Update app.py

app.py

@@ -4,13 +4,12 @@ import numpy as np
 import matplotlib.pyplot as plt
 import seaborn as sns
 from sklearn.model_selection import train_test_split
-from sklearn.preprocessing import StandardScaler
+from sklearn.preprocessing import StandardScaler, LabelEncoder
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.ensemble import RandomForestClassifier
 from xgboost import XGBClassifier
 from sklearn.inspection import permutation_importance
 from sklearn.feature_selection import mutual_info_classif
-from sklearn.preprocessing import LabelEncoder
 import io
 import base64
 
@@ -65,39 +64,10 @@ 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')
 
-# File upload
+# File upload (this line defines `uploaded_file`)
 uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
 
 if uploaded_file is not None:
@@ -112,16 +82,13 @@ if uploaded_file is not None:
         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)
 
-        # Download correlation matrix as PNG
-        buf = io.BytesIO()
-        plt.savefig(buf, format='png')
-        buf.seek(0)
-        st.markdown(get_download_link(buf.getvalue(), "correlation_matrix.png", "Download Correlation Matrix as PNG"), unsafe_allow_html=True)
-
         # Feature Importance
         st.subheader('Feature Importance')
         importance_dict = calculate_feature_importance(X, y)
@@ -130,12 +97,5 @@ if uploaded_file is not None:
         importance_df = pd.DataFrame(importance_dict, index=X.columns)
         st.write(importance_df)
 
-        # Download feature importance as XLSX
-        excel_buffer = io.BytesIO()
-        with pd.ExcelWriter(excel_buffer, engine='xlsxwriter') as writer:
-            importance_df.to_excel(writer, sheet_name='Feature Importance')
-        excel_buffer.seek(0)
-        st.markdown(get_download_link(excel_buffer.getvalue(), "feature_importance.xlsx", "Download Feature Importance as XLSX"), unsafe_allow_html=True)
-
 else:
     st.write("Please upload a CSV file to begin the analysis.")