sklearn中交叉验证的两种方式

1、cross_val_score

from sklearn.model_selection import cross_val_score
knn_clf = KNeighborsClassifier()
# 返回的是一个数组，有五个元素，说明cross_val_score方法默认将我们的数据集分成了五份
# 这五份数据集进行交叉验证后产生了这五个结果
# cv默认为5，可以修改改参数，修改修改不同分数的数据集
cross_val_score(knn_clf,X_train,y_train,cv=5)

# 使用交叉验证的方式来进行调参的过程
best_score,best_k,best_p = 0,0,0
# k为k近邻中的寻找k个最近元素
for k in range(2,11):
    # p为明科夫斯基距离的p
    for p in range(1,6):
        knn_clf = KNeighborsClassifier(weights='distance',n_neighbors=k,p=p)
        scores = cross_val_score(knn_clf,X_train,y_train)
        score = np.mean(scores)
        if score > best_score:
            best_score,best_k,best_p = score,k,p
print("Best_score = ",best_score)
print("Best_k = ",best_k)
print("Best_p = ",best_p)

2、网格搜索GridSearchCV

from sklearn.model_selection import GridSearchCV

param_grid = [
    {
        'weights':['distance'],
        'n_neighbors':[i for i in range(2,11)],
        'p':[i for i in range(1,6)]
    }
]

grid_search = GridSearchCV(knn_clf,param_grid,verbose=1，cv=5)
grid_search.fit(X_train,y_train)

#最好的分数
grid_search.best_score_
#最好的参数
grid_search.best_params_
#最好的模型
best_knn_clf = grid_search.best_estimator_

实验结果表明，两种方法得到的结果一致。