Skip to content
Switch branches/tags
Go to file
7 contributors

Users who have contributed to this file

@tqchen @trivialfis @bobonovski @nscozzaro @mnogu @LevineHuang @jseabold
63 lines (57 sloc) 2.31 KB
import os
import numpy as np
import xgboost as xgb
# load data in do training
CURRENT_DIR = os.path.dirname(__file__)
dtrain = xgb.DMatrix(os.path.join(CURRENT_DIR, '../data/agaricus.txt.train'))
param = {'max_depth':2, 'eta':1, 'objective':'binary:logistic'}
num_round = 2
print('running cross validation')
# do cross validation, this will print result out as
# [iteration] metric_name:mean_value+std_value
# std_value is standard deviation of the metric, dtrain, num_round, nfold=5,
metrics={'error'}, seed=0,
print('running cross validation, disable standard deviation display')
# do cross validation, this will print result out as
# [iteration] metric_name:mean_value
res =, dtrain, num_boost_round=10, nfold=5,
metrics={'error'}, seed=0,
print('running cross validation, with preprocessing function')
# define the preprocessing function
# used to return the preprocessed training, test data, and parameter
# we can use this to do weight rescale, etc.
# as a example, we try to set scale_pos_weight
def fpreproc(dtrain, dtest, param):
label = dtrain.get_label()
ratio = float(np.sum(label == 0)) / np.sum(label == 1)
param['scale_pos_weight'] = ratio
return (dtrain, dtest, param)
# do cross validation, for each fold
# the dtrain, dtest, param will be passed into fpreproc
# then the return value of fpreproc will be used to generate
# results of that fold, dtrain, num_round, nfold=5,
metrics={'auc'}, seed=0, fpreproc=fpreproc)
# you can also do cross validation with customized loss function
# See
print('running cross validation, with customized loss function')
def logregobj(preds, dtrain):
labels = dtrain.get_label()
preds = 1.0 / (1.0 + np.exp(-preds))
grad = preds - labels
hess = preds * (1.0 - preds)
return grad, hess
def evalerror(preds, dtrain):
labels = dtrain.get_label()
return 'error', float(sum(labels != (preds > 0.0))) / len(labels)
param = {'max_depth':2, 'eta':1}
# train with customized objective, dtrain, num_round, nfold=5, seed=0,
obj=logregobj, feval=evalerror)