XGBoost XGBClassifier Defaults in Python

Question

I am attempting to use XGBoosts classifier to classify some binary data. When I do the simplest thing and just use the defaults (as follows)

clf = xgb.XGBClassifier()
metLearn=CalibratedClassifierCV(clf, method='isotonic', cv=2)
metLearn.fit(train, trainTarget)
testPredictions = metLearn.predict(test)

I get reasonably good classification results.

My next step was to try tuning my parameters. Guessing from the parameters guide at... https://github.com/dmlc/xgboost/blob/master/doc/parameter.md I wanted to start from the default and work from there...

# setup parameters for xgboost
param = {}
param['booster'] = 'gbtree'
param['objective'] = 'binary:logistic'
param["eval_metric"] = "error"
param['eta'] = 0.3
param['gamma'] = 0
param['max_depth'] = 6
param['min_child_weight']=1
param['max_delta_step'] = 0
param['subsample']= 1
param['colsample_bytree']=1
param['silent'] = 1
param['seed'] = 0
param['base_score'] = 0.5

clf = xgb.XGBClassifier(params)
metLearn=CalibratedClassifierCV(clf, method='isotonic', cv=2)
metLearn.fit(train, trainTarget)
testPredictions = metLearn.predict(test)

The result is everything being predicted to be one of the conditions and not the other.

curiously if I set

params={}

which I expected to give me the same defaults as not feeding any parameters, I get the same thing happening

So does anyone know what the defaults for XGBclassifier is? so that I can start tuning?

This question encounters similar behavior but no answer given http://stackoverflow.com/questions/33470477/xgboost-predict-method-returns-the-same-predicted-value-for-all-rows — Chris Arthur, Jan 08 '16 at 14:18

David · Accepted Answer · 2016-01-09T17:20:21.027

That isn't how you set parameters in xgboost. You would either want to pass your param grid into your training function, such as xgboost's train or sklearn's GridSearchCV, or you would want to use your XGBClassifier's set_params method. Another thing to note is that if you're using xgboost's wrapper to sklearn (ie: the XGBClassifier() or XGBRegressor() classes) then the paramater names used are the same ones used in sklearn's own GBM class (ex: eta --> learning_rate). I'm not seeing where the exact documentation for the sklearn wrapper is hidden, but the code for those classes is here: https://github.com/dmlc/xgboost/blob/master/python-package/xgboost/sklearn.py

For your reference here is how you would set the model object parameters directly.

>>> grid = {'max_depth':10}
>>> 
>>> clf = XGBClassifier()
>>> clf.max_depth
3
>>> clf.set_params(**grid)
XGBClassifier(base_score=0.5, colsample_bylevel=1, colsample_bytree=1,
       gamma=0, learning_rate=0.1, max_delta_step=0, max_depth=10,
       min_child_weight=1, missing=None, n_estimators=100, nthread=-1,
       objective='binary:logistic', reg_alpha=0, reg_lambda=1,
       scale_pos_weight=1, seed=0, silent=True, subsample=1)
>>> clf.max_depth
10

EDIT: I suppose you can set parameters on model creation, it just isn't super typical to do so since most people grid search in some means. However if you do so you would need to either list them as full params or use **kwargs. For example:

>>> XGBClassifier(max_depth=10)
XGBClassifier(base_score=0.5, colsample_bylevel=1, colsample_bytree=1,
       gamma=0, learning_rate=0.1, max_delta_step=0, max_depth=10,
       min_child_weight=1, missing=None, n_estimators=100, nthread=-1,
       objective='binary:logistic', reg_alpha=0, reg_lambda=1,
       scale_pos_weight=1, seed=0, silent=True, subsample=1)
>>> XGBClassifier(**grid)
XGBClassifier(base_score=0.5, colsample_bylevel=1, colsample_bytree=1,
       gamma=0, learning_rate=0.1, max_delta_step=0, max_depth=10,
       min_child_weight=1, missing=None, n_estimators=100, nthread=-1,
       objective='binary:logistic', reg_alpha=0, reg_lambda=1,
       scale_pos_weight=1, seed=0, silent=True, subsample=1)

Using a dictionary as input without **kwargs will set that parameter to literally be your dictionary:

>>> XGBClassifier(grid)
XGBClassifier(base_score=0.5, colsample_bylevel=1, colsample_bytree=1,
       gamma=0, learning_rate=0.1, max_delta_step=0,
       max_depth={'max_depth': 10}, min_child_weight=1, missing=None,
       n_estimators=100, nthread=-1, objective='binary:logistic',
       reg_alpha=0, reg_lambda=1, scale_pos_weight=1, seed=0, silent=True,
       subsample=1)

As much as I wish it were true, you can't pass a parameter grid into xgboost's train function - parameter dictionary values cannot be lists — Edi Bice, Apr 20 '16 at 19:47

score 42 · Answer 2 · answered Sep 13 '18 at 20:37

42

The defaults for XGBClassifier are:

max_depth=3
learning_rate=0.1
n_estimators=100
silent=True
objective='binary:logistic'
booster='gbtree'
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

Link to XGBClassifier documentation with class defaults: https://xgboost.readthedocs.io/en/latest/python/python_api.html#xgboost.XGBClassifier

answered Sep 13 '18 at 20:37

Jake Zidow

513
1
5
9

5

Default parameters are not referenced for the sklearn API's XGBClassifier on the official documentation (they are for the official default xgboost API but there is no guarantee it is the same default parameters used by sklearn, especially when xgboost states some behaviors are different when using it). Anyone has any idea where it might be found now ? It's really not inviting to have to dive into the source code in order to know what defaut parameters might be. – Pythalex Feb 18 '20 at 14:08
Unfortunately these are the closest I have to official docs but they have been reliable for defining defaults when I have needed it – Jake Zidow Mar 16 '20 at 16:26

score 2 · Answer 3 · edited Apr 21 '18 at 20:39

2

For starters, looks like you're missing an s for your variable param.

You wrote param at the top:

param = {}
param['booster'] = 'gbtree'
param['objective'] = 'binary:logistic'
  .
  .
  .

...but use params farther down, when training the model:

clf = xgb.XGBClassifier(params)  <-- different variable!

Was that just a typo in your example?

edited Apr 21 '18 at 20:39

Scott Smith

3,900
2
31
63

answered Jan 15 '18 at 06:57

luoshao23

391
2
14

score 2 · Answer 4 · answered May 21 '21 at 19:32

You're almost there! You just forgot to unpack the params dictionary (the ** operator). Instead of this (which passes a single dictionary as the first positional arg):

clf = xgb.XGBClassifier(params)

You should have done this (which makes it so that the keys in the dictionary are each passed as keyword args):

clf = xgb.XGBClassifier(**params)

score 2 · Answer 5 · answered Jan 26 '22 at 23:41

(Updated) Default values are visible once you fit the out-of-box classifier model:

XGBClassifier(base_score=0.5, booster='gbtree', colsample_bylevel=1,
              colsample_bynode=1, colsample_bytree=1, gamma=0, gpu_id=-1,
              importance_type='gain', interaction_constraints='',
              learning_rate=0.300000012, max_delta_step=0, max_depth=6,
              min_child_weight=1, missing=nan, monotone_constraints='()',
              n_estimators=100, n_jobs=12, num_parallel_tree=1,
              objective='multi:softprob', random_state=0, reg_alpha=0,
              reg_lambda=1, scale_pos_weight=None, subsample=1,
              tree_method='exact', use_label_encoder=False,
              validate_parameters=1, verbosity=None)

Details are available here: https://xgboost.readthedocs.io/en/latest/parameter.html

XGBoost XGBClassifier Defaults in Python

5 Answers5