Update app.py

app.py

@@ -8,18 +8,18 @@ from sklearn.linear_model import LogisticRegression
 from imblearn.over_sampling import SMOTE
 from transformers import pipeline
 import gradio as gr
-from google.colab import files
 
-# Load the creditcard.csv dataset from Google Drive or Colab local file upload
-uploaded = files.upload()  # This will prompt you to upload your file
-df = pd.read_csv('creditcard.csv')
+# Load the creditcard.csv dataset from your local directory
+file_path = 'creditcard.csv'  # Make sure this file is in the same directory as your script
+
+# Load the dataset
+df = pd.read_csv(file_path)
 
 # Display basic information
 print("Columns in the dataset:", df.columns)
 print(df.head())
 
 # Preprocessing: Selecting relevant columns
-# Assuming the dataset has 'Time', 'Amount', and 'Class' columns along with 'V1' to 'V28' features
 time_col = 'Time'
 amount_col = 'Amount'
 class_col = 'Class'
@@ -63,36 +63,24 @@ retrieval_pipeline = pipeline("feature-extraction", model="distilbert-base-uncas
 
 def retrieve_explanation(prediction):
     if prediction == 1:
-        explanation = "The transaction is classified as fraudulent based on the provided features."
-    else:
-        explanation = "The transaction is classified as non-fraudulent based on the provided features."
-    return explanation
+        return "The transaction is classified as fraudulent based on the provided features."
+    return "The transaction is classified as non-fraudulent based on the provided features."
 
-# Gradio prediction function with complete feature padding
+# Gradio prediction function
 def fraud_detection_predictor(V1, V2, V3, Amount):
-    # Create a list of features with default zero values for missing ones
+    # Prepare input features
     input_features = [0] * len(feature_cols)
-    
-    # Map the provided features to their indices (ensure they are in correct feature_cols)
-    v1_index = feature_cols.index('V1')  # Ensure these columns exist in feature_cols
-    v2_index = feature_cols.index('V2')
-    v3_index = feature_cols.index('V3')
-    amount_index = feature_cols.index('Amount')
-    
-    # Assign user inputs to the correct feature indices
-    input_features[v1_index] = V1
-    input_features[v2_index] = V2
-    input_features[v3_index] = V3
-    input_features[amount_index] = Amount
+    input_features[feature_cols.index('V1')] = V1
+    input_features[feature_cols.index('V2')] = V2
+    input_features[feature_cols.index('V3')] = V3
+    input_features[feature_cols.index('Amount')] = Amount
 
-    # Scale input data using the pre-fitted scaler
+    # Scale input data
     input_data = scaler.transform([input_features])
     
     # Make a prediction
     prediction = model.predict(input_data)[0]
     fraud_status = "Fraudulent" if prediction == 1 else "Non-Fraudulent"
-    
-    # Get explanation
     explanation = retrieve_explanation(prediction)
     return fraud_status, explanation
 
@@ -109,8 +97,8 @@ interface = gr.Interface(
         gr.Textbox(label="Fraud Status"),
         gr.Textbox(label="Explanation")
     ],
-    title="Simplified Credit Card Fraud Detection",
-    description="Enter a few transaction features (V1, V2, V3, Amount) to predict fraud status."
+    title="Credit Card Fraud Detection",
+    description="Enter transaction features (V1, V2, V3, Amount) to predict fraud status."
 )
 
 # Launch Gradio Interface