in src/sagemaker_sklearn_extension/preprocessing/encoders.py [0:0]
def inverse_transform(self, X):
"""Convert the data back to the original representation.
In slots where the encoding is that of an unrecognised category, the output of the inverse transform is np.nan
for float or complex arrays, and None otherwise
Parameters
----------
X : array-like or sparse matrix, shape [n_samples, n_encoded_features]
The transformed data.
Returns
-------
X_tr : array-like, shape [n_samples, n_features]
Inverse transformed array.
Notes
-----
Most of the logic is copied from sklearn.preprocessing.OrdinalEncoder.inverse_transform. The difference is in
handling unknown values.
"""
check_is_fitted(self, "categories_")
X = check_array(X, dtype="numeric", force_all_finite="allow-nan" if self.unknown_as_nan else True)
n_samples, _ = X.shape
n_features = len(self.categories_)
# validate shape of passed X
msg = "Shape of the passed X data is not correct. Expected {0} " "columns, got {1}."
if X.shape[1] != n_features:
raise ValueError(msg.format(n_features, X.shape[1]))
# create resulting array of appropriate dtype
dt = np.find_common_type([cat.dtype for cat in self.categories_], [])
X_tr = np.empty((n_samples, n_features), dtype=dt)
found_unknown = {}
for i in range(n_features):
labels = X[:, i].astype("int64", copy=False)
known_mask = np.isfinite(X[:, i]) if self.unknown_as_nan else (labels != self.categories_[i].shape[0])
labels *= known_mask
X_tr[:, i] = self.categories_[i][labels]
if not np.all(known_mask):
found_unknown[i] = ~known_mask
# if unknown are found cast to an object array and transform the missing values to None
if found_unknown:
if X_tr.dtype != object:
X_tr = X_tr.astype(object)
for idx, unknown_mask in found_unknown.items():
X_tr[unknown_mask, idx] = None
X_tr[:, self.feature_idxs_no_categories_] = None
return X_tr