Update app.py

app.py

@@ -945,19 +945,18 @@ elif app_mode == "EDA":
 elif app_mode == "Model Training":
     st.title("🤖 Intelligent Model Training")
 
-     # Universal check for all dependent pages
+    # Universal check for all dependent pages
     if 'cleaned_data' not in st.session_state:
         st.warning("No cleaned data found! Please either:")
-        
+
         col1, col2 = st.columns(2)
         with col1:
             if st.button("↩️ Go to Data Cleaning"):
                 st.session_state.app_mode = "Data Cleaning"
                 st.experimental_rerun()
-        
+
         with col2:
-            uploaded_clean = st.file_uploader("📤 Or upload clean data", 
-                                             type=["csv", "xlsx"])
+            uploaded_clean = st.file_uploader("📤 Or upload clean data", type=["csv", "xlsx"])
             if uploaded_clean:
                 try:
                     st.session_state.cleaned_data = pd.read_csv(uploaded_clean)
@@ -965,20 +964,20 @@ elif app_mode == "Model Training":
                     st.experimental_rerun()
                 except Exception as e:
                     st.error(f"Invalid file: {str(e)}")
-        
+
         st.stop()  # Halt execution until resolved
 
     # Only reaches here if cleaned_data exists
     df = st.session_state.cleaned_data.copy()
-    
+
     # Model Setup
     col1, col2, col3 = st.columns(3)
     with col1:
         target = st.selectbox("Select Target Variable", df.columns)
-        problem_type = st.selectbox("Problem Type", ["Classification", "Regression", "Multiclass"]) #Added Multiclass
+        problem_type = st.selectbox("Problem Type", ["Classification", "Regression", "Multiclass"])  # Added Multiclass
     with col2:
         available_features = df.columns.drop(target)
-        features = st.multiselect("Select Features", available_features, default=list(available_features)) # Select all as default
+        features = st.multiselect("Select Features", available_features, default=list(available_features))  # Select all as default
     with col3:
         test_size = st.slider("Test Size", 0.1, 0.5, 0.2)
 
@@ -988,25 +987,25 @@ elif app_mode == "Model Training":
     elif problem_type == "Classification":
         model_type = st.selectbox("Select Classification Model", ["Random Forest", "Gradient Boosting", "Neural Network"])
     elif problem_type == "Multiclass":
-        model_type = st.selectbox("Select Multiclass Model", ["Logistic Regression", "Support Vector Machine", "Random Forest"]) #Added SVM and Logistic Regression
+        model_type = st.selectbox("Select Multiclass Model", ["Logistic Regression", "Support Vector Machine", "Random Forest"])  # Added SVM and Logistic Regression
     else:
-        model_type = None #handle this
+        model_type = None  # handle this
 
     # Hyperparameter Configuration - Dynamic based on Model Type
     st.subheader("Hyperparameter Configuration")
     model_params = {}
 
-    if model_type == "Neural Network": #Add options for NN parameters
+    if model_type == "Neural Network":  # Add options for NN parameters
         hidden_layers = st.text_input("Hidden Layer Sizes (e.g., 50,50 for two layers of 50 neurons)", "50,50")
         activation = st.selectbox("Activation Function", ["relu", "tanh", "logistic"])
         alpha = st.number_input("L2 Regularization (Alpha)", value=0.0001)
 
-        #Process the hidden layers string to a tuple of ints
+        # Process the hidden layers string to a tuple of ints
         try:
             hidden_layer_sizes = tuple(map(int, hidden_layers.split(',')))
             model_params['hidden_layer_sizes'] = hidden_layer_sizes
         except ValueError:
-            st.error("Invalid format for Hidden Layer Sizes.  Use comma-separated integers (e.g., 50,50)")
+            st.error("Invalid format for Hidden Layer Sizes. Use comma-separated integers (e.g., 50,50)")
 
         model_params['activation'] = activation
         model_params['alpha'] = alpha
@@ -1019,6 +1018,7 @@ elif app_mode == "Model Training":
         model_params['n_estimators'] = n_estimators
         model_params['learning_rate'] = learning_rate
         model_params['max_depth'] = max_depth
+
     elif model_type == "Logistic Regression":
         c_value = st.number_input("C (Regularization)", value=1.0)
         model_params['C'] = c_value
@@ -1035,12 +1035,10 @@ elif app_mode == "Model Training":
         model_params['n_estimators'] = n_estimators
         model_params['max_depth'] = max_depth
 
-
-
     use_grid_search = st.checkbox("Use Grid Search for Hyperparameter Tuning")
 
     # In Model Training section - Fix indentation for training logic
-   if st.button("Train Model"):
+    if st.button("Train Model"):
         if not features:
             st.error("Please select at least one feature.")
             st.stop()
@@ -1051,52 +1049,49 @@ elif app_mode == "Model Training":
             df.copy(), target, features, problem_type, test_size, model_type, model_params, use_grid_search
         )
 
-    if model:  # Only proceed if training was successful
-        st.success("Model trained successfully!")
-
-        # Display Metrics
-        st.subheader("Model Evaluation Metrics")
-        if problem_type in ["Classification", "Multiclass"]:  # Combined here
-            st.metric("Accuracy", f"{metrics['accuracy']:.2%}")
-
-            # Confusion Matrix Visualization
-            st.subheader("Confusion Matrix")
-            cm = metrics['confusion_matrix']
-            class_names = [str(i) for i in np.unique(df[target])]  # Get original class names
-            fig_cm = px.imshow(cm,
-                               labels=dict(x="Predicted", y="Actual"),
-                               x=class_names,
-                               y=class_names,
-                               color_continuous_scale="Viridis")
-            st.plotly_chart(fig_cm, use_container_width=True)
-
-            # Classification Report
-            st.subheader("Classification Report")
-            report = metrics['classification_report']
-            report_df = pd.DataFrame(report).transpose()
-            st.dataframe(report_df)
+        if model:  # Only proceed if training was successful
+            st.success("Model trained successfully!")
+
+            # Display Metrics
+            st.subheader("Model Evaluation Metrics")
+            if problem_type in ["Classification", "Multiclass"]:  # Combined here
+                st.metric("Accuracy", f"{metrics['accuracy']:.2%}")
+
+                # Confusion Matrix Visualization
+                st.subheader("Confusion Matrix")
+                cm = metrics['confusion_matrix']
+                class_names = [str(i) for i in np.unique(df[target])]  # Get original class names
+                fig_cm = px.imshow(cm,
+                                   labels=dict(x="Predicted", y="Actual"),
+                                   x=class_names,
+                                   y=class_names,
+                                   color_continuous_scale="Viridis")
+                st.plotly_chart(fig_cm, use_container_width=True)
+
+                # Classification Report
+                st.subheader("Classification Report")
+                report = metrics['classification_report']
+                report_df = pd.DataFrame(report).transpose()
+                st.dataframe(report_df)
 
-        else:
-            st.metric("MSE", f"{metrics['mse']:.2f}")
-            st.metric("R2", f"{metrics['r2']:.2f}")
-
-        # A
-
-        # Additional model display code...
+            else:
+                st.metric("MSE", f"{metrics['mse']:.2f}")
+                st.metric("R2", f"{metrics['r2']:.2f}")
 
+            # Additional model display code...
 
             # Feature Importance
             st.subheader("Feature Importance")
             try:
                 fig_importance = px.bar(
                     x=importance,
-                    y=column_order, #Use stored column order
+                    y=column_order,  # Use stored column order
                     orientation='h',
                     title="Feature Importance"
                 )
                 st.plotly_chart(fig_importance, use_container_width=True)
             except Exception as e:
-                st.warning(f"Could not display feature importance: {e}")
+                st.warning((f"Could not display feature importance: {e}")
 
              # Explainable AI (Placeholder)
             st.subheader("Explainable AI (XAI)")