Update app.py

app.py

@@ -30,7 +30,7 @@ def plot_correlation_matrix(data):
 
 # Function to calculate feature importance
 def calculate_feature_importance(X, y):
-    # Convert non-sequential class labels to sequential integers
+    # Encode non-sequential class labels to sequential integers
     le = LabelEncoder()
     y_encoded = le.fit_transform(y)  # Transform y into continuous integers
 
@@ -65,6 +65,35 @@ def calculate_feature_importance(X, y):
 
     return importance_dict
 
+# Example of usage in the main script
+# After uploading the file and selecting the target column, run the analysis
+if uploaded_file is not None:
+    data = pd.read_csv(uploaded_file)
+    st.write("Data Preview:")
+    st.write(data.head())
+
+    # Select target variable
+    target_col = st.selectbox("Select the target variable", data.columns)
+
+    if st.button('Analyze'):
+        X = data.drop(target_col, axis=1)
+        y = data[target_col]
+
+        # Ensure that `y` has continuous integer values for classification
+        st.write("Original Target Values:", y.unique())  # Show original target values for debugging
+
+        # Correlation Matrix
+        st.subheader('Correlation Matrix')
+        plot_correlation_matrix(data)
+
+        # Feature Importance
+        st.subheader('Feature Importance')
+        importance_dict = calculate_feature_importance(X, y)
+
+        # Create a DataFrame with all feature importances
+        importance_df = pd.DataFrame(importance_dict, index=X.columns)
+        st.write(importance_df)
+
 # Streamlit app
 st.title('Heart Disease Feature Analysis')