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

[sklearn] Fix loading model attributes. (#9808)

Browse Source
This commit is contained in:
Jiaming Yuan
2023-11-27 17:19:01 +08:00
committed by GitHub
parent 3f4e22015a
commit e9f149481e
4 changed files with 48 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
tests/python/test_with_sklearn.py
View File

@@ -944,6 +944,7 @@ def save_load_model(model_path):
predt_0 = clf.predict(X)
clf.save_model(model_path)
clf.load_model(model_path)
assert clf.booster == "gblinear"
predt_1 = clf.predict(X)
np.testing.assert_allclose(predt_0, predt_1)
assert clf.best_iteration == best_iteration
@@ -959,25 +960,26 @@ def save_load_model(model_path):
def test_save_load_model():
with tempfile.TemporaryDirectory() as tempdir:
model_path = os.path.join(tempdir, 'digits.model')
model_path = os.path.join(tempdir, "digits.model")
save_load_model(model_path)
with tempfile.TemporaryDirectory() as tempdir:
model_path = os.path.join(tempdir, 'digits.model.json')
model_path = os.path.join(tempdir, "digits.model.json")
save_load_model(model_path)
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
with tempfile.TemporaryDirectory() as tempdir:
model_path = os.path.join(tempdir, 'digits.model.ubj')
model_path = os.path.join(tempdir, "digits.model.ubj")
digits = load_digits(n_class=2)
y = digits['target']
X = digits['data']
booster = xgb.train({'tree_method': 'hist',
'objective': 'binary:logistic'},
dtrain=xgb.DMatrix(X, y),
num_boost_round=4)
y = digits["target"]
X = digits["data"]
booster = xgb.train(
{"tree_method": "hist", "objective": "binary:logistic"},
dtrain=xgb.DMatrix(X, y),
num_boost_round=4,
)
predt_0 = booster.predict(xgb.DMatrix(X))
booster.save_model(model_path)
cls = xgb.XGBClassifier()
@@ -1011,6 +1013,8 @@ def test_save_load_model():
clf = xgb.XGBClassifier()
clf.load_model(model_path)
assert clf.classes_.size == 10
assert clf.objective == "multi:softprob"
np.testing.assert_equal(clf.classes_, np.arange(10))
assert clf.n_classes_ == 10

7
tests/test_distributed/test_with_dask/test_with_dask.py
View File

@@ -1931,6 +1931,7 @@ class TestWithDask:
cls.client = client
cls.fit(X, y)
predt_0 = cls.predict(X)
proba_0 = cls.predict_proba(X)
with tempfile.TemporaryDirectory() as tmpdir:
path = os.path.join(tmpdir, "model.pkl")
@@ -1940,7 +1941,9 @@ class TestWithDask:
with open(path, "rb") as fd:
cls = pickle.load(fd)
predt_1 = cls.predict(X)
proba_1 = cls.predict_proba(X)
np.testing.assert_allclose(predt_0.compute(), predt_1.compute())
np.testing.assert_allclose(proba_0.compute(), proba_1.compute())
path = os.path.join(tmpdir, "cls.json")
cls.save_model(path)
@@ -1949,16 +1952,20 @@ class TestWithDask:
cls.load_model(path)
assert cls.n_classes_ == 10
predt_2 = cls.predict(X)
proba_2 = cls.predict_proba(X)
np.testing.assert_allclose(predt_0.compute(), predt_2.compute())
np.testing.assert_allclose(proba_0.compute(), proba_2.compute())
# Use single node to load
cls = xgb.XGBClassifier()
cls.load_model(path)
assert cls.n_classes_ == 10
predt_3 = cls.predict(X_)
proba_3 = cls.predict_proba(X_)
np.testing.assert_allclose(predt_0.compute(), predt_3)
np.testing.assert_allclose(proba_0.compute(), proba_3)
def test_dask_unsupported_features(client: "Client") -> None: