make_dataset.py 文件源码

def create_regression_dataset(n_samples, n_features, n_informative, effective_rank, tail_strength,
                              noise, random_state=None):
    """
    Creates a regression dataset

    :param n_samples: number of observations
    :param n_features: number of features
    :param n_informative: number of informative features
    :param n_targets: The number of regression targets, i.e., the dimension of the y output vector associated with a sample. By default, the output is a scalar.
    :param effective_rank: approximate number of singular vectors required to explain data
    :param tail_strength: relative importance of the fat noisy tail of the singular values profile
    :param noise: standard deviation of the gaussian noise applied to the output
    :param random_state: the numpy RandomState
    :return: the requested dataframe
    """
    random_state = get_random_state(random_state)
    X, y = make_regression(n_samples=n_samples, n_features=n_features, n_informative=n_informative,
                           n_targets=1, effective_rank=effective_rank, tail_strength=tail_strength,
                           noise=noise, random_state=random_state)

    # cast to a data frame
    df = pd.DataFrame(X)
    # rename X columns
    df = rename_columns(df)
    # and add the Y
    df['y'] = y
    return df