def transform()

in src/sagemaker_sklearn_extension/preprocessing/encoders.py [0:0]

• 15 lines of code
• 7 McCabe index (conditional complexity)

    def transform(self, X):
        """Transform each column of `X` using the Weight-of-Evidence encoding.

        Returns
        -------
        X_encoded: array, shape (n_samples, n_encoded_features)
            Array with each of the encoded columns.
        """
        # check is fitted
        check_is_fitted(self, "woe_pairs_")
        # check input
        X = check_array(X)

        if X.shape[1] != self._dim:
            raise ValueError(f"The input dimension is {X.shape[1]} instead of the expected {self._dim}")

        if self.binning:
            Xp = self.binner_.transform(X)
        else:
            Xp = X

        Xe = np.zeros(Xp.shape)
        for (i, x) in enumerate(Xp.T):
            codex, woe = self.woe_pairs_[i]
            # check that the data to encode doesn't have classes yet unseen
            assert all([e in codex.keys() for e in np.unique(x)]), WOEAsserts.UNSEEN_CAT
            # construct the encoded column by inverting the codex, if the category
            # is not recognised (not a key of the codex), a np.nan is inputted
            Xe[:, i] = np.array([woe[codex[xi]] for xi in x])

        return Xe