Update app.py

app.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import pandas as pd
-import plotly.express as px
-import plotly.graph_objects as go
+import matplotlib.pyplot as plt
+import seaborn as sns
 from sklearn.ensemble import RandomForestClassifier
 from xgboost import XGBClassifier
 from sklearn.tree import DecisionTreeClassifier
@@ -38,14 +38,26 @@ def calculate_importances(file):
     feature_names = X.columns
     
     # Prepare DataFrame
-    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})
+    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')
     
     # Correlation Matrix
     corr_matrix = heart_df.corr()
     
-    return rf_importance, xgb_importance, cart_importance, corr_matrix
+    # 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, xgb_importances, cart_importances, feature_names
 
 # Streamlit interface
 st.title("Feature Importance Calculation")
@@ -55,24 +67,44 @@ uploaded_file = st.file_uploader("Upload heart.csv file", type=['csv'])
 
 if uploaded_file is not None:
     # Process the file and get results
-    rf_importance, xgb_importance, cart_importance, corr_matrix = calculate_importances(uploaded_file)
+    excel_file, importance_df, corr_matrix, rf_importances, xgb_importances, cart_importances, feature_names = calculate_importances(uploaded_file)
     
-    # Display the correlation matrix as an interactive heatmap with Plotly
+    # Display a preview of the DataFrame
+    st.write("Feature Importances (Preview):")
+    st.dataframe(importance_df.head())
+    
+    # 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
     st.write("Correlation Matrix:")
-    fig_corr = px.imshow(corr_matrix, text_auto=True, aspect="auto", title="Correlation Matrix", color_continuous_scale="coolwarm")
-    st.plotly_chart(fig_corr)
+    plt.figure(figsize=(10, 8))
+    sns.heatmap(corr_matrix, annot=True, fmt=".2f", cmap="coolwarm", cbar=True)
+    st.pyplot(plt)
     
-    # Plot and display Random Forest Feature Importances with Plotly
+    # Plot and display the Feature Importance (Random Forest)
     st.write("Random Forest Feature Importance:")
-    fig_rf = px.bar(rf_importance, x='Importance', y='Feature', orientation='h', title="Random Forest Feature Importances")
-    st.plotly_chart(fig_rf)
+    fig_rf, ax_rf = plt.subplots()
+    sns.barplot(x=rf_importances, y=feature_names, ax=ax_rf)
+    ax_rf.set_title('Random Forest Feature Importances')
+    st.pyplot(fig_rf)
     
-    # Plot and display XGBoost Feature Importances with Plotly
+    # Plot and display the Feature Importance (XGBoost)
     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)
+    fig_xgb, ax_xgb = plt.subplots()
+    sns.barplot(x=xgb_importances, y=feature_names, ax=ax_xgb)
+    ax_xgb.set_title('XGBoost Feature Importances')
+    st.pyplot(fig_xgb)
     
-    # Plot and display CART (Decision Tree) Feature Importances with Plotly
+    # Plot and display the Feature Importance (Decision Tree - CART)
     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)
+    fig_cart, ax_cart = plt.subplots()
+    sns.barplot(x=cart_importances, y=feature_names, ax=ax_cart)
+    ax_cart.set_title('CART (Decision Tree) Feature Importances')
+    st.pyplot(fig_cart)