Create app.py

app.py

@@ -0,0 +1,71 @@
+import pandas as pd
+import seaborn as sns
+import matplotlib.pyplot as plt
+from sklearn.preprocessing import LabelEncoder
+from sklearn.model_selection import train_test_split
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import confusion_matrix, classification_report
+import streamlit as st
+
+def process_and_evaluate(file):
+    # Load the dataset
+    df = pd.read_csv(file)
+
+    # Encode categorical features
+    categorical_columns = df.select_dtypes(include=['object']).columns
+    label_encoders = {}
+    for col in categorical_columns:
+        le = LabelEncoder()
+        df[col] = le.fit_transform(df[col])
+        label_encoders[col] = le
+
+    # Define the target and features
+    target = 'target'  # Assuming the target column is named 'target'
+    X = df.drop(columns=[target])
+    y = df[target]
+
+    # Split the data into training and testing sets
+    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+    # Train a RandomForestClassifier
+    clf = RandomForestClassifier(random_state=42)
+    clf.fit(X_train, y_train)
+
+    # Predict on the test set
+    y_pred = clf.predict(X_test)
+
+    # Compute the confusion matrix
+    conf_matrix = confusion_matrix(y_test, y_pred)
+
+    # Generate the classification report
+    classification_rep = classification_report(y_test, y_pred)
+
+    return df, conf_matrix, classification_rep
+
+# Streamlit interface
+st.title("Heart Disease Prediction")
+st.write("Upload a CSV file containing heart disease data to get the classification report.")
+
+uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+
+if uploaded_file is not None:
+    df, conf_matrix, report = process_and_evaluate(uploaded_file)
+
+    # Display the classification report
+    st.subheader("Classification Report")
+    st.text(report)
+
+    # Plot the correlation matrix
+    st.subheader("Correlation Matrix")
+    corr_matrix = df.corr()
+    fig, ax = plt.subplots(figsize=(10, 8))
+    sns.heatmap(corr_matrix, annot=True, fmt=".2f", cmap="coolwarm", ax=ax)
+    st.pyplot(fig)
+
+    # Plot the confusion matrix
+    st.subheader("Confusion Matrix")
+    fig, ax = plt.subplots()
+    sns.heatmap(conf_matrix, annot=True, fmt="d", cmap="Blues", ax=ax)
+    ax.set_xlabel('Predicted')
+    ax.set_ylabel('Actual')
+    st.pyplot(fig)