将 XGBoost xgb.train 的输出保存为带有 python 日志记录的日志文件

Question

我试图通过 logging 将 XGBoost xgb.train 的输出保存为日志文件，但无法记录输出。我怎样才能记录下来？我试图参考现有的 Whosebug 问题，但这是不可能的。我希望你用一个具体的例子来展示它。

import sys
import logging

# ---------------------------------------------- #
# Some logging settings
# ---------------------------------------------- #

import xgboost as xgb

import numpy as np
from sklearn.model_selection import KFold
from sklearn.datasets import load_digits

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

# I want to record this output.
# Zeros and Ones from the Digits dataset: binary classification
# [0]   eval-error:0.011111 train-error:0.011111
# [1]   eval-error:0.011111 train-error:0.005556
# [0]   eval-error:0.016667 train-error:0.005556
# [1]   eval-error:0.005556 train-error:0

Answer 1

import sys
%logstart -o "test.log"
sys.stdout = open('test.log', 'a')

import xgboost as xgb

import numpy as np
from sklearn.model_selection import KFold
from sklearn.datasets import load_digits

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

这将开始保存文件 test.log 中的所有内容。输出和输入。

Answer 2

xgboost 将它们的日志直接打印到标准输出中，您无法更改该行为。但是 xgb.train 的 callbacks 参数能够记录结果与内部打印相同的时间。

以下代码是使用回调将 xgboost 日志记录到记录器中的示例。 log_evaluation() returns 从 xgboost 内部调用的回调函数，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)

将 XGBoost xgb.train 的输出保存为带有 python 日志记录的日志文件

Save the output of xgb.train of XGBoost as a log file with python logging

python

logging

xgboost