if self.axis is None:
            self._axis = 0
        else:
            warnings.warn("Parameter 'axis' has been deprecated in 0.20 and "
                          "will be removed in 0.22. Future (and default) "
                          "behavior is equivalent to 'axis=0' (impute along "
                          "columns). Row-wise imputation can be performed "
                          "with FunctionTransformer.", DeprecationWarning)
            self._axis = self.axis

        if self._axis not in [0, 1]:
            raise ValueError("Can only impute missing values on axis 0 and 1, "
                             " got axis={0}".format(self._axis))

        # Since two different arrays can be provided in fit(X) and
        # transform(X), the imputation data will be computed in transform()
        # when the imputation is done per sample (i.e., when axis=1).
        if self.axis == 0:
            faf = 'allow-nan' if self.missing_values == 'NaN' else True
            X = check_array(X, accept_sparse='csc', dtype=np.float64,
                            force_all_finite=faf)

            if sparse.issparse(X):
                self.statistics_ = self._sparse_fit(X,
                                                    self.strategy,
                                                    self.missing_values,
                                                    self._axis)
            else:
                self.statistics_ = self._dense_fit(X,
                                                   self.strategy,
                                                   self.missing_values,
                                                   self._axis)