Skip to content
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

Jump to bottom

[python] disabled split value histogram for categorical features #2045

Merged
merged 3 commits into from
Mar 14, 2019
Merged

[python] disabled split value histogram for categorical features #2045

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
94012cf
disabled split value histogram for categorical features
StrikerRUS Mar 10, 2019
c6456fa
updated test for cat. feature
StrikerRUS Mar 10, 2019
a39f806
updated docs
StrikerRUS Mar 10, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
10 changes: 9 additions & 1 deletion python-package/lightgbm/basic.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2437,6 +2437,11 @@ def get_split_value_histogram(self, feature, bins=None, xgboost_style=False):
The feature name or index the histogram is calculated for.
If int, interpreted as index.
If string, interpreted as name.

Note
----
Categorical features are not supported.

bins : int, string or None, optional (default=None)
The maximum number of bins.
If None, or int and > number of unique split values and ``xgboost_style=True``,
Expand Down Expand Up @@ -2464,7 +2469,10 @@ def add(root):
else:
split_feature = root['split_feature']
if split_feature == feature:
values.append(root['threshold'])
if isinstance(root['threshold'], string_type):
raise LightGBMError('Cannot compute split value histogram for the categorical feature')
else:
values.append(root['threshold'])
add(root['left_child'])
add(root['right_child'])

Expand Down
14 changes: 8 additions & 6 deletions tests/python_package_test/test_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1245,17 +1245,17 @@ def test_model_size(self):

def test_get_split_value_histogram(self):
X, y = load_boston(True)
lgb_train = lgb.Dataset(X, y)
lgb_train = lgb.Dataset(X, y, categorical_feature=[2])
gbm = lgb.train({'verbose': -1}, lgb_train, num_boost_round=20)
# test XGBoost-style return value
params = {'feature': 0, 'xgboost_style': True}
self.assertTupleEqual(gbm.get_split_value_histogram(**params).shape, (10, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=999, **params).shape, (10, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(**params).shape, (9, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=999, **params).shape, (9, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=-1, **params).shape, (1, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=0, **params).shape, (1, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=1, **params).shape, (1, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=2, **params).shape, (2, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=6, **params).shape, (6, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=6, **params).shape, (5, 2))
self.assertTupleEqual(gbm.get_split_value_histogram(bins=7, **params).shape, (6, 2))
if lgb.compat.PANDAS_INSTALLED:
np.testing.assert_almost_equal(
Expand All @@ -1277,8 +1277,8 @@ def test_get_split_value_histogram(self):
)
# test numpy-style return value
hist, bins = gbm.get_split_value_histogram(0)
self.assertEqual(len(hist), 22)
self.assertEqual(len(bins), 23)
self.assertEqual(len(hist), 23)
self.assertEqual(len(bins), 24)
hist, bins = gbm.get_split_value_histogram(0, bins=999)
self.assertEqual(len(hist), 999)
self.assertEqual(len(bins), 1000)
Expand Down Expand Up @@ -1316,3 +1316,5 @@ def test_get_split_value_histogram(self):
mask = hist_vals > 0
np.testing.assert_array_equal(hist_vals[mask], hist[:, 1])
np.testing.assert_almost_equal(bin_edges[1:][mask], hist[:, 0])
# test histogram is disabled for categorical features
self.assertRaises(lgb.basic.LightGBMError, gbm.get_split_value_histogram, 2)