Update app.py

app.py

@@ -245,91 +245,4 @@ gradio_interface.launch(share=True)
 
 
 
-import numpy as np
-import shap
-import lime
-from lime import lime_tabular
-
-
-# SHAP Explanations
-explainer = shap.Explainer(xgb_model)
-shap_values = explainer(X_test)
-
-# Visualize SHAP values (e.g., summary plot)
-shap.summary_plot(shap_values, X_test)
-
-# LIME Explanations
-explainer = lime_tabular.LimeTabularExplainer(
-    training_data=np.array(X_train),
-    feature_names=X_train.columns,
-    class_names=['Not Fraud', 'Fraud'],
-    mode='classification'
-)
-
-# Explain a single prediction (e.g., the first instance in X_test)
-i = 0
-exp = explainer.explain_instance(
-    data_row=X_test.iloc[i],
-    predict_fn=xgb_model.predict_proba
-)
-
-# Visualize the LIME explanation
-exp.show_in_notebook(show_table=True)
-
-
-from tensorflow import keras
-from tensorflow.keras import layers
-
-# Define the model
-model = keras.Sequential([
-    layers.Dense(128, activation='relu', input_shape=(X_train.shape[1],)),
-    layers.Dense(64, activation='relu'),
-    layers.Dense(1, activation='sigmoid')
-])
-
-# Compile the model
-model.compile(optimizer='adam',
-              loss='binary_crossentropy',
-              metrics=['accuracy'])
-
-# Train the model
-model.fit(X_train, y_train, epochs=10, batch_size=32)
-
-# Evaluate the model
-loss, accuracy = model.evaluate(X_test, y_test)
-print('Test accuracy:', accuracy)
-
-# Make predictions
-y_pred_nn = (model.predict(X_test) > 0.5).astype("int32")
-
-# Analyze the results
-analyze_results(y_test, y_pred_nn)
-
-# Add NN to the Gradio Interface
-def predict_fraud_with_nn(*features):
-    # ... (Same as before, but get prediction from the NN model) ...
-    input_data = [features]
-    nn_pred = (model.predict(input_data) > 0.5).astype("int32")[0][0]
-    return (
-        "Fraud" if nn_pred == 1 else "Not Fraud",
-        "Fraud" if xgb_pred == 1 else "Not Fraud",
-        "Fraud" if rf_pred == 1 else "Not Fraud",
-        "Fraud" if gb_pred == 1 else "Not Fraud"
-    )
-
-# Update the Gradio interface with the new prediction function and output
-gradio_interface = gr.Interface(
-    fn=predict_fraud_with_nn,
-    inputs=[gr.Number(label=label) for label in input_labels],
-    outputs=[
-        gr.Textbox(label="Neural Network Prediction"),
-        gr.Textbox(label="XGBoost Prediction"),
-        gr.Textbox(label="Random Forest Prediction"),
-        gr.Textbox(label="Gradient Boosting Prediction")
-    ],
-    title="Credit Card Fraud Detection with XGBoost, Random Forest, Gradient Boosting, and NN",
-    description="Enter transaction details to get predictions from four different models."
-)
 
-# Launch the Gradio app
-#gradio_interface.launch(share=True)