Update app.py

app.py

@@ -445,63 +445,76 @@ elif option == "Financial Recommender Engine":
             st.write(f"- {rec}")
     else:
         st.write("Click the 'Get Recommendations' button to receive personalized financial recommendations.")
+        
+elif option == "Income Bracket & SHAP Analysis":
+    st.markdown("<h2 style='text-align: center;'>Income Bracket & SHAP Analysis</h2>", unsafe_allow_html=True)
+
+    st.subheader('Enter your information')
+
+    # Categorical 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?')
+
+    # 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]  # No longer using income_value
+        })
+        
+        # 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']))
 
-elif option == "SML Classification":
-    st.title("SML Classification - Financial Product Prediction")
-
-    # Collect user inputs for prediction
-    st.markdown("### Provide the details to predict the financial product:")
-
-    # User inputs
-    income_bracket = st.selectbox("Income Bracket (1 = Lowest, 5 = Highest)", [1, 2, 3, 4, 5])
-    has_internet_access = st.radio("Do you have Internet Access?", ["Yes", "No"])
-    employed = st.radio("Are you employed?", ["Yes", "No"])
-    high_income_region = st.radio("Are you in a High Income Region?", ["Yes", "No"])
-    is_mobileowner = st.radio("Are you a Mobileowner?", ["Yes", "No"])
-    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", ["Teen", "Young Adult", "Adult", "Middle Age", "Older Adult", "Elder", "Senior"])
-
-    # Prepare input data to match the model's expected features
-    input_data = pd.DataFrame({
-        'Income Bracket': [income_bracket],
-        'Has Internet Access': [1 if has_internet_access == "Yes" else 0],
-        'Employed': [1 if employed == "Yes" else 0],
-        'High Income Region': [1 if high_income_region == "Yes" else 0],
-        'Is Mobileowner': [1 if is_mobileowner == "Yes" else 0],
-        'Place of living_Unknown': [1 if place_of_living == "Unknown" else 0],
-        'Place of living_Urban Area': [1 if place_of_living == "Urban Area" else 0],
-        'Place of living_Rural Area': [1 if place_of_living == "Rural Area" else 0],
-        'Education Level_Primary': [1 if education_level == "Primary" else 0],
-        'Education Level_Secondary': [1 if education_level == "Secondary" else 0],
-        'Education Level_Tertiary': [1 if education_level == "Tertiary" else 0],
-        'Age Group_Teen': [1 if age_group == "Teen" else 0],
-        'Age Group_Young Adult': [1 if age_group == "Young Adult" else 0],
-        'Age Group_Adult': [1 if age_group == "Adult" else 0],
-        'Age Group_Middle Age': [1 if age_group == "Middle Age" else 0],
-        'Age Group_Older Adult': [1 if age_group == "Older Adult" else 0],
-        'Age Group_Elder': [1 if age_group == "Elder" else 0],
-        'Age Group_Senior': [1 if age_group == "Senior" else 0]
-    })
-
-    # One-hot encode the input data
-    input_data_encoded = pd.DataFrame(ohe.transform(input_data).todense(), columns=ohe.get_feature_names_out())
-
-    # Prediction
-    if st.button("Predict"):
-        # Predict using the loaded model
-        prediction = xgb_model.predict(input_data_encoded)[0]
-        st.write(f"Prediction: {prediction}")
+        # 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
 
-        # SHAP explanation
-        st.subheader('Factors Influencing Prediction 🤖')
-        shap_values = explainer.shap_values(input_data_encoded)
-        st_shap(shap.force_plot(explainer.expected_value, shap_values, input_data_encoded), height=400, width=600)
+        # 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]
+
+        # Display prediction result
+        st.metric(label="Predicted Probability of Saving", value=f'{round(predicted_saved * 100, 2)}%')
+
+        # SHAP explanation
+        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 prediction:
-        - Blue bars push the prediction lower
-        - Red bars push the prediction higher
+        This plot shows how each feature contributes to the predicted likelihood of saving:
+        - Blue bars push the probability lower
+        - Red bars push the probability higher
         """)
 
-# Add other elif blocks for 'Description of Variables', 'Regional-Based Analysis', 'Income-Based Analysis', and 'Gender-Based Analysis'
+# Continue with other sections such as "Regional-Based Analysis", "Income-Based Analysis", etc.
+# ...