Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Test scikit-learn model IO with gblinear. (#9459)

Browse Source
This commit is contained in:
Jiaming Yuan 2023-08-13 23:41:49 +08:00 committed by GitHub
parent bb56183396
commit 801116c307
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 25 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

31
tests/python/test_with_sklearn.py
View File

@ -792,19 +792,19 @@ def test_kwargs_grid_search():
from sklearn import datasets from sklearn import datasets
from sklearn.model_selection import GridSearchCV from sklearn.model_selection import GridSearchCV
params = {'tree_method': 'hist'} params = {"tree_method": "hist"}
clf = xgb.XGBClassifier(n_estimators=1, learning_rate=1.0, **params) clf = xgb.XGBClassifier(n_estimators=3, **params)
assert clf.get_params()['tree_method'] == 'hist' assert clf.get_params()["tree_method"] == "hist"
# 'max_leaves' is not a default argument of XGBClassifier # 'eta' is not a default argument of XGBClassifier
# Check we can still do grid search over this parameter # Check we can still do grid search over this parameter
search_params = {'max_leaves': range(2, 5)} search_params = {"eta": [0, 0.2, 0.4]}
grid_cv = GridSearchCV(clf, search_params, cv=5) grid_cv = GridSearchCV(clf, search_params, cv=5)
iris = datasets.load_iris() iris = datasets.load_iris()
grid_cv.fit(iris.data, iris.target) grid_cv.fit(iris.data, iris.target)
# Expect unique results for each parameter value # Expect unique results for each parameter value
# This confirms sklearn is able to successfully update the parameter # This confirms sklearn is able to successfully update the parameter
means = grid_cv.cv_results_['mean_test_score'] means = grid_cv.cv_results_["mean_test_score"]
assert len(means) == len(set(means)) assert len(means) == len(set(means))
@ -928,6 +928,25 @@ def save_load_model(model_path):
xgb_model = xgb.XGBModel() xgb_model = xgb.XGBModel()
xgb_model.load_model(model_path) xgb_model.load_model(model_path)
clf = xgb.XGBClassifier(booster="gblinear", early_stopping_rounds=1)
clf.fit(X, y, eval_set=[(X, y)])
best_iteration = clf.best_iteration
best_score = clf.best_score
predt_0 = clf.predict(X)
clf.save_model(model_path)
clf.load_model(model_path)
predt_1 = clf.predict(X)
np.testing.assert_allclose(predt_0, predt_1)
assert clf.best_iteration == best_iteration
assert clf.best_score == best_score
clfpkl = pickle.dumps(clf)
clf = pickle.loads(clfpkl)
predt_2 = clf.predict(X)
np.testing.assert_allclose(predt_0, predt_2)
assert clf.best_iteration == best_iteration
assert clf.best_score == best_score
def test_save_load_model(): def test_save_load_model():
with tempfile.TemporaryDirectory() as tempdir: with tempfile.TemporaryDirectory() as tempdir: