Update app.py

app.py

@@ -7,7 +7,7 @@ import altair as alt
 import plotly.express as px
 from sklearn.model_selection import train_test_split
 import joblib
-import shap as shap
+import shap
 from xgboost import XGBClassifier
 from sklearn.preprocessing import OneHotEncoder
 from streamlit_shap import st_shap
@@ -26,6 +26,8 @@ def load_model_and_encoder():
 
 xgb_model, ohe = load_model_and_encoder()
 
+# Create SHAP explainer
+explainer = shap.TreeExplainer(xgb_model)
 
 # Load the data
 data = load_data()
@@ -445,29 +447,58 @@ elif option == "Financial Recommender Engine":
         st.write("Click the 'Get Recommendations' button to receive personalized financial recommendations.")
 
 elif option == "SML Classification":
-    st.title("SML Classification - Financial Prediction")
+    st.title("SML Classification - Financial Product Prediction")
 
-    # Collect user inputs for prediction
-    st.markdown("### Provide the details to predict the financial product:")
+    # User inputs
     age = st.slider("Your Age", 18, 70, 30)
     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"])
-    
-    # Convert user inputs to a DataFrame
+    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 categorical features
     input_data = pd.DataFrame({
-        'Age': [age],
         '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]
+        '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 categorical features
-    input_data_encoded = ohe.transform(input_data)
+    input_data_encoded = pd.DataFrame(ohe.transform(input_data).todense(), columns=ohe.get_feature_names_out())
 
-    # Make prediction
+    # Prediction
     if st.button("Predict"):
-        prediction = xgb_model.predict(input_data_encoded)
-        st.write(f"Prediction: {prediction[0]}")
+        prediction = xgb_model.predict(input_data_encoded)[0]
+        st.write(f"Prediction: {prediction}")
+
+        # 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)
+
+        st.markdown("""
+        This plot shows how each feature contributes to the prediction:
+        - Blue bars push the prediction lower
+        - Red bars push the prediction higher
+        """)
+
+# Add other elif blocks for 'Description of Variables', 'Regional-Based Analysis', 'Income-Based Analysis', and 'Gender-Based Analysis'