TermDocMatrix.py 文件源码

def _get_scaler_function(self, scaler_algo):
        scaler = None
        if scaler_algo == 'percentile':
            scaler = lambda x: rankdata(x).astype(np.float64) / len(x)
        elif scaler_algo == 'normcdf':
            # scaler = lambda x: ECDF(x[cat_word_counts != 0])(x)
            scaler = lambda x: norm.cdf(x, x.mean(), x.std())
        elif scaler_algo == 'none':
            scaler = lambda x: x
        else:
            raise InvalidScalerException("Invalid scaler alogrithm.  Must be either percentile or normcdf.")
        return scaler