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

Fix skl nan tag. (#5538)

Browse Source
This commit is contained in:
Jiaming Yuan 2020-04-18 06:52:17 +08:00 committed by GitHub
parent cfee9fae91
commit c69a19e2b1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 25 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Jenkinsfile-win64
View File

@ -112,6 +112,10 @@ def TestWin64CPU() {
bat """ bat """
conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i" conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
""" """
echo "Installing Python dependencies..."
bat """
conda activate && conda upgrade scikit-learn pandas numpy
"""
echo "Running Python tests..." echo "Running Python tests..."
bat "conda activate && python -m pytest -v -s --fulltrace tests\\python" bat "conda activate && python -m pytest -v -s --fulltrace tests\\python"
bat "conda activate && python -m pip uninstall -y xgboost" bat "conda activate && python -m pip uninstall -y xgboost"
@ -133,6 +137,10 @@ def TestWin64GPU(args) {
bat """ bat """
conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i" conda activate && for /R %%i in (python-package\\dist\\*.whl) DO python -m pip install "%%i"
""" """
echo "Installing Python dependencies..."
bat """
conda activate && conda upgrade scikit-learn pandas numpy
"""
echo "Running Python tests..." echo "Running Python tests..."
bat """ bat """
conda activate && python -m pytest -v -s --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu conda activate && python -m pytest -v -s --fulltrace -m "(not slow) and (not mgpu)" tests\\python-gpu

4
python-package/xgboost/sklearn.py
View File

@ -244,6 +244,10 @@ class XGBModel(XGBModelBase):
self.gpu_id = gpu_id self.gpu_id = gpu_id
self.validate_parameters = validate_parameters self.validate_parameters = validate_parameters
def _more_tags(self):
'''Tags used for scikit-learn data validation.'''
return {'allow_nan': True}
def get_booster(self): def get_booster(self):
"""Get the underlying xgboost Booster of this model. """Get the underlying xgboost Booster of this model.

16
tests/python/test_with_sklearn.py
View File

@ -719,7 +719,7 @@ def test_RFECV():
# Regression # Regression
X, y = load_boston(return_X_y=True) X, y = load_boston(return_X_y=True)
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1, bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10, n_jobs=1, n_estimators=10,
objective='reg:squarederror', objective='reg:squarederror',
random_state=0, verbosity=0) random_state=0, verbosity=0)
rfecv = RFECV( rfecv = RFECV(
@ -729,7 +729,7 @@ def test_RFECV():
# Binary classification # Binary classification
X, y = load_breast_cancer(return_X_y=True) X, y = load_breast_cancer(return_X_y=True)
bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1, bst = xgb.XGBClassifier(booster='gblinear', learning_rate=0.1,
n_estimators=10, n_jobs=1, n_estimators=10,
objective='binary:logistic', objective='binary:logistic',
random_state=0, verbosity=0) random_state=0, verbosity=0)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='roc_auc') rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='roc_auc')
@ -739,13 +739,23 @@ def test_RFECV():
X, y = load_iris(return_X_y=True) X, y = load_iris(return_X_y=True)
bst = xgb.XGBClassifier(base_score=0.4, booster='gblinear', bst = xgb.XGBClassifier(base_score=0.4, booster='gblinear',
learning_rate=0.1, learning_rate=0.1,
n_estimators=10, n_jobs=1, n_estimators=10,
objective='multi:softprob', objective='multi:softprob',
random_state=0, reg_alpha=0.001, reg_lambda=0.01, 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)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='neg_log_loss') rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='neg_log_loss')
rfecv.fit(X, y) rfecv.fit(X, y)
X[0:4, :] = np.nan # verify scikit_learn doesn't throw with nan
reg = xgb.XGBRegressor()
rfecv = RFECV(estimator=reg)
rfecv.fit(X, y)
cls = xgb.XGBClassifier()
rfecv = RFECV(estimator=cls, step=1, cv=3,
scoring='neg_mean_squared_error')
rfecv.fit(X, y)
def test_XGBClassifier_resume(): def test_XGBClassifier_resume():
from sklearn.datasets import load_breast_cancer from sklearn.datasets import load_breast_cancer