test_normalization.py 文件源码

def preprocess_feature(self, feature, parameters):
        is_not_empty = 1 - np.isclose(feature, normalization.MISSING_VALUE)
        if parameters.feature_type == identify_types.BINARY:
            # Binary features are always 1 unless they are 0
            return ((feature != 0) * is_not_empty).astype(np.float32)
        if parameters.boxcox_lambda is not None:
            feature = stats.boxcox(
                np.maximum(
                    feature + parameters.boxcox_shift,
                    normalization.BOX_COX_MARGIN
                ), parameters.boxcox_lambda
            )
        # No *= to ensure consistent out-of-place operation.
        if parameters.feature_type == identify_types.PROBABILITY:
            feature = np.clip(feature, 0.01, 0.99)
            feature = special.logit(feature)
        elif parameters.feature_type == identify_types.QUANTILE:
            quantiles = parameters.quantiles
            values = np.zeros(feature.shape)
            for quantile in quantiles:
                values += feature >= quantile
            feature = values / float(len(quantiles))
        elif parameters.feature_type == identify_types.ENUM:
            possible_values = parameters.possible_values
            mapping = {}
            for i, possible_value in enumerate(possible_values):
                mapping[possible_value] = i
            output_feature = np.zeros((len(feature), len(possible_values)))
            for i, val in enumerate(feature):
                output_feature[i][mapping[val]] = 1.0
            return output_feature
        else:
            feature = feature - parameters.mean
            feature /= parameters.stddev
        feature *= is_not_empty
        return feature