synthetic_data_generator.py 文件源码

def remove_unneeded_features(samples):
    """
    Removes features that have the same value in given data samples.
    :param samples: data samples
    :return: samples with updated features
    """
    selector = VarianceThreshold()
    selector.fit_transform(samples)
    # Array of integers corresponding to non removed features
    features = selector.get_support(indices=True)

    # Array of all non removed features names
    feature_names = [column for column in samples[features]]

    return pd.DataFrame(selector.fit_transform(samples), columns=feature_names)