dual_imputer.py 文件源码

def __init__(self, strategy_categorical="most_frequent", strategy_numerical="median", categorical=None):
        """
        An Imputer that can apply a different strategy for both categorical data and numerical data.
        :param strategy_categorical: "mean", "median" or "most_frequent"
        :param strategy_numerical: "mean", "median" or "most_frequent"
        :param categorical: A boolean mask for the categorical columns of a dataset
        """
        if categorical is None:
            categorical = []
        self.strategy_categorical = strategy_categorical
        self.strategy_numerical = strategy_numerical
        self.cat_imputer = Imputer(strategy=strategy_categorical)
        self.num_imputer = Imputer(strategy=strategy_numerical)
        self.categorical = categorical
        self._update_indices()