V2

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, roc_curve, roc_auc_score
import streamlit as st

def process_and_evaluate(df):
    # 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)
    y_prob = clf.predict_proba(X_test)[:, 1]  # Get probabilities for ROC

    # Compute the confusion matrix and classification report
    conf_matrix = confusion_matrix(y_test, y_pred)
    classification_rep = classification_report(y_test, y_pred)

    # Calculate and plot the correlation matrix
    correlation_matrix = df.corr()
    plt.figure(figsize=(10, 8))
    sns.heatmap(correlation_matrix, annot=True, fmt=".2f", cmap='coolwarm')
    plt.title('相依矩陣')
    plt.savefig('correlation_matrix.png')  # Save the plot as an image
    plt.close()  # Close the plot to free memory

    # Compute ROC curve and AUC
    fpr, tpr, thresholds = roc_curve(y_test, y_prob)
    roc_auc = roc_auc_score(y_test, y_prob)

    # Plot ROC curve
    plt.figure(figsize=(10, 6))
    plt.plot(fpr, tpr, color='blue', label='ROC 曲線 (AUC = {:.2f})'.format(roc_auc))
    plt.plot([0, 1], [0, 1], color='red', linestyle='--')
    plt.xlim([0.0, 1.0])
    plt.ylim([0.0, 1.05])
    plt.xlabel('假陽性率')
    plt.ylabel('真正率')
    plt.title('Receiver Operating Characteristic (ROC) 曲線')
    plt.legend(loc='lower right')
    plt.savefig('roc_curve.png')  # Save the ROC curve as an image
    plt.close()  # Close the plot to free memory

    return classification_rep, conf_matrix, 'correlation_matrix.png', 'roc_curve.png'

# Create the Streamlit app
st.set_page_config(page_title="心臟病預測系統", layout="wide")

st.title("心臟病預測系統")
st.markdown("<h5 style='text-align: center;'>上傳包含心臟病數據的 CSV 文件以獲取分類報告、相依矩陣和 ROC 曲線。</h5>", unsafe_allow_html=True)

uploaded_file = st.file_uploader("上傳 CSV 文件", type="csv")

if uploaded_file is not None:
    # Load the dataset directly from the uploaded file
    df = pd.read_csv(uploaded_file)

    # Process the data and generate reports
    classification_report, conf_matrix, correlation_matrix_path, roc_curve_path = process_and_evaluate(df)

    st.subheader("分類報告")
    st.text_area("分類報告", classification_report, height=400)

    st.subheader("混淆矩陣")
    # Plot and display the confusion matrix
    plt.figure(figsize=(8, 6))
    sns.heatmap(conf_matrix, annot=True, fmt='d', cmap='Blues', xticklabels=['Negative', 'Positive'], yticklabels=['Negative', 'Positive'])
    plt.ylabel('實際值')
    plt.xlabel('預測值')
    plt.title('混淆矩陣')
    plt.savefig('confusion_matrix.png')  # Save the confusion matrix as an image
    plt.close()  # Close the plot to free memory
    st.image('confusion_matrix.png')

    st.subheader("相依矩陣")
    st.image(correlation_matrix_path)

    st.subheader("ROC 曲