使用python日志记录将XGBoost的xgb.train的输出保存为日志文件
我试图通过使用python日志记录将XGBoost的xgb.train的输出保存为日志文件,python,logging,xgboost,Python,Logging,Xgboost,我试图通过logging将XGBoost的xgb.train的输出保存为日志文件,但无法记录输出。我怎样才能录下来?我试图提及现有的Stackoverflow问题,但这是不可能的。我想请你拿一个具体的样品给我看看 导入系统 导入日志记录 # ---------------------------------------------- # #一些日志设置 # ---------------------------------------------- # 将xgboost作为xgb导入 将nump
logging
将XGBoost的xgb.train
的输出保存为日志文件,但无法记录输出。我怎样才能录下来?我试图提及现有的Stackoverflow问题,但这是不可能的。我想请你拿一个具体的样品给我看看
导入系统
导入日志记录
# ---------------------------------------------- #
#一些日志设置
# ---------------------------------------------- #
将xgboost作为xgb导入
将numpy作为np导入
从sklearn.model_选择导入KFold
从sklearn.dataset导入load_数字
rng=np.random.RandomState(31337)
打印(“数字数据集中的零和一:二进制分类”)
位数=加载\位数(2)
y=数字['target']
X=数字[“数据”]
kf=KFold(n_splits=2,shuffle=True,random_state=rng)
对于列车索引,测试kf中的列车索引。拆分(X):
param={'max_depth':2,'eta':0.3,'silent':1,'objective':'binary:logistic'}
dtrain=xgb.DMatrix(X[列索引],y[列索引])
dtest=xgb.DMatrix(X[测试指数],y[测试指数])
#指定设置为监视性能的验证
观察列表=[(数据测试,'eval'),(数据训练,'train')]
轮数=2
bst=xgb.列车(参数、数据列车、轮数、值班表)
#我想记录这个输出。
#数字数据集中的0和1:二进制分类
#[0]评估错误:0.011111列车错误:0.011111
#[1]评估错误:0.011111列车错误:0.005556
#[0]评估错误:0.016667列车错误:0.005556
#[1]评估错误:0.005556列车错误:0
这将开始保存文件test.log中的所有内容。输出和输入。xgboost将其日志直接打印到标准输出中,您无法更改其行为。 但是
xgb.train的callbacks
参数能够记录与内部打印相同的时间结果
下面的代码是一个使用回调将xgboost日志记录到记录器中的示例。
log\u evaluation()
返回从xgboost internal调用的回调函数,您可以将回调函数添加到callbacks
from logging import getLogger, basicConfig, INFO
import numpy as np
import xgboost as xgb
from sklearn.datasets import load_digits
from sklearn.model_selection import KFold
# Some logging settings
basicConfig(level=INFO)
logger = getLogger(__name__)
def log_evaluation(period=1, show_stdv=True):
"""Create a callback that logs evaluation result with logger.
Parameters
----------
period : int
The period to log the evaluation results
show_stdv : bool, optional
Whether show stdv if provided
Returns
-------
callback : function
A callback that logs evaluation every period iterations into logger.
"""
def _fmt_metric(value, show_stdv=True):
"""format metric string"""
if len(value) == 2:
return '%s:%g' % (value[0], value[1])
elif len(value) == 3:
if show_stdv:
return '%s:%g+%g' % (value[0], value[1], value[2])
else:
return '%s:%g' % (value[0], value[1])
else:
raise ValueError("wrong metric value")
def callback(env):
if env.rank != 0 or len(env.evaluation_result_list) == 0 or period is False:
return
i = env.iteration
if i % period == 0 or i + 1 == env.begin_iteration or i + 1 == env.end_iteration:
msg = '\t'.join([_fmt_metric(x, show_stdv) for x in env.evaluation_result_list])
logger.info('[%d]\t%s\n' % (i, msg))
return callback
rng = np.random.RandomState(31337)
print("Zeros and Ones from the Digits dataset: binary classification")
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
param = {'max_depth': 2, 'eta': 0.3, 'silent': 1, 'objective': 'binary:logistic'}
dtrain = xgb.DMatrix(X[train_index], y[train_index])
dtest = xgb.DMatrix(X[test_index], y[test_index])
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
# add logger
callbacks = [log_evaluation(1, True)]
bst = xgb.train(param, dtrain, num_round, watchlist, callbacks=callbacks)
看看
from logging import getLogger, basicConfig, INFO
import numpy as np
import xgboost as xgb
from sklearn.datasets import load_digits
from sklearn.model_selection import KFold
# Some logging settings
basicConfig(level=INFO)
logger = getLogger(__name__)
def log_evaluation(period=1, show_stdv=True):
"""Create a callback that logs evaluation result with logger.
Parameters
----------
period : int
The period to log the evaluation results
show_stdv : bool, optional
Whether show stdv if provided
Returns
-------
callback : function
A callback that logs evaluation every period iterations into logger.
"""
def _fmt_metric(value, show_stdv=True):
"""format metric string"""
if len(value) == 2:
return '%s:%g' % (value[0], value[1])
elif len(value) == 3:
if show_stdv:
return '%s:%g+%g' % (value[0], value[1], value[2])
else:
return '%s:%g' % (value[0], value[1])
else:
raise ValueError("wrong metric value")
def callback(env):
if env.rank != 0 or len(env.evaluation_result_list) == 0 or period is False:
return
i = env.iteration
if i % period == 0 or i + 1 == env.begin_iteration or i + 1 == env.end_iteration:
msg = '\t'.join([_fmt_metric(x, show_stdv) for x in env.evaluation_result_list])
logger.info('[%d]\t%s\n' % (i, msg))
return callback
rng = np.random.RandomState(31337)
print("Zeros and Ones from the Digits dataset: binary classification")
digits = load_digits(2)
y = digits['target']
X = digits['data']
kf = KFold(n_splits=2, shuffle=True, random_state=rng)
for train_index, test_index in kf.split(X):
param = {'max_depth': 2, 'eta': 0.3, 'silent': 1, 'objective': 'binary:logistic'}
dtrain = xgb.DMatrix(X[train_index], y[train_index])
dtest = xgb.DMatrix(X[test_index], y[test_index])
# specify validations set to watch performance
watchlist = [(dtest, 'eval'), (dtrain, 'train')]
num_round = 2
# add logger
callbacks = [log_evaluation(1, True)]
bst = xgb.train(param, dtrain, num_round, watchlist, callbacks=callbacks)