XGBoost Heart Disease Prediction Function

This code defines a function that loads a heart disease dataset, trains and makes predictions using XGBoost, and calculates the accuracy of the predictions.

Technology Stack : The code uses the XGBoost library, scikit-learn's load_heart_disease dataset, train_test_split for data splitting, DMatrix for model training, XGBClassifier for model creation, and accuracy_score for accuracy calculation.

Code Type : The type of code

Code Difficulty :

                
                    
def predict_heart_disease(features):
    import xgboost as xgb
    from sklearn.datasets import load_heart_disease
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import accuracy_score

    # Load dataset
    data = load_heart_disease()
    X = data.data
    y = data.target

    # Split the dataset 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)

    # Create a DMatrix from the training data
    dtrain = xgb.DMatrix(X_train, label=y_train)

    # Create a XGBoost model
    model = xgb.XGBClassifier(use_label_encoder=False, eval_metric='mlogloss')

    # Train the model
    model.fit(dtrain, evals=[(dtrain, 'train')], eval_metric='mlogloss', verbose=True)

    # Predict using the trained model
    predictions = model.predict(xgb.DMatrix(X_test))

    # Calculate accuracy
    accuracy = accuracy_score(y_test, predictions)

    return accuracy