def fit(self, X, y=None):
"""Fit OneHotEncoder to X.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data to determine the categories of each feature.
Returns
-------
self
"""
if self.handle_unknown not in ('error', 'ignore'):
msg = ("handle_unknown should be either 'error' or 'ignore', "
"got {0}.".format(self.handle_unknown))
raise ValueError(msg)
self._handle_deprecations(X)
if self._legacy_mode:
_transform_selected(X, self._legacy_fit_transform, self.dtype,
self._categorical_features,
copy=True)
return self
else:
self._fit(X, handle_unknown=self.handle_unknown)
return self
def test_transform_selected_retain_order():
X = [[-1, 1], [2, -2]]
assert_raise_message(ValueError,
"The retain_order option can only be set to True "
"for dense matrices.",
_transform_selected, sparse.csr_matrix(X),
Binarizer().transform, dtype=np.int, selected=[0],
retain_order=True)
def transform(X):
return np.hstack((X, [[0], [0]]))
assert_raise_message(ValueError,
"The retain_order option can only be set to True "
"if the dimensions of the input array match the "
"dimensions of the transformed array.",
_transform_selected, X, transform, dtype=np.int,
selected=[0], retain_order=True)
X_expected = [[-1, 1], [2, 0]]
Xtr = _transform_selected(X, Binarizer().transform, dtype=np.int,
selected=[1], retain_order=True)
assert_array_equal(toarray(Xtr), X_expected)
X_expected = [[0, 1], [1, -2]]
Xtr = _transform_selected(X, Binarizer().transform, dtype=np.int,
selected=[0], retain_order=True)
assert_array_equal(toarray(Xtr), X_expected)
def fit_transform(self, X, y=None):
"""Fit OneHotEncoder to X, then transform X.
Equivalent to fit(X).transform(X) but more convenient.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data to encode.
Returns
-------
X_out : sparse matrix if sparse=True else a 2-d array
Transformed input.
"""
if self.handle_unknown not in ('error', 'ignore'):
msg = ("handle_unknown should be either 'error' or 'ignore', "
"got {0}.".format(self.handle_unknown))
raise ValueError(msg)
self._handle_deprecations(X)
if self._legacy_mode:
return _transform_selected(
X, self._legacy_fit_transform, self.dtype,
self._categorical_features, copy=True)
else:
return self.fit(X).transform(X)
def transform(self, X, y=None):
check_is_fitted(self, 'n_features_')
n_features = X.shape[1]
if n_features != self.n_features_:
raise ValueError(f'X has different shape than during fitting.'
f' Expected {self.n_features_} features,'
f' got {n_features}.')
return _transform_selected(
X,
self._transform,
dtype=X.dtype,
selected=self.periodic_features,
copy=True
)
def test_transform_selected_copy_arg(output_dtype, input_dtype):
# transformer that alters X
def _mutating_transformer(X):
X[0, 0] = X[0, 0] + 1
return X
original_X = np.asarray([[1, 2], [3, 4]], dtype=input_dtype)
expected_Xtr = np.asarray([[2, 2], [3, 4]], dtype=output_dtype)
X = original_X.copy()
Xtr = _transform_selected(X, _mutating_transformer, output_dtype,
copy=True, selected='all')
assert_array_equal(toarray(X), toarray(original_X))
assert_array_equal(toarray(Xtr), expected_Xtr)
def transform(self, X):
"""Transform X using one-hot encoding.
Parameters
----------
X : array-like, shape [n_samples, n_features]
The data to encode.
Returns
-------
X_out : sparse matrix if sparse=True else a 2-d array
Transformed input.
"""
if self._legacy_mode:
return _transform_selected(X, self._legacy_transform, self.dtype,
self._categorical_features,
copy=True)
else:
return self._transform_new(X)
def _check_transform_selected(X, X_expected, dtype, sel):
for M in (X, sparse.csr_matrix(X)):
Xtr = _transform_selected(M, Binarizer().transform, dtype, sel)
assert_array_equal(toarray(Xtr), X_expected)