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

Sklearn kwargs (#2338)

Browse Source 
* Added kwargs support for Sklearn API

* Updated NEWS and CONTRIBUTORS

* Fixed CONTRIBUTORS.md

* Added clarification of **kwargs and test for proper usage

* Fixed lint error

* Fixed more lint errors and clf assigned but never used

* Fixed more lint errors

* Fixed more lint errors

* Fixed issue with changes from different branch bleeding over

* Fixed issue with changes from other branch bleeding over

* Added note that kwargs may not be compatible with Sklearn

* Fixed linting on kwargs note
This commit is contained in:
gaw89
2017-05-23 22:47:53 -04:00
committed by Yuan (Terry) Tang
parent 6cea1e3fb7
commit 0f3a404d91
4 changed files with 38 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
python-package/xgboost/sklearn.py
View File

@@ -101,6 +101,14 @@ class XGBModel(XGBModelBase):
missing : float, optional
Value in the data which needs to be present as a missing value. If
None, defaults to np.nan.
**kwargs : dict, optional
Keyword arguments for XGBoost Booster object. Full documentation of parameters can
be found here: https://github.com/dmlc/xgboost/blob/master/doc/parameter.md.
Attempting to set a parameter via the constructor args and **kwargs dict simultaneously
will result in a TypeError.
Note:
**kwargs is unsupported by Sklearn. We do not guarantee that parameters passed via
this argument will interact properly with Sklearn.
Note
----
@@ -124,7 +132,7 @@ class XGBModel(XGBModelBase):
n_jobs=1, nthread=None, gamma=0, min_child_weight=1, max_delta_step=0,
subsample=1, colsample_bytree=1, colsample_bylevel=1,
reg_alpha=0, reg_lambda=1, scale_pos_weight=1,
base_score=0.5, random_state=0, seed=None, missing=None):
base_score=0.5, random_state=0, seed=None, missing=None, **kwargs):
if not SKLEARN_INSTALLED:
raise XGBoostError('sklearn needs to be installed in order to use this module')
self.max_depth = max_depth
@@ -133,7 +141,6 @@ class XGBModel(XGBModelBase):
self.silent = silent
self.objective = objective
self.booster = booster
self.nthread = nthread
self.gamma = gamma
self.min_child_weight = min_child_weight
@@ -146,6 +153,7 @@ class XGBModel(XGBModelBase):
self.scale_pos_weight = scale_pos_weight
self.base_score = base_score
self.missing = missing if missing is not None else np.nan
self.kwargs = kwargs
self._Booster = None
if seed:
warnings.warn('The seed parameter is deprecated as of version .6.'
@@ -192,6 +200,8 @@ class XGBModel(XGBModelBase):
def get_params(self, deep=False):
"""Get parameter.s"""
params = super(XGBModel, self).get_params(deep=deep)
if isinstance(self.kwargs, dict): # if kwargs is a dict, update params accordingly
params.update(self.kwargs)
if params['missing'] is np.nan:
params['missing'] = None # sklearn doesn't handle nan. see #4725
if not params.get('eval_metric', True):
@@ -388,7 +398,7 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
n_jobs=1, nthread=None, gamma=0, min_child_weight=1,
max_delta_step=0, subsample=1, colsample_bytree=1, colsample_bylevel=1,
reg_alpha=0, reg_lambda=1, scale_pos_weight=1,
base_score=0.5, random_state=0, seed=None, missing=None):
base_score=0.5, random_state=0, seed=None, missing=None, **kwargs):
super(XGBClassifier, self).__init__(max_depth, learning_rate,
n_estimators, silent, objective, booster,
n_jobs, nthread, gamma, min_child_weight,
@@ -396,7 +406,7 @@ class XGBClassifier(XGBModel, XGBClassifierBase):
colsample_bytree, colsample_bylevel,
reg_alpha, reg_lambda,
scale_pos_weight, base_score,
random_state, seed, missing)
random_state, seed, missing, **kwargs)
def fit(self, X, y, sample_weight=None, eval_set=None, eval_metric=None,
early_stopping_rounds=None, verbose=True):