features.py 文件源码

def create_scipy_features(base_features, sentinel):
    r"""Calculate the skew, kurtosis, and other statistical features
    for each row.

    Parameters
    ----------
    base_features : numpy array
        The feature dataframe.
    sentinel : float
        The number to be imputed for NaN values.

    Returns
    -------
    sp_features : numpy array
        The calculated SciPy features.

    """

    logger.info("Creating SciPy Features")

    # Generate scipy features

    logger.info("SciPy Feature: geometric mean")
    row_gmean = sps.gmean(base_features, axis=1)
    logger.info("SciPy Feature: kurtosis")
    row_kurtosis = sps.kurtosis(base_features, axis=1)
    logger.info("SciPy Feature: kurtosis test")
    row_ktest, pvalue = sps.kurtosistest(base_features, axis=1)
    logger.info("SciPy Feature: normal test")
    row_normal, pvalue = sps.normaltest(base_features, axis=1)
    logger.info("SciPy Feature: skew")
    row_skew = sps.skew(base_features, axis=1)
    logger.info("SciPy Feature: skew test")
    row_stest, pvalue = sps.skewtest(base_features, axis=1)
    logger.info("SciPy Feature: variation")
    row_var = sps.variation(base_features, axis=1)
    logger.info("SciPy Feature: signal-to-noise ratio")
    row_stn = sps.signaltonoise(base_features, axis=1)
    logger.info("SciPy Feature: standard error of mean")
    row_sem = sps.sem(base_features, axis=1)

    sp_features = np.column_stack((row_gmean, row_kurtosis, row_ktest,
                                   row_normal, row_skew, row_stest,
                                   row_var, row_stn, row_sem))
    sp_features = impute_values(sp_features, 'float64', sentinel)
    sp_features = StandardScaler().fit_transform(sp_features)

    # Return new SciPy features

    logger.info("SciPy Feature Count : %d", sp_features.shape[1])
    return sp_features


#
# Function create_clusters
#