问题:运行gridsearchcv时似乎存在内存泄漏问题。当我使用1或32个并发工作器(n_jobs=-1)运行时会出现这种情况。之前在ubuntu 16.04上多次运行没有任何问题,但最近升级到18.04并进行了内存升级。
import os
import pickle
from xgboost import XGBClassifier
from sklearn.model_selection import GridSearchCV,StratifiedKFold,train_test_split
from sklearn.calibration import CalibratedClassifierCV
from sklearn.metrics import make_scorer,log_loss
from horsebet import performance
scorer = make_scorer(log_loss,greater_is_better=True)
kfold = StratifiedKFold(n_splits=3)
# import and split data
input_vectors = pickle.load(open(os.path.join('horsebet','data','x_normalized'),'rb'))
output_vector = pickle.load(open(os.path.join('horsebet','data','y'),'rb')).ravel()
x_train,x_test,y_train,y_test = train_test_split(input_vectors,output_vector,test_size=0.2)
# XGB
model = XGBClassifier()
param = {
'booster':['gbtree'],
'tree_method':['hist'],
'objective':['binary:logistic'],
'n_estimators':[100,500],
'min_child_weight': [.8,1],
'gamma': [1,3],
'subsample': [0.1,.4,1.0],
'colsample_bytree': [1.0],
'max_depth': [10,20],
}
jobs = 8
model = GridSearchCV(model,param_grid=param,cv=kfold,scoring=scorer,pre_dispatch=jobs*2,n_jobs=jobs,verbose=5).fit(x_train,y_train)
返回: UserWarning: 当一些工作被分配给执行器时,其中一个工作者停止了。这可能是由于工作者超时时间过短或内存泄漏引起的。 "timeout or by a memory leak.", UserWarning
或者
TerminatedWorkerError:由执行器管理的一个工作进程意外终止。这可能是由于调用函数时发生段错误或由于过度使用内存而导致操作系统杀死工作者。工作者的退出代码为{SIGKILL(-9)}