Update app.py

app.py

@@ -50,54 +50,65 @@ def get_pred():
         "bmi": bmi
     }
 
-    # Prediction button
+
     if st.button("Predict"):
         # Convert input data to a DataFrame
         X = pd.DataFrame([data])
 
-        # Encode categorical features
+
         encoded_features = encoder.transform(X[categorical_features])
 
-        # Get the feature names from the encoder
+
         feature_names = encoder.get_feature_names_out(input_features=categorical_features)
 
-        # Create a DataFrame with the encoded features and feature names
+
         encoded_df = pd.DataFrame(encoded_features, columns=feature_names)
         X_encoded = pd.concat([X.drop(columns=categorical_features), encoded_df], axis=1)
 
-        # Make predictions
+
         prediction_proba = lgb1.predict_proba(X_encoded)
 
-        # Get SHAP values
+
         explainer = shap.TreeExplainer(lgb1)
         shap_values = explainer.shap_values(X_encoded)
 
-        # Extract prediction probability and display it to the user
+
         probability = prediction_proba[0, 1]  # Assuming binary classification
         st.subheader(f"The predicted probability of stroke is {probability}.")
         st.subheader("IF you see result , higher than 0.3, we advice you to see a doctor")
         st.header("Shap forceplot")
         st.subheader("Features values impact on model made prediction")
 
-        # Display SHAP force plot using Matplotlib
+
         shap.force_plot(explainer.expected_value[1], shap_values[1], features=X_encoded.iloc[0, :], matplotlib=True)
 
-        # Save the figure to a BytesIO buffer
+
         buf = io.BytesIO()
         plt.savefig(buf, format="png", dpi=800)
         buf.seek(0)
 
-        # Display the image in Streamlit
+
         st.image(buf, width=1100)
 
-        # Display summary plot of feature importance
+
         shap.summary_plot(shap_values[1], X_encoded)
 
-        # Display interaction summary plot
+
         shap_interaction_values = explainer.shap_interaction_values(X_encoded)
         shap.summary_plot(shap_interaction_values, X_encoded)
 
-# Execute get_pred() only if the option is "Stroke prediction"
+
+if option == "Information about training data":
+    st.header("Stroke Prediction Dataset")
+    st.subheader("According to the World Health Organization (WHO) stroke is the 2nd leading cause of death globally, responsible for approximately 11% of total deaths. This dataset is used to predict whether a patient is likely to get stroke based on the input parameters like gender, age, various diseases, and smoking status. Each row in the data provides relavant information about the patient.")
+    st.subheader(" Stroke dataset has 5110 records and 12 features.")
+    st.subheader(" Correlation between features:.")
+    st.image(r'lgbm_tree.png')
+    st.subheader("Features Shap values and how it effects Target variable "Stroke")
+    st.image(r'lgbm_tree.png')
+    
+
+    
 if option == "Stroke prediction":
     get_pred()
 
@@ -105,6 +116,9 @@ if option == "Model information":
     st.header("Light gradient boosting model")
     st.subheader("First tree of light gradient boosting model and how it makes decisions")
     st.image(r'lgbm_tree.png')
+    
+
+
 
     st.subheader("Shap values visualization of how features contribute to model prediction")
     st.image(r'lgbm_model_shap_evaluation.png')