Update app.py

app.py

@@ -409,6 +409,27 @@ def validate_model(model_path, df, target, features, test_size):
         st.error(f"Validation failed: {str(e)}")
         return None, None
 
+# Prediction helper Function
+def prediction_input_form(features, default_values=None):
+    """Generates input forms for each feature and returns a dictionary of inputs.
+
+    Args:
+        features (list): List of feature names.
+        default_values (dict, optional): Default values for each feature. Defaults to None.
+
+    Returns:
+        dict: Dictionary where keys are feature names and values are user inputs.
+    """
+    input_data = {}
+    for feature in features:
+        if default_values and feature in default_values:
+            default_value = default_values[feature]
+        else:
+            default_value = 0.0  # Provide a reasonable default
+
+        input_data[feature] = st.number_input(f"{feature}:", value=default_value)
+    return input_data
+
 # --------------------------
 # Sidebar Navigation
 # --------------------------
@@ -1039,40 +1060,106 @@ elif app_mode == "Model Training":
                     st.metric("R2", f"{validation_metrics['r2']:.2f}")
 
 elif app_mode == "Predictions":
-    st.title("🔮 Predictive Analytics")
-    
-    if st.session_state.model is None:
+    st.title("🔮 Predictive Analytics - Informed Business Decisions")
+
+    if st.session_state.get("model") is None:
         st.warning("Please train a model first")
         st.stop()
-    
-    model = st.session_state.model
-    
-    # Prediction Interface
-    col1, col2 = st.columns(2)
+
+    model_data = st.session_state.model  # Get the entire dictionary
+    model = model_data['model']  # Access model
+    scaler = model_data['scaler']
+    column_order = model_data['column_order']
+    imputer_numerical = model_data['imputer_numerical']
+    features = model_data['features']
+    problem_type = model_data['problem_type']
+
+    enhance_section_title("Input Parameters", "📝")
+
+    # Generate Input Forms
+    col1, col2 = st.columns([2, 1])
+
     with col1:
-        st.subheader("Input Parameters")
-        input_data = {}
-        for feature in model.feature_names_in_:
-            input_data[feature] = st.number_input(feature)
-    
+        input_data = prediction_input_form(features)
+
     with col2:
-        st.subheader("Prediction Result")
-        if st.button("Generate Prediction"):
-            try:
-                input_df = pd.DataFrame([input_data])
-                prediction = model.predict(input_df)[0]
-                st.metric("Predicted Value", prediction)
-                
-                # SHAP Explanation
+        st.subheader("Data Overview")
+        input_df = pd.DataFrame([input_data]) #Make DataFrame
+        st.dataframe(input_df,use_container_width=True) #DataFrame of the input to see it
+
+    # Predicts Function and Displays Result
+    if st.button("Generate Prediction & Insights"):
+        try:
+            # 1. Create DataFrame from input
+            input_df = pd.DataFrame([input_data])
+
+            # 2. Impute missing values
+            numerical_features = input_df.select_dtypes(include=np.number).columns
+            input_df[numerical_features] = imputer_numerical.transform(input_df[numerical_features])
+
+            # 3. One-hot encode (handle unseen categories)
+            categorical_features = input_df.select_dtypes(exclude=np.number).columns
+            input_df = pd.get_dummies(input_df, columns=categorical_features, dummy_na=False) # dummy_na = False.  We imputed already.
+
+            # 4. Ensure correct column order
+            # Add missing columns with 0 values
+            for col in column_order:
+                if col not in input_df.columns:
+                    input_df[col] = 0
+            # Reorder Columns
+            input_df = input_df[column_order]
+
+            # 5. Scale the input
+            scaled_input = scaler.transform(input_df)
+
+            # 6. Make prediction
+            prediction = model.predict(scaled_input)[0]
+
+            # 7. Display Prediction
+            enhance_section_title("Prediction Results", "📈")
+            st.subheader("Model Prediction:")
+
+            if problem_type == "Classification":
+                st.metric("Predicted Class", str(prediction))
+            else:
+                st.metric("Predicted Value", f"{prediction:.2f}")
+
+            # 8. Feature Explanation (SHAP)
+            enhance_section_title("Insights", "💡")
+
+            if problem_type == "Classification":
                 explainer = shap.TreeExplainer(model)
-                shap_values = explainer.shap_values(input_df)
-                fig = shap.force_plot(
-                    explainer.expected_value[0], 
-                    shap_values[0], 
-                    input_df.iloc[0], 
-                    matplotlib=False
-                )
-                st.components.v1.html(shap.getjs() + fig.html(), height=300)
-            
+                shap_values = explainer.shap_values(scaled_input)  # Use the scaled input
+                # class_names = [str(i) for i in range(len(shap_values))]  # Dynamic class names - not needed for force plot
+
+                fig = shap.force_plot(explainer.expected_value[1], shap_values[1], input_df, matplotlib=False,link="logit") # shap_values[1] for class 1 - force plot
+                st.components.v1.html(shap.getjs() + fig.html(), height=400, width=900) # Adjust height and width as needed.
+
+            else:
+                explainer = shap.TreeExplainer(model)  # Regression
+                shap_values = explainer.shap_values(scaled_input)  # Use the scaled input
+
+                fig = shap.force_plot(explainer.expected_value, shap_values, input_df, matplotlib=False) # shap_values single array for regression
+                st.components.v1.html(shap.getjs() + fig.html(), height=400, width=900) # Adjust height and width as needed.
+
+            st.write("The visualization above explains how each feature contributed to the final prediction.")
+
+            # 9. Add Permutation Feature Importance (for more global understanding)
+            try:
+                enhance_section_title("Global Feature Importance", "🌍")
+                X = pd.DataFrame(scaler.transform(pd.get_dummies(pd.DataFrame(imputer_numerical.transform(input_df), columns=input_df.columns))), columns=input_df.columns) # Apply preprocessing for permutation
+                #X = pd.DataFrame(scaler.transform(input_df), columns = input_df.columns)
+                #X = input_df[input_df.columns]
+                X_train = model_data['X_train'] #Get X train
+                y_train = model_data['y_train'] #Get Y train
+                result = permutation_importance(model, X, input_df, n_repeats=10, random_state=42)
+                importance = result.importances_mean
+
+                fig_importance = px.bar(x=importance, y=features, orientation='h', title="Permutation Feature Importance")
+                st.plotly_chart(fig_importance)
+
             except Exception as e:
-                st.error(f"Prediction failed: {str(e)}")
+                st.warning(f"Could not calculate permutation feature importance: {e}")
+
+        except Exception as e:
+            st.error(f"Prediction failed: {str(e)}")