8000 [WIP] Sparse and Multioutput LabelEncoder by hamsal · Pull Request #3592 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content

[WIP] Sparse and Multioutput LabelEncoder #3592

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

[WIP] Sparse and Multioutput LabelEncoder #3592

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6f02d5f
Implement multioutput fit, transform, and fit_transform
hamsal Aug 26, 2014
2377dbf
Test sparse implementation of label encoding
hamsal Aug 26, 2014
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
40 changes: 27 additions & 13 deletions sklearn/preprocessing/label.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,9 +105,12 @@ def fit(self, y):
-------
self : returns an instance of self.
"""
y = column_or_1d(y, warn=True)
# y = column_or_1d(y, warn=True)
_check_numpy_unicode_bug(y)
self.classes_ = np.unique(y)
if 'multioutput' in type_of_target(y):
self.classes_ = [np.unique(y[:, k]) for k in range(y.shape[1])]
else:
self.classes_ = np.unique(y)
return self

def fit_transform(self, y):
Expand All @@ -122,9 +125,17 @@ def fit_transform(self, y):
-------
y : array-like of shape [n_samples]
"""
y = column_or_1d(y, warn=True)
# y = column_or_1d(y, warn=True)
_check_numpy_unicode_bug(y)
self.classes_, y = np.unique(y, return_inverse=True)
if 'multioutput' in type_of_target(y):
self.classes_ = []
y_enc = np.empty(y.shape, dtype=np.int)
for k in range(y_enc.shape[1]):
classes, y_enc[:, k] = np.unique(y[:, k], return_inverse=True)
self.classes_.append(classes)
y = y_enc
else:
self.classes_, y = np.unique(y, return_inverse=True)
return y

def transform(self, y):
Expand All @@ -141,12 +152,18 @@ def transform(self, y):
"""
self._check_fitted()

classes = np.unique(y)
_check_numpy_unicode_bug(classes)
if len(np.intersect1d(classes, self.classes_)) < len(classes):
diff = np.setdiff1d(classes, self.classes_)
raise ValueError("y contains new labels: %s" % str(diff))
return np.searchsorted(self.classes_, y)
if 'multioutput' in type_of_target(y):
y_enc = np.empty(y.shape, dtype=np.int)
for k in range(y.shape[1]):
y_enc[:, k] = np.searchsorted(self.classes_[k], y[:, k])
return y_enc
else:
classes = np.unique(y)
_check_numpy_unicode_bug(classes)
if len(np.intersect1d(classes, self.classes_)) < len(classes):
diff = np.setdiff1d(classes, self.classes_)
raise ValueError("y contains new labels: %s" % str(diff))
return np.searchsorted(self.classes_, y)

def inverse_transform(self, y):
"""Transform labels back to original encoding.
Expand Down Expand Up @@ -668,9 +685,6 @@ class MultiLabelBinarizer(BaseEstimator, TransformerMixin):
classes : array-like of shape [n_classes] (optional)
Indicates an ordering for the class labels

sparse_output : boolean (default: False),
Set to true if output binary array is desired in CSR sparse format

Attributes
----------
classes_ : array of labels
8000 Expand Down
73 changes: 73 additions & 0 deletions sklearn/preprocessing/tests/test_label.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -229,6 +229,79 @@ def test_label_encoder():
assert_raises(ValueError, le.transform, [0, 6])


def test_label_encoder_multioutput():
"""Test LabelEncoder's with multioutput target data"""
le = LabelEncoder()
y = np.array([[1,2,3,4,0],
[1,0,0,0,0],
[1,1,1,1,1],
[1,-1,2,0,1],
[1,0,1,1,0],
[1,2,3,4,5]])
classes = [[1],[-1,0,1,2],[0,1,2,3],[0,1,4],[0,1,5]]
y_enc = np.array([[0,3,3,2,0],
[0,1,0,0,0],
[0,2,1,1,1],
[0,0,2,0,1],
[0,1,1,1,0],
[0,3,3,2,2]])

# Test fit
le.fit(y)
for i in range(y.shape[1]):
assert_array_equal(le.classes_[i], classes[i])

# Test transform
assert_array_equal(le.transform(y), y_enc)

# Test inverse transform
assert_array_equal(le.inverse_transform(y_enc), y)

# Test fit transform
le = LabelEncoder()
ret = le.fit_transform(y)
assert_array_equal(ret, y_enc)

# Test unseeen label error
assert_raises(ValueError, le.transform, [0, 6])

def test_label_encoder_sparse_multioutput():
"""Test LabelEncoder's with multioutput target data in sparse formats"""
"""Test LabelEncoder's with multioutput target data"""
le = LabelEncoder()
y = sp.csc_matrix(np.array([[0,2,3,4,0],
[0,0,0,0,0],
[0,1,1,1,0],
[0,-1,2,0,1],
[0,0,1,1,0],
[0,2,3,4,5]]))
classes = [[0],[-1,0,1,2],[0,1,2,3],[0,1,4],[0,1,5]]
y = sp.csc_matrix(np.array([[0,3,3,2,0],
[0,2,0,0,0],
[0,2,1,1,0],
[0,0,2,0,1],
[0,1,1,1,0],
[0,3,3,2,2]]))

# Test fit
le.fit(y)
for i in range(y.shape[1]):
assert_array_equal(le.classes_[i], classes[i])

# Test transform
assert_array_equal(le.transform(y).toarray(), y_enc)

# Test inverse transform
assert_array_equal(le.inverse_transform(y_enc).toarray(), y)

# Test fit transform
le = LabelEncoder()
ret = le.fit_transform(y)
assert_array_equal(ret.toarray(), y_enc)

# Test unseeen label error
assert_raises(ValueError, le.transform, [0, 6])

def test_label_encoder_fit_transform():
"""Test fit_transform"""
le = LabelEncoder()
Expand Down
0