import numpy as np
import xgboost as xgb

dtrain = xgb.DMatrix('./demo/data/agaricus.txt.train')

dtest = xgb.DMatrix('./demo/data/agaricus.txt.test')

watchlist = [(dtest, 'eval'), (dtrain, 'train')]

print('Start running example to start from a initial prediction')

Start running example to start from a initial prediction

param = {'max_depth': 2, 'eta': 1, 'silent': 1, 'objective': 'binary:logistic'}

bst = xgb.train(param, dtrain, 1, watchlist)

[0]    eval-error:0.042831    train-error:0.046522

ptrain = bst.predict(dtrain, output_margin = True) # output_margin? margin value 是什么？

ptest = bst.predict(dtest, output_margin = True)

dtrain.set_base_margin(ptrain)

dtest.set_base_margin(ptest)

print('This is result of running from initial prediction')

This is result of running from initial prediction

bst = xgb.train(param, dtrain, 1, watchlist)

[0]    eval-error:0.021726    train-error:0.022263

从结果上来看，错误率似乎下降了。