missing_data_imputation.py 文件源码

def summarize(self, x, summary_func, missing_data_cond, in_place=False):
        """ Substitutes missing values with a statistical summary of each
        feature vector

        Parameters
        ----------
        x : numpy.array
            Assumes that each feature column is of single type. Converts
            digit string features to float.
        summary_func : function
            Summarization function to be used for imputation
            (mean, median, mode, max, min...)
        missing_data_cond : function
            Method that takes one value and returns True if it represents
            missing data or false otherwise.
        """

        if in_place:
            data = x
        else:
            data = np.copy(x)

        # replace missing values with the summarization function
        for col in xrange(x.shape[1]):
            nan_ids = missing_data_cond(x[:, col])
            if True in nan_ids:
                val = summary_func(x[~nan_ids, col])
                data[nan_ids, col] = val

        return data