Update app.py

app.py

@@ -1,6 +1,6 @@
 import streamlit as st
 import pandas as pd
-import matplotlib.pyplot as plt
+import plotly.express as px
 import seaborn as sns
 from sklearn.ensemble import RandomForestClassifier
 from xgboost import XGBClassifier
@@ -38,26 +38,14 @@ def calculate_importances(file):
     feature_names = X.columns
     
     # Prepare DataFrame
-    rf_importance = {'Feature': feature_names, 'Random Forest': rf_importances}
-    xgb_importance = {'Feature': feature_names, 'XGBoost': xgb_importances}
-    cart_importance = {'Feature': feature_names, 'CART': cart_importances}
-    
-    # Create DataFrames
-    rf_df = pd.DataFrame(rf_importance)
-    xgb_df = pd.DataFrame(xgb_importance)
-    cart_df = pd.DataFrame(cart_importance)
-    
-    # Merge DataFrames
-    importance_df = rf_df.merge(xgb_df, on='Feature').merge(cart_df, on='Feature')
+    rf_importance = pd.DataFrame({'Feature': feature_names, 'Importance': rf_importances})
+    xgb_importance = pd.DataFrame({'Feature': feature_names, 'Importance': xgb_importances})
+    cart_importance = pd.DataFrame({'Feature': feature_names, 'Importance': cart_importances})
     
     # Correlation Matrix
     corr_matrix = heart_df.corr()
     
-    # Save to Excel
-    file_name = 'feature_importances.xlsx'
-    importance_df.to_excel(file_name, index=False)
-    
-    return file_name, importance_df, corr_matrix, rf_importances, feature_names
+    return rf_importance, xgb_importance, cart_importance, corr_matrix
 
 # Streamlit interface
 st.title("Feature Importance Calculation")
@@ -67,30 +55,25 @@ uploaded_file = st.file_uploader("Upload heart.csv file", type=['csv'])
 
 if uploaded_file is not None:
     # Process the file and get results
-    excel_file, importance_df, corr_matrix, rf_importances, feature_names = calculate_importances(uploaded_file)
-    
-    # Display a preview of the DataFrame
-    st.write("Feature Importances (Preview):")
-    st.dataframe(importance_df.head())
+    rf_importance, xgb_importance, cart_importance, corr_matrix = calculate_importances(uploaded_file)
     
-    # Provide a link to download the Excel file
-    with open(excel_file, "rb") as file:
-        btn = st.download_button(
-            label="Download Excel File",
-            data=file,
-            file_name=excel_file,
-            mime="application/vnd.ms-excel"
-        )
-
-    # Plot and display the Correlation Matrix
+    # Display the correlation matrix as a heatmap (static for now)
     st.write("Correlation Matrix:")
     plt.figure(figsize=(10, 8))
     sns.heatmap(corr_matrix, annot=True, fmt=".2f", cmap="coolwarm", cbar=True)
     st.pyplot(plt)
     
-    # Plot and display the Feature Importance (Random Forest)
+    # Plot and display Random Forest Feature Importances with Plotly
     st.write("Random Forest Feature Importance:")
-    fig, ax = plt.subplots()
-    sns.barplot(x=rf_importances, y=feature_names, ax=ax)
-    ax.set_title('Random Forest Feature Importances')
-    st.pyplot(fig)
+    fig_rf = px.bar(rf_importance, x='Importance', y='Feature', orientation='h', title="Random Forest Feature Importances")
+    st.plotly_chart(fig_rf)
+    
+    # Plot and display XGBoost Feature Importances with Plotly
+    st.write("XGBoost Feature Importance:")
+    fig_xgb = px.bar(xgb_importance, x='Importance', y='Feature', orientation='h', title="XGBoost Feature Importances")
+    st.plotly_chart(fig_xgb)
+    
+    # Plot and display CART (Decision Tree) Feature Importances with Plotly
+    st.write("CART (Decision Tree) Feature Importance:")
+    fig_cart = px.bar(cart_importance, x='Importance', y='Feature', orientation='h', title="CART (Decision Tree) Feature Importances")
+    st.plotly_chart(fig_cart)