Update app.py

app.py

@@ -52,103 +52,4 @@ warnings.filterwarnings("ignore")
 # model with the filename 'model.joblib'
 subprocess.run(['python', 'train.py'])
 
-# Load the freshly trained model from disk
-model = joblib.load("model.joblib")
-
-# Define the predict function
-def predict(csv_filename):
-    # Read the CSV file
-    df = pd.read_csv(csv_filename, header=None)
-
-    # Convert the DataFrame to a list of floats
-    client_data = df.iloc[0].tolist()
-
-    # Check if the length of client_data is 29
-    if len(client_data) != 29:
-        raise ValueError("The CSV file must contain exactly 29 values.")
-
-    # Unpack the list of values
-    V1, V2, V3, V4, V5, V6, V7, V8, V9, V10, V11, V12, V13, V14, V15, V16, V17, V18, V19, V20, V21, V22, V23, V24, V25, V26, V27, V28, Amount = client_data
-
-    # Create the data dictionary
-    data = {
-        'V1': V1, 'V2': V2, 'V3': V3, 'V4': V4, 'V5': V5, 'V6': V6, 'V7': V7, 'V8': V8, 'V9': V9, 'V10': V10,
-        'V11': V11, 'V12': V12, 'V13': V13, 'V14': V14, 'V15': V15, 'V16': V16, 'V17': V17, 'V18': V18, 'V19': V19, 'V20': V20,
-        'V21': V21, 'V22': V22, 'V23': V23, 'V24': V24, 'V25': V25, 'V26': V26, 'V27': V27, 'V28': V28, 'Amount': Amount
-    }
-
-    # Convert the data dictionary to a DataFrame
-    input_df = pd.DataFrame([data])
-
-    # Make predictions using the loaded model
-    prediction = model.predict(input_df)
-
-    return prediction[0], Amount  # Return both the prediction and Amount
-
-# Define a function to map the names to their respective CSV filenames
-def get_csv_filename(name):
-    name_to_filename = {
-        'Ted': 'Ted.csv',
-        'Bill': 'Bill.csv',
-        'Jill': 'Jill.csv',
-        'Juan': 'Juan.csv'
-    }
-    return name_to_filename.get(name, 'Ted.csv')  # Default to 'Ted.csv' if name not found
-
-# Define the Gradio interface function for single prediction
-def gradio_predict(name):
-    csv_filename = get_csv_filename(name)
-    prediction, amount = predict(csv_filename)
-    return f"The flagged transaction amount is {amount} and the prediction is {prediction}"
-
-# Define the function for bulk analysis
-def bulk_analysis(file):
-    # Read the uploaded CSV file
-    df = pd.read_csv(file.name)
-
-    # Assuming the last column is 'Amount' and the rest are features
-    X_test = df.iloc[:, :-1]
-    y_test = df.iloc[:, -1]
-
-    # Make predictions using the loaded model
-    y_test_pred = model.predict(X_test)
-
-    # Debugging: Print counts of anomalies in actual and predicted
-    actual_anomalies = sum(y_test == 1)
-    predicted_anomalies = sum(y_test_pred == 1)
-    print(f"Actual anomalies: {actual_anomalies}, Predicted anomalies: {predicted_anomalies}")
-
-    # Find rows where actual and predicted are both 1
-    correctly_predicted_anomalies = X_test[(y_test == 1) & (y_test_pred == 1)]
-    print(f"Correctly predicted anomalies: {len(correctly_predicted_anomalies)}")
-
-    # Save the results to a CSV file
-    result_filename = "correct_anomalies.csv"
-    correctly_predicted_anomalies.to_csv(result_filename, index=False)
-
-    return result_filename  # Return the path to the saved file
-
-
-# Create the Gradio interface
-iface = gr.Interface(
-    fn=gradio_predict,
-    inputs=gr.Dropdown(choices=['Ted', 'Bill', 'Jill', 'Juan'], label="Select a name"),
-    outputs="text"
-)
-
-# Add the bulk analysis upload interface
-bulk_iface = gr.Interface(
-    fn=bulk_analysis,
-    inputs=gr.File(label="Bulk Analysis"),
-    outputs=gr.File(label="Download Results")
-)
-
-# Combine the interfaces
-combined_iface = gr.TabbedInterface(
-    [iface, bulk_iface],
-    tab_names=["Single Prediction", "Bulk Analysis"]
-)
-
-# Launch the interface
-combined_iface.launch(share=True)