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-package] Accept numpy generators as random_state #6174

Merged
merged 7 commits into from
Nov 9, 2023
Merged

[python-package] Accept numpy generators as random_state #6174

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
de92fcc
accept numpy generators
david-cortes Nov 1, 2023
67143d1
fix tests
david-cortes Nov 1, 2023
5bde06a
Merge branch 'master' into take_generator
david-cortes Nov 1, 2023
122be33
use python int
david-cortes Nov 1, 2023
1af35b4
add compat workaround for older numpy
david-cortes Nov 8, 2023
c6316ca
Merge branch 'master' into take_generator
david-cortes Nov 8, 2023
e86776e
Merge branch 'master' into take_generator
jameslamb Nov 8, 2023
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
6 changes: 3 additions & 3 deletions python-package/lightgbm/dask.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1142,7 +1142,7 @@ def __init__(
colsample_bytree: float = 1.,
reg_alpha: float = 0.,
reg_lambda: float = 0.,
random_state: Optional[Union[int, np.random.RandomState]] = None,
random_state: Optional[Union[int, np.random.RandomState, np.random.Generator]] = None,
n_jobs: Optional[int] = None,
importance_type: str = 'split',
client: Optional[Client] = None,
Expand Down Expand Up @@ -1347,7 +1347,7 @@ def __init__(
colsample_bytree: float = 1.,
reg_alpha: float = 0.,
reg_lambda: float = 0.,
random_state: Optional[Union[int, np.random.RandomState]] = None,
random_state: Optional[Union[int, np.random.RandomState, np.random.Generator]] = None,
n_jobs: Optional[int] = None,
importance_type: str = 'split',
client: Optional[Client] = None,
Expand Down Expand Up @@ -1517,7 +1517,7 @@ def __init__(
colsample_bytree: float = 1.,
reg_alpha: float = 0.,
reg_lambda: float = 0.,
random_state: Optional[Union[int, np.random.RandomState]] = None,
random_state: Optional[Union[int, np.random.RandomState, np.random.Generator]] = None,
n_jobs: Optional[int] = None,
importance_type: str = 'split',
client: Optional[Client] = None,
Expand Down
8 changes: 6 additions & 2 deletions python-package/lightgbm/sklearn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -409,7 +409,7 @@ def __init__(
colsample_bytree: float = 1.,
reg_alpha: float = 0.,
reg_lambda: float = 0.,
random_state: Optional[Union[int, np.random.RandomState]] = None,
random_state: Optional[Union[int, np.random.RandomState, np.random.Generator]] = None,
n_jobs: Optional[int] = None,
importance_type: str = 'split',
**kwargs
Expand Down Expand Up @@ -470,7 +470,7 @@ def __init__(
random_state : int, RandomState object or None, optional (default=None)
Random number seed.
If int, this number is used to seed the C++ code.
If RandomState object (numpy), a random integer is picked based on its state to seed the C++ code.
If RandomState or Generator object (numpy), a random integer is picked based on its state to seed the C++ code.
If None, default seeds in C++ code are used.
n_jobs : int or None, optional (default=None)
Number of parallel threads to use for training (can be changed at prediction time by
Expand Down Expand Up @@ -671,6 +671,10 @@ def _process_params(self, stage: str) -> Dict[str, Any]:

if isinstance(params['random_state'], np.random.RandomState):
params['random_state'] = params['random_state'].randint(np.iinfo(np.int32).max)
elif isinstance(params['random_state'], np.random.Generator):
params['random_state'] = int(
params['random_state'].integers(np.iinfo(np.int32).max)
)
if self._n_classes > 2:
for alias in _ConfigAliases.get('num_class'):
params.pop(alias, None)
Expand Down
7 changes: 4 additions & 3 deletions tests/python_package_test/test_sklearn.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -534,11 +534,12 @@ def test_non_serializable_objects_in_callbacks(tmp_path):
assert gbm.booster_.attr_set_inside_callback == 40


def test_random_state_object():
@pytest.mark.parametrize("rng_constructor", [np.random.RandomState, np.random.default_rng])
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

forgot to add in my review... thanks very much for adding this to this test!

def test_random_state_object(rng_constructor):
X, y = load_iris(return_X_y=True)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.1, random_state=42)
state1 = np.random.RandomState(123)
state2 = np.random.RandomState(123)
state1 = rng_constructor(123)
state2 = rng_constructor(123)
clf1 = lgb.LGBMClassifier(n_estimators=10, subsample=0.5, subsample_freq=1, random_state=state1)
clf2 = lgb.LGBMClassifier(n_estimators=10, subsample=0.5, subsample_freq=1, random_state=state2)
# Test if random_state is properly stored
Expand Down
Loading