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

Deprecate LabelEncoder in XGBClassifier; Enable cuDF/cuPy inputs in XGBClassifier (#6269)

Browse Source 
* Deprecate LabelEncoder in XGBClassifier; skip LabelEncoder for cuDF/cuPy inputs

* Add unit tests for cuDF and cuPy inputs with XGBClassifier

* Fix lint

* Clarify warning

* Move use_label_encoder option to XGBClassifier constructor

* Add a test for cudf.Series

* Add use_label_encoder to XGBRFClassifier doc

* Address reviewer feedback
This commit is contained in:
Philip Hyunsu Cho
2020-10-26 13:20:51 -07:00
committed by GitHub
parent bcfab4d726
commit c8ec62103a
4 changed files with 119 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
tests/python-gpu/test_from_cudf.py
View File

@@ -172,6 +172,34 @@ Arrow specification.'''
_test_cudf_metainfo(xgb.DeviceQuantileDMatrix)
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_sklearn())
@pytest.mark.skipif(**tm.no_pandas())
def test_cudf_training_with_sklearn():
from cudf import DataFrame as df
from cudf import Series as ss
import pandas as pd
np.random.seed(1)
X = pd.DataFrame(np.random.randn(50, 10))
y = pd.DataFrame((np.random.randn(50) > 0).astype(np.int8))
weights = np.random.random(50) + 1.0
cudf_weights = df.from_pandas(pd.DataFrame(weights))
base_margin = np.random.random(50)
cudf_base_margin = df.from_pandas(pd.DataFrame(base_margin))
X_cudf = df.from_pandas(X)
y_cudf = df.from_pandas(y)
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.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)
assert np.array_equal(np.unique(pred), np.array([0, 1]))
class IterForDMatrixTest(xgb.core.DataIter):
'''A data iterator for XGBoost DMatrix.

19
tests/python-gpu/test_from_cupy.py
View File

@@ -108,6 +108,25 @@ def _test_cupy_metainfo(DMatrixT):
dmat_cupy.get_uint_info('group_ptr'))
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_sklearn())
def test_cupy_training_with_sklearn():
import cupy as cp
np.random.seed(1)
cp.random.seed(1)
X = cp.random.randn(50, 10, dtype='float32')
y = (cp.random.randn(50, dtype='float32') > 0).astype('int8')
weights = np.random.random(50) + 1
cupy_weights = cp.array(weights)
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.fit(X, y, sample_weight=cupy_weights, base_margin=cupy_base_margin, eval_set=[(X, y)])
pred = clf.predict(X)
assert np.array_equal(np.unique(pred), np.array([0, 1]))
class TestFromCupy:
'''Tests for constructing DMatrix from data structure conforming Apache
Arrow specification.'''

26
tests/python/test_with_sklearn.py
View File

@@ -706,19 +706,17 @@ def save_load_model(model_path):
from sklearn.datasets import load_digits
from sklearn.model_selection import KFold
digits = load_digits(2)
digits = load_digits(n_class=2)
y = digits['target']
X = digits['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X, y):
xgb_model = xgb.XGBClassifier().fit(X[train_index], y[train_index])
xgb_model = xgb.XGBClassifier(use_label_encoder=False).fit(X[train_index], y[train_index])
xgb_model.save_model(model_path)
xgb_model = xgb.XGBClassifier()
xgb_model = xgb.XGBClassifier(use_label_encoder=False)
xgb_model.load_model(model_path)
assert isinstance(xgb_model.classes_, np.ndarray)
assert isinstance(xgb_model._Booster, xgb.Booster)
assert isinstance(xgb_model._le, XGBoostLabelEncoder)
assert isinstance(xgb_model._le.classes_, np.ndarray)
preds = xgb_model.predict(X[test_index])
labels = y[test_index]
err = sum(1 for i in range(len(preds))
@@ -750,7 +748,7 @@ def test_save_load_model():
from sklearn.datasets import load_digits
with TemporaryDirectory() as tempdir:
model_path = os.path.join(tempdir, 'digits.model.json')
digits = load_digits(2)
digits = load_digits(n_class=2)
y = digits['target']
X = digits['data']
booster = xgb.train({'tree_method': 'hist',
@@ -761,7 +759,7 @@ def test_save_load_model():
booster.save_model(model_path)
cls = xgb.XGBClassifier()
cls.load_model(model_path)
predt_1 = cls.predict(X)
predt_1 = cls.predict_proba(X)[:, 1]
assert np.allclose(predt_0, predt_1)
cls = xgb.XGBModel()
@@ -778,10 +776,10 @@ def test_RFECV():
# Regression
X, y = load_boston(return_X_y=True)
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10,
objective='reg:squarederror',
random_state=0, verbosity=0)
bst = xgb.XGBRegressor(booster='gblinear', learning_rate=0.1,
n_estimators=10,
objective='reg:squarederror',
random_state=0, verbosity=0)
rfecv = RFECV(
estimator=bst, step=1, cv=3, scoring='neg_mean_squared_error')
rfecv.fit(X, y)
@@ -791,7 +789,7 @@ def test_RFECV():
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10,
objective='binary:logistic',
random_state=0, verbosity=0)
random_state=0, verbosity=0, use_label_encoder=False)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='roc_auc')
rfecv.fit(X, y)
@@ -802,7 +800,7 @@ 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)
scale_pos_weight=0.5, verbosity=0, use_label_encoder=False)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='neg_log_loss')
rfecv.fit(X, y)
@@ -811,7 +809,7 @@ def test_RFECV():
rfecv = RFECV(estimator=reg)
rfecv.fit(X, y)
cls = xgb.XGBClassifier()
cls = xgb.XGBClassifier(use_label_encoder=False)
rfecv = RFECV(estimator=cls, step=1, cv=3,
scoring='neg_mean_squared_error')
rfecv.fit(X, y)