python 中bayes模型超参数并行网格搜索 程序分析

from sklearn.datasets import fetch_20newsgroups

import numpy as np

news = fetch_20newsgroups(subset='all')



from sklearn.cross_validation import train_test_split

X_train,X_test,y_train,y_test = train_test_split(news.data[:3000],
                                                 news.target[:3000],test_size=0.25,random_state=33)

from sklearn.svm import SVC

from sklearn.feature_extraction.text  import  TfidfVectorizer

#导入 pipeline

from sklearn.pipeline import Pipeline

#使用pipeline 简化系统搭建流程，将文本抽取与分类器模型串联起来

clf = Pipeline([('vect',TfidfVectorizer(stop_words='english',analyzer='word')),('svc',SVC())])


parameters = {'svc__gamma': np.logspace(-2, 1, 4), 'svc__C': np.logspace(-1, 1, 3)}  

#从sklearn.grid_search 中导入网络搜索模块GridSearchCV

from sklearn.grid_search import GridSearchCV

if __name__ == '__main__':
#将12组参数组合以及初始化的pipline包括3折交叉验证的要求全部告知GridSearchCV  务必注意refit=true这样一个设定

  gs = GridSearchCV(clf,parameters,verbose=2,refit = True,cv=3,n_jobs = -1)
#执行单线程网搜索

  gs.fit(X_train,y_train)
 # %time_=gs.best_params_,gs.best_score_

gs.best_params_,gs.best_score_

print(gs.score(X_test,y_test))

程序运行出现如下错误:

  File "D:\Python35\demo\gridsearch_model_parallel.py", line 42
    %time_ =gs.best_params_,gs.best_score_
    ^
SyntaxError: invalid syntax

去掉%time_符号，程序正常运行