模型训练中巧用CV

灰太狼 2023-06-23 14:21 22阅读 0赞

1.分层KFold

import numpy as np
    from sklearn.model_selection import StratifiedKFold
    X=np.array([[1,2,3,4],
                [11,12,13,14],
                [21,22,23,24],
                [31,32,33,34],
                [41,42,43,44]
                ])
    y=np.array([0,1,1,0,0])
    folder=StratifiedKFold(n_splits=2,shuffle=False,random_state=1000)
    
    for train_index,test_index in folder.split(X=X,y=y):
        print('训练集索引：',train_index,'测试集索引：',test_index)
        print('train:',X[train_index],'---',y[train_index])
        print('test:',X[test_index],'---',y[test_index])
    print('*'*30)
    
    
    训练集索引： [2 4] 测试集索引： [0 1 3]
    train: [[21 22 23 24]
     [41 42 43 44]] --- [1 0]
    test: [[ 1  2  3  4]
     [11 12 13 14]
     [31 32 33 34]] --- [0 1 0]
    训练集索引： [0 1 3] 测试集索引： [2 4]
    train: [[ 1  2  3  4]
     [11 12 13 14]
     [31 32 33 34]] --- [0 1 0]
    test: [[21 22 23 24]
     [41 42 43 44]] --- [1 0]

2.KFold

from sklearn.model_selection import KFold
    X=np.array([[1,2,3,4],
                [11,12,13,14],
                [21,22,23,24],
                [31,32,33,34],
                [41,42,43,44]
                ])
    y=np.array([0,1,1,0,0])
    folder=KFold(n_splits=2,shuffle=False,random_state=100)
    for train_index,test_index in folder.split(X=X,y=y):
        print('训练集索引：',train_index,'测试集索引：',test_index)
        print('train：',X[train_index],'>>>',y[train_index])
        print('test：',X[test_index],'>>>',y[test_index])
    
    训练集索引： [3 4] 测试集索引： [0 1 2]
    train： [[31 32 33 34]
     [41 42 43 44]] >>> [0 0]
    test： [[ 1  2  3  4]
     [11 12 13 14]
     [21 22 23 24]] >>> [0 1 1]
    训练集索引： [0 1 2] 测试集索引： [3 4]
    train： [[ 1  2  3  4]
     [11 12 13 14]
     [21 22 23 24]] >>> [0 1 1]
    test： [[31 32 33 34]
     [41 42 43 44]] >>> [0 0]

3. 使用Keras进行10折交叉验证

for train,test in kfold.split(train_data_X,train_data_Y):
        model = getModel()
        t1,t2,t3,t4 = np.array(train_data_X)[train], np.array(train_data_X)[test],
    np.array(train_data_Y)[train],np.array(train_data_Y)[test]
        train_D = data_generator(t1.tolist(), t3.tolist())
        dev_D = data_generator(t2.tolist(), t4.tolist())
        evaluator = Evaluate()
        model.fit_generator(train_D.__iter__(),
                            steps_per_epoch=len(train_D),
                            epochs=3,
                            callbacks=[evaluator,lrate]
                            )
        del model
    
    K.clear_session()