plot_model_complexity_influence.py 文件源码

def generate_data(case, sparse=False):
    """Generate regression/classification data."""
    bunch = None
    if case == 'regression':
        bunch = datasets.load_boston()
    elif case == 'classification':
        bunch = datasets.fetch_20newsgroups_vectorized(subset='all')
    X, y = shuffle(bunch.data, bunch.target)
    offset = int(X.shape[0] * 0.8)
    X_train, y_train = X[:offset], y[:offset]
    X_test, y_test = X[offset:], y[offset:]
    if sparse:
        X_train = csr_matrix(X_train)
        X_test = csr_matrix(X_test)
    else:
        X_train = np.array(X_train)
        X_test = np.array(X_test)
    y_test = np.array(y_test)
    y_train = np.array(y_train)
    data = {'X_train': X_train, 'X_test': X_test, 'y_train': y_train,
            'y_test': y_test}
    return data