Update app.py

app.py

@@ -10,10 +10,8 @@ import joblib
 import numpy as np
 import gradio as gr
 
-# Load the XGBoost model
+# Load Model and Scaler:
 xgboost_model = joblib.load('xgboost_model_new.pkl')
-
-# Load the StandardScaler
 scaler = joblib.load('scaler.pkl')
 
 month_to_number = {
@@ -58,7 +56,7 @@ options = [
     'Travel',
     'Entertainment'
 ]
-# Define category options
+
 category_options = [
     'Food/Dining',
     'Gas/Transport',
@@ -76,28 +74,18 @@ category_options = [
 ]
 
 def predict_credit_card_fraud(amount, city_pop, month, hour, age, gender, category):
-    # Map the input month name to its corresponding number
-    month = month_to_number[month]
 
+    month = month_to_number[month]
     time_of_day = time_of_dayy(hour)
-
-    # Prepare input data with dummy variables for category
     input_data = np.array([[amount, city_pop, month, hour, age, int(gender == 'M'),
                             int(time_of_day == 'Night'), int(time_of_day == 'Evening'), int(time_of_day == 'Morning')] +
                            [int(category == cat) for cat in category_options]])
 
-    # Scale the input data using the loaded StandardScaler
     input_data[:, 0:2] = scaler.transform(input_data[:, 0:2])
-
-    # Use predict_proba to get probability scores for class 1
     probability = xgboost_model.predict_proba(input_data)[:, 1]
-
-    # Make predictions using the XGBoost model
     prediction = xgboost_model.predict(input_data)
 
     label = "Fraudulent" if prediction[0] == 1 else "Non-Fraudulent"
-
-    # Return the probability score
     return round(probability[0], 2), label
 
 gender_options = ["M", "F"]