Imputation.py 文件源码

def _dense_fit(self, X, strategy, missing_values, axis):
        """Fit the transformer on dense data."""
        X = check_array(X, force_all_finite=False)
        mask = _get_mask(X, missing_values)
        masked_X = ma.masked_array(X, mask=mask)

        # Mean
        if strategy == "mean":
            mean_masked = np.ma.mean(masked_X, axis=axis)
            # Avoid the warning "Warning: converting a masked element to nan."
            mean = np.ma.getdata(mean_masked)
            mean[np.ma.getmask(mean_masked)] = np.nan

            return mean

        # Median
        elif strategy == "median":
            if tuple(int(v) for v in np.__version__.split('.')[:2]) < (1, 5):
                # In old versions of numpy, calling a median on an array
                # containing nans returns nan. This is different is
                # recent versions of numpy, which we want to mimic
                masked_X.mask = np.logical_or(masked_X.mask,
                                              np.isnan(X))
            median_masked = np.ma.median(masked_X, axis=axis)
            # Avoid the warning "Warning: converting a masked element to nan."
            median = np.ma.getdata(median_masked)
            median[np.ma.getmaskarray(median_masked)] = np.nan

            return median

        # Most frequent
        elif strategy == "most_frequent":
            # scipy.stats.mstats.mode cannot be used because it will no work
            # properly if the first element is masked and if it's frequency
            # is equal to the frequency of the most frequent valid element
            # See https://github.com/scipy/scipy/issues/2636

            # To be able access the elements by columns
            if axis == 0:
                X = X.transpose()
                mask = mask.transpose()

            most_frequent = np.empty(X.shape[0])

            for i, (row, row_mask) in enumerate(zip(X[:], mask[:])):
                row_mask = np.logical_not(row_mask).astype(np.bool)
                row = row[row_mask]
                most_frequent[i] = _most_frequent(row, np.nan, 0)

            return most_frequent