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

[breaking] Remove label encoder deprecated in 1.3. (#7357)

Browse Source
This commit is contained in:
Jiaming Yuan
2021-10-28 13:24:29 +08:00
committed by GitHub
parent d05754f558
commit 3c4aa9b2ea
7 changed files with 74 additions and 83 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/python-gpu/test_from_cudf.py
View File

@@ -239,7 +239,7 @@ def test_cudf_training_with_sklearn():
y_cudf_series = ss(data=y.iloc[:, 0])
for y_obj in [y_cudf, y_cudf_series]:
clf = xgb.XGBClassifier(gpu_id=0, tree_method='gpu_hist', use_label_encoder=False)
clf = xgb.XGBClassifier(gpu_id=0, tree_method='gpu_hist')
clf.fit(X_cudf, y_obj, sample_weight=cudf_weights, base_margin=cudf_base_margin,
eval_set=[(X_cudf, y_obj)])
pred = clf.predict(X_cudf)

2
tests/python-gpu/test_from_cupy.py
View File

@@ -122,7 +122,7 @@ def test_cupy_training_with_sklearn():
base_margin = np.random.random(50)
cupy_base_margin = cp.array(base_margin)
clf = xgb.XGBClassifier(gpu_id=0, tree_method="gpu_hist", use_label_encoder=False)
clf = xgb.XGBClassifier(gpu_id=0, tree_method="gpu_hist")
clf.fit(
X,
y,

24
tests/python-gpu/test_gpu_basic_models.py
View File

@@ -7,6 +7,7 @@ sys.path.append("tests/python")
# Don't import the test class, otherwise they will run twice.
import test_callback as test_cb # noqa
import test_basic_models as test_bm
import testing as tm
rng = np.random.RandomState(1994)
@@ -14,16 +15,12 @@ class TestGPUBasicModels:
cpu_test_cb = test_cb.TestCallbacks()
cpu_test_bm = test_bm.TestModels()
def run_cls(self, X, y, deterministic):
cls = xgb.XGBClassifier(tree_method='gpu_hist',
deterministic_histogram=deterministic,
single_precision_histogram=True)
def run_cls(self, X, y):
cls = xgb.XGBClassifier(tree_method='gpu_hist', single_precision_histogram=True)
cls.fit(X, y)
cls.get_booster().save_model('test_deterministic_gpu_hist-0.json')
cls = xgb.XGBClassifier(tree_method='gpu_hist',
deterministic_histogram=deterministic,
single_precision_histogram=True)
cls = xgb.XGBClassifier(tree_method='gpu_hist', single_precision_histogram=True)
cls.fit(X, y)
cls.get_booster().save_model('test_deterministic_gpu_hist-1.json')
@@ -49,19 +46,22 @@ class TestGPUBasicModels:
kClasses = 4
# Create large values to force rounding.
X = np.random.randn(kRows, kCols) * 1e4
y = np.random.randint(0, kClasses, size=kRows) * 1e4
y = np.random.randint(0, kClasses, size=kRows)
model_0, model_1 = self.run_cls(X, y, True)
model_0, model_1 = self.run_cls(X, y)
assert model_0 == model_1
@pytest.mark.skipif(**tm.no_sklearn())
def test_invalid_gpu_id(self):
X = np.random.randn(10, 5) * 1e4
y = np.random.randint(0, 2, size=10) * 1e4
from sklearn.datasets import load_digits
X, y = load_digits(return_X_y=True)
# should pass with invalid gpu id
cls1 = xgb.XGBClassifier(tree_method='gpu_hist', gpu_id=9999)
cls1.fit(X, y)
# should throw error with fail_on_invalid_gpu_id enabled
cls2 = xgb.XGBClassifier(tree_method='gpu_hist', gpu_id=9999, fail_on_invalid_gpu_id=True)
cls2 = xgb.XGBClassifier(
tree_method='gpu_hist', gpu_id=9999, fail_on_invalid_gpu_id=True
)
try:
cls2.fit(X, y)
assert False, "Should have failed with with fail_on_invalid_gpu_id enabled"

4
tests/python-gpu/test_gpu_pickling.py
View File

@@ -146,8 +146,10 @@ class TestPickling:
os.remove(model_path)
@pytest.mark.skipif(**tm.no_sklearn())
def test_predict_sklearn_pickle(self):
x, y = build_dataset()
from sklearn.datasets import load_digits
x, y = load_digits(return_X_y=True)
kwargs = {'tree_method': 'gpu_hist',
'predictor': 'gpu_predictor',

34
tests/python-gpu/test_gpu_with_sklearn.py
View File

@@ -56,7 +56,6 @@ def test_categorical():
X, y = load_svmlight_file(os.path.join(data_dir, "agaricus.txt.train"))
clf = xgb.XGBClassifier(
tree_method="gpu_hist",
use_label_encoder=False,
enable_categorical=True,
n_estimators=10,
)
@@ -98,3 +97,36 @@ def test_categorical():
X = cudf.DataFrame(X)
check_predt(X, y)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_cudf())
def test_classififer():
from sklearn.datasets import load_digits
import cupy as cp
import cudf
X, y = load_digits(return_X_y=True)
y *= 10
clf = xgb.XGBClassifier(tree_method="gpu_hist", n_estimators=1)
# numpy
with pytest.raises(ValueError, match=r"Invalid classes.*"):
clf.fit(X, y)
# cupy
X, y = cp.array(X), cp.array(y)
with pytest.raises(ValueError, match=r"Invalid classes.*"):
clf.fit(X, y)
# cudf
X, y = cudf.DataFrame(X), cudf.DataFrame(y)
with pytest.raises(ValueError, match=r"Invalid classes.*"):
clf.fit(X, y)
# pandas
X, y = load_digits(return_X_y=True, as_frame=True)
y *= 10
with pytest.raises(ValueError, match=r"Invalid classes.*"):
clf.fit(X, y)

18
tests/python/test_with_sklearn.py
View File

@@ -283,7 +283,6 @@ def test_feature_importances_gain():
random_state=0, tree_method="exact",
learning_rate=0.1,
importance_type="gain",
use_label_encoder=False,
).fit(X, y)
exp = np.array([0., 0., 0., 0., 0., 0., 0., 0., 0., 0.,
@@ -306,7 +305,6 @@ def test_feature_importances_gain():
tree_method="exact",
learning_rate=0.1,
importance_type="gain",
use_label_encoder=False,
).fit(X, y)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
@@ -315,14 +313,11 @@ def test_feature_importances_gain():
tree_method="exact",
learning_rate=0.1,
importance_type="gain",
use_label_encoder=False,
).fit(X, y)
np.testing.assert_almost_equal(xgb_model.feature_importances_, exp)
# no split can be found
cls = xgb.XGBClassifier(
min_child_weight=1000, tree_method="hist", n_estimators=1, use_label_encoder=False
)
cls = xgb.XGBClassifier(min_child_weight=1000, tree_method="hist", n_estimators=1)
cls.fit(X, y)
assert np.all(cls.feature_importances_ == 0)
@@ -497,7 +492,7 @@ def test_classification_with_custom_objective():
X, y
)
cls = xgb.XGBClassifier(use_label_encoder=False, n_estimators=1)
cls = xgb.XGBClassifier(n_estimators=1)
cls.fit(X, y)
is_called = [False]
@@ -923,7 +918,7 @@ def test_RFECV():
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10,
objective='binary:logistic',
random_state=0, verbosity=0, use_label_encoder=False)
random_state=0, verbosity=0)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='roc_auc')
rfecv.fit(X, y)
@@ -934,7 +929,7 @@ def test_RFECV():
n_estimators=10,
objective='multi:softprob',
random_state=0, reg_alpha=0.001, reg_lambda=0.01,
scale_pos_weight=0.5, verbosity=0, use_label_encoder=False)
scale_pos_weight=0.5, verbosity=0)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='neg_log_loss')
rfecv.fit(X, y)
@@ -943,7 +938,7 @@ def test_RFECV():
rfecv = RFECV(estimator=reg)
rfecv.fit(X, y)
cls = xgb.XGBClassifier(use_label_encoder=False)
cls = xgb.XGBClassifier()
rfecv = RFECV(estimator=cls, step=1, cv=3,
scoring='neg_mean_squared_error')
rfecv.fit(X, y)
@@ -1052,8 +1047,9 @@ def test_deprecate_position_arg():
with pytest.warns(FutureWarning):
model.fit(X, y, w)
with pytest.warns(FutureWarning):
with pytest.raises(ValueError):
xgb.XGBRFClassifier(1, use_label_encoder=True)
model = xgb.XGBRFClassifier(n_estimators=1)
with pytest.warns(FutureWarning):
model.fit(X, y, w)