def _transform(self, X, handle_unknown='error'):
X = self._check_X(X)
_, n_features = X.shape
X_int = np.zeros_like(X, dtype=np.int)
X_mask = np.ones_like(X, dtype=np.bool)
for i in range(n_features):
Xi = X[:, i]
diff, valid_mask = _encode_check_unknown(Xi, self.categories_[i],
return_mask=True)
if not np.all(valid_mask):
if handle_unknown == 'error':
msg = ("Found unknown categories {0} in column {1}"
" during transform".format(diff, i))
raise ValueError(msg)
else:
# Set the problematic rows to an acceptable value and
# continue `The rows are marked `X_mask` and will be
# removed later.
X_mask[:, i] = valid_mask
Xi = Xi.copy()
Xi[~valid_mask] = self.categories_[i][0]
_, encoded = _encode(Xi, self.categories_[i], encode=True)
X_int[:, i] = encoded
return X_int, X_mask
def transform(self, y):
"""Transform labels to normalized encoding.
If ``self.fill_unseen_labels`` is ``True``, use ``self.fill_encoded_label_value`` for unseen values.
Seen labels are encoded with value between 0 and n_classes-1. Unseen labels are encoded with
``self.fill_encoded_label_value`` with a default value of n_classes.
Parameters
----------
y : array-like of shape [n_samples]
Label values.
Returns
-------
y_encoded : array-like of shape [n_samples]
Encoded label values.
"""
check_is_fitted(self, "classes_")
y = column_or_1d(y, warn=True)
# transform of empty array is empty array
if _num_samples(y) == 0:
return np.array([])
if self.fill_unseen_labels:
_, mask = _encode_check_unknown(y, self.classes_, return_mask=True)
y_encoded = np.searchsorted(self.classes_, y)
fill_encoded_label_value = self.fill_encoded_label_value or len(
self.classes_)
y_encoded[~mask] = fill_encoded_label_value
else:
_, y_encoded = _encode(y, uniques=self.classes_, encode=True)
return y_encoded
def _fit(self, X, handle_unknown='error'):
X = self._check_X(X)
n_samples, n_features = X.shape
if self._categories != 'auto':
if X.dtype != object:
for cats in self._categories:
if not np.all(np.sort(cats) == np.array(cats)):
raise ValueError("Unsorted categories are not "
"supported for numerical categories")
if len(self._categories) != n_features:
raise ValueError("Shape mismatch: if n_values is an array,"
" it has to be of shape (n_features,).")
self.categories_ = []
for i in range(n_features):
Xi = X[:, i]
if self._categories == 'auto':
cats = _encode(Xi)
else:
cats = np.array(self._categories[i], dtype=X.dtype)
if handle_unknown == 'error':
diff = _encode_check_unknown(Xi, cats)
if diff:
msg = ("Found unknown categories {0} in column {1}"
" during fit".format(diff, i))
raise ValueError(msg)
self.categories_.append(cats)