def test_parameters_access(self):
self._init_ray()
from sklearn import datasets
params = {"updater": "grow_gpu_hist", "subsample": 0.5, "n_jobs": -1}
clf = RayXGBClassifier(n_estimators=1000, **params)
assert clf.get_params()["updater"] == "grow_gpu_hist"
assert clf.get_params()["subsample"] == 0.5
assert clf.get_params()["n_estimators"] == 1000
clf = RayXGBClassifier(n_estimators=1, nthread=4)
X, y = datasets.load_iris(return_X_y=True)
clf.fit(X, y)
config = json.loads(clf.get_booster().save_config())
assert int(config["learner"]["generic_param"]["nthread"]) == 4
clf.set_params(nthread=16)
config = json.loads(clf.get_booster().save_config())
assert int(config["learner"]["generic_param"]["nthread"]) == 16
clf.predict(X)
config = json.loads(clf.get_booster().save_config())
assert int(config["learner"]["generic_param"]["nthread"]) == 16
def test_sklearn_get_default_params(self):
self._init_ray()
from sklearn.datasets import load_digits
digits_2class = load_digits(n_class=2)
X = digits_2class["data"]
y = digits_2class["target"]
cls = RayXGBClassifier()
assert cls.get_params()["base_score"] is None
cls.fit(X[:4, ...], y[:4, ...])
assert cls.get_params()["base_score"] is not None
def test_kwargs_grid_search(self):
self._init_ray()
from sklearn.model_selection import GridSearchCV
from sklearn import datasets
params = {"tree_method": "hist"}
clf = RayXGBClassifier(n_estimators=1, learning_rate=1.0, **params)
assert clf.get_params()["tree_method"] == "hist"
# 'max_leaves' is not a default argument of XGBClassifier
# Check we can still do grid search over this parameter
search_params = {"max_leaves": range(2, 5)}
grid_cv = GridSearchCV(clf, search_params, cv=5)
iris = datasets.load_iris()
grid_cv.fit(iris.data, iris.target)
# Expect unique results for each parameter value
# This confirms sklearn is able to successfully update the parameter
means = grid_cv.cv_results_["mean_test_score"]
assert len(means) == len(set(means))
