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

enable xgb_model in scklearn XGBClassifier and test. (#4092)

Browse Source 
* Enable xgb_model parameter in XGClassifier scikit-learn API

https://github.com/dmlc/xgboost/issues/3049

* add test_XGBClassifier_resume():

test for xgb_model parameter in XGBClassifier API.

* Update test_with_sklearn.py

* Fix lint
This commit is contained in:
tmitanitky 2019-02-01 04:29:19 +09:00 committed by Philip Hyunsu Cho
parent 0d0ce32908
commit 59f868bc60
2 changed files with 40 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
python-package/xgboost/sklearn.py
View File

@ -709,7 +709,7 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
evals=evals,
early_stopping_rounds=early_stopping_rounds,
evals_result=evals_result, obj=obj, feval=feval,
verbose_eval=verbose, xgb_model=None,
verbose_eval=verbose, xgb_model=xgb_model,
callbacks=callbacks)
self.objective = xgb_options["objective"]

39
tests/python/test_with_sklearn.py
View File

@ -609,3 +609,42 @@ def test_RFECV():
scale_pos_weight=0.5, silent=True)
rfecv = RFECV(estimator=bst, step=1, cv=3, scoring='neg_log_loss')
rfecv.fit(X, y)
def test_XGBClassifier_resume():
from sklearn.datasets import load_breast_cancer
from sklearn.metrics import log_loss
with TemporaryDirectory() as tempdir:
model1_path = os.path.join(tempdir, 'test_XGBClassifier.model')
model1_booster_path = os.path.join(tempdir, 'test_XGBClassifier.booster')
X, Y = load_breast_cancer(return_X_y=True)
model1 = xgb.XGBClassifier(learning_rate=0.3, seed=0, n_estimators=8)
model1.fit(X, Y)
pred1 = model1.predict(X)
log_loss1 = log_loss(pred1, Y)
# file name of stored xgb model
model1.save_model(model1_path)
model2 = xgb.XGBClassifier(learning_rate=0.3, seed=0, n_estimators=8)
model2.fit(X, Y, xgb_model=model1_path)
pred2 = model2.predict(X)
log_loss2 = log_loss(pred2, Y)
assert np.any(pred1 != pred2)
assert log_loss1 > log_loss2
# file name of 'Booster' instance Xgb model
model1.get_booster().save_model(model1_booster_path)
model2 = xgb.XGBClassifier(learning_rate=0.3, seed=0, n_estimators=8)
model2.fit(X, Y, xgb_model=model1_booster_path)
pred2 = model2.predict(X)
log_loss2 = log_loss(pred2, Y)
assert np.any(pred1 != pred2)
assert log_loss1 > log_loss2