Create app.py

app.py

@@ -0,0 +1,105 @@
+import streamlit as st
+import pandas as pd
+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.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
+import io
+import base64
+
+# Function to create a download link
+def get_download_link(data, filename, text):
+    b64 = base64.b64encode(data).decode()
+    href = f'<a href="data:file/csv;base64,{b64}" download="{filename}">{text}</a>'
+    return href
+
+# Function to plot correlation matrix
+def plot_correlation_matrix(data):
+    plt.figure(figsize=(12, 10))
+    sns.heatmap(data.corr(), annot=True, cmap='coolwarm', linewidths=0.5)
+    plt.title('Correlation Matrix')
+    plt.tight_layout()
+    st.pyplot(plt)
+
+# Function to calculate feature importance
+def calculate_feature_importance(X, y):
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+    scaler = StandardScaler()
+    X_train_scaled = scaler.fit_transform(X_train)
+    X_test_scaled = scaler.transform(X_test)
+
+    methods = {
+        "Decision Tree": DecisionTreeClassifier(random_state=42),
+        "Random Forest": RandomForestClassifier(n_estimators=100, random_state=42),
+        "XGBoost": XGBClassifier(random_state=42)
+    }
+
+    importance_dict = {}
+
+    for name, model in methods.items():
+        model.fit(X_train_scaled, y_train)
+        importance_dict[name] = model.feature_importances_
+
+    # Permutation Importance
+    rf = RandomForestClassifier(n_estimators=100, random_state=42)
+    rf.fit(X_train_scaled, y_train)
+    perm_importance = permutation_importance(rf, X_test_scaled, y_test, n_repeats=10, random_state=42)
+    importance_dict["Permutation"] = perm_importance.importances_mean
+
+    # Mutual Information
+    mi_scores = mutual_info_classif(X_train_scaled, y_train)
+    importance_dict["Mutual Information"] = mi_scores
+
+    return importance_dict
+
+# Streamlit app
+st.title('Heart Disease Feature Analysis')
+
+# File upload
+uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+
+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]
+
+        # 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)
+
+        # Create a DataFrame with all feature importances
+        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.")