Update app.py

app.py

@@ -446,61 +446,45 @@ elif option == "Financial Recommender Engine":
     else:
         st.write("Click the 'Get Recommendations' button to receive personalized financial recommendations.")
 
-elif option == "SML Classification":  # This is the section you want to display content on
+elif option == "SML Classification":
     st.markdown("<h2 style='text-align: center;'>SML Classification</h2>", unsafe_allow_html=True)
-    
-    st.write("This section allows you to predict savings behavior based on multiple variables.")
-    
-    st.subheader('Enter your information')
 
-    # Categorical Inputs
+    # Collect user inputs
     place_of_living = st.selectbox('Place of Living', ['Urban Area', 'Rural Area', 'Unknown'])
     education_level = st.selectbox('Education Level', ['Primary', 'Secondary', 'Tertiary'])
     age_group = st.selectbox('Age Group', ['Adult', 'Middle Age', 'Older Adult', 'Senior', 'Teen', 'Young Adult'])
     income_bracket = st.selectbox('Income Bracket', [1, 2, 3, 4, 5])
-
-    # Binary Inputs
     female = st.radio('Gender', ['Female', 'Male'])
     is_mobileowner = st.checkbox('Is Mobile Owner?')
     has_internet_access = st.checkbox('Has Internet Access?')
     employed = st.checkbox('Employed?')
     high_income_region = st.checkbox('High Income Region?')
 
+    # Prepare categorical and numerical features
+    cat_features = pd.DataFrame({
+        'Place of living': [place_of_living],
+        'Education Level': [education_level],
+        'Age Group': [age_group]
+    })
+
+    num_features = pd.DataFrame({
+        'Female': [1 if female == 'Female' else 0],
+        'Is Mobileowner': [1 if is_mobileowner else 0],
+        'Has Internet Access': [1 if has_internet_access else 0],
+        'Employed': [1 if employed else 0],
+        'High Income Region': [1 if high_income_region else 0],
+        'Income Bracket': [income_bracket]  # Directly use Income Bracket as numerical
+    })
+
+    # OneHotEncode only the categorical variables
+    cat_encoded = pd.DataFrame(ohe.transform(cat_features).todense(),
+                               columns=ohe.get_feature_names_out(['Place of living', 'Education Level', 'Age Group']))
+
+    # Combine categorical and numerical features
+    features = pd.concat([num_features, cat_encoded], axis=1)
+
     # Prediction button
     if st.button('Predict Saving Behavior'):
-        # Prepare categorical features
-        cat_features = pd.DataFrame({
-            'Place of living': [place_of_living],
-            'Education Level': [education_level],
-            'Age Group': [age_group],
-            'Income Bracket': [income_bracket]
-        })
-        
-        # Transform categorical features using the loaded OneHotEncoder
-        cat_encoded = pd.DataFrame(ohe.transform(cat_features).todense(), 
-                                columns=ohe.get_feature_names_out(['Place of living', 'Education Level', 'Age Group', 'Income Bracket']))
-
-        # Ensure all expected columns are present
-        expected_columns = ohe.get_feature_names_out(['Place of living', 'Education Level', 'Age Group', 'Income Bracket'])
-        for col in expected_columns:
-            if col not in cat_encoded.columns:
-                cat_encoded[col] = 0  # Add missing columns with a default value of 0
-
-        # Reorder columns to match the expected order
-        cat_encoded = cat_encoded[expected_columns]
-
-        # Prepare binary and numerical features
-        num_features = pd.DataFrame({
-            'Female': [1 if female == 'Female' else 0],
-            'Is Mobileowner': [1 if is_mobileowner else 0],
-            'Has Internet Access': [1 if has_internet_access else 0],
-            'Employed': [1 if employed else 0],
-            'High Income Region': [1 if high_income_region else 0]
-        })
-
-        # Combine categorical and numerical features
-        features = pd.concat([num_features, cat_encoded], axis=1)
-
         # Make the prediction
         predicted_saved = xgb_model.predict(features)[0]
 
@@ -511,7 +495,7 @@ elif option == "SML Classification":  # This is the section you want to display
         st.subheader('Feature Contributions 🤖')
         shap_values = explainer.shap_values(features)
         st_shap(shap.force_plot(explainer.expected_value, shap_values, features), height=400, width=600)
-        
+
         st.markdown("""
         This plot shows how each feature contributes to the predicted likelihood of saving:
         - Blue bars push the probability lower