_Groceries', 'purchase_category_Retail', 'purchase_category_Travel', 'Age_group_33-60', 'Age_group_60+']])
         data['pca1'] = X_pca[:, 0]
         data['pca2'] = X_pca[:, 1]
-    
-        data.drop(columns=['customer_age'], inplace=True)  # Remove 'customer_age' as it's already included in Age_group
 
+        data.drop(columns=['customer_age', 'card_type_Discover', 'card_type_Visa', 'purchase_category_Groceries', 'purchase_category_Retail', 'purchase_category_Travel', 'Age_group_33-60', 'Age_group_60+'], inplace=True)
         # Make predictions
         prediction = clf.predict(data)
-        result = "Fraudulent" if prediction[0] == 1 else "Not Fraudulent"
-        # Custom output for specific IDs
-        return f'Customer with ID {customer_id} and Transaction ID {transaction_id}, which happened at {transaction_time}, is {result}'
+        return "Fraudulent" if prediction[0] == 1 else "Not Fraudulent"
     except Exception as e:
         return str(e)
 
-
 # Define Gradio interface
 inputs = [
     gr.Textbox(label="Transaction ID"),
     gr.Textbox(label="Customer ID"),
     gr.Textbox(label="Merchant ID"),
     gr.Number(label="Amount"),
-    gr.Textbox(label="Transaction Date (YYYY-MM-DD)"), 
+    gr.Textbox(label="Transaction Time"),
     gr.Dropdown(choices=card_type_choices, label="Card Type"),  
     gr.Dropdown(choices=location_choices, label="Location"),
     gr.Dropdown(choices=purchase_category_choices, label="Purchase Category"),