Create app.py

app.py

@@ -0,0 +1,80 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.ensemble import RandomForestClassifier
+from xgboost import XGBClassifier
+from sklearn.tree import DecisionTreeClassifier
+from sklearn.model_selection import train_test_split
+import numpy as np
+
+# Function to process data and return feature importances
+def calculate_importances(file):
+    # Read uploaded file
+    heart_df = pd.read_csv(file)
+    
+    # Set X and y
+    X = heart_df.drop('target', axis=1)
+    y = heart_df['target']
+    
+    # Split the data
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.25, random_state=42)
+    
+    # Initialize models
+    rf_model = RandomForestClassifier(random_state=42)
+    xgb_model = XGBClassifier(use_label_encoder=False, eval_metric='logloss', random_state=42)
+    cart_model = DecisionTreeClassifier(random_state=42)
+    
+    # Train models
+    rf_model.fit(X_train, y_train)
+    xgb_model.fit(X_train, y_train)
+    cart_model.fit(X_train, y_train)
+    
+    # Get feature importances
+    rf_importances = rf_model.feature_importances_
+    xgb_importances = xgb_model.feature_importances_
+    cart_importances = cart_model.feature_importances_
+    
+    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')
+    
+    # Save to Excel
+    file_name = 'feature_importances.xlsx'
+    importance_df.to_excel(file_name, index=False)
+    
+    return file_name, importance_df.head()
+
+# Streamlit interface
+st.title("Feature Importance Calculation")
+
+# File upload
+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, preview_df = calculate_importances(uploaded_file)
+    
+    # Display a preview of the DataFrame
+    st.write("Feature Importances (Preview):")
+    st.dataframe(preview_df)
+    
+    # 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"
+        )