问题::怎么查看网格搜索中找到的最优的参数
解答:
代码:GS.best_params_ 执行结果就是最优参数组合Xtrain,Xtest,Ytrain,Ytest = train_test_split(X,Y,test_size = 0.3
,random_state=420
) ##切分数据集
std = StandardScaler().fit(Xtrain) ##对数据集做标准化
Xtrain_ = std.transform(Xtrain)
Xtest_ = std.transform(Xtest)
from sklearn.model_selection import GridSearchCV ##导入网格搜索
p = {'penalty' : ['l1', 'l2'],
'C' : np.linspace(0.05, 5, 100) ##建立参数字典
}
model = LogisticRegression(max_iter = 1000, solver = 'liblinear') ##使用逻辑回归模型
GS = GridSearchCV(model, p, cv = 5)
GS.fit(Xtrain_, Ytrain) ##实例化网格搜索