在本文中，将选取正确率作为衡量标准，自行实现搜索最优超参数，而非直接调用sklearn中的GridSearchCV。

先简单介绍KNN中的三个超参数：

# n_neighbors：取邻近点的个数k。k取1-10测试
#weight：距离的权重；uniform：一致的权重；distance：距离的倒数作为权重
#p:闵可斯基距离的p值;闵可斯基距离公式： (∑|xi-yi|^p)^(1/p) (i=1,2,...n)。p=1:即欧式距离；p=2:即曼哈顿距离；p取1-6测试
#只有当weight=distance的时候，p值才有意义

if __name__ == '__main__':
    iris=datasets.load_iris()
    trainX, testX, trainY, testY = train_test_split(iris.data,iris.target)
    searchBestPar()

#寻找最优超参数:n_neighbors /weight/p
def searchBestPar():
    bestScore=0
    bestK=-1
    bestWeight=""

    # weight==uniform时
    for k in range(1,11):
        clf = KNeighborsClassifier(n_neighbors=k,weights="uniform")
        clf.fit(trainX,trainY)
        scor=clf.score(testX,testY)
        if scor > bestScore:
            bestScore=scor
            bestK=k
            bestWeight="uniform"

    # weight==distance时
    for k in range(1,10):
        for p in range(1,7):
            clf=KNeighborsClassifier(n_neighbors=k,weights="distance",p=p)
            clf.fit(trainX,trainY)
            scor = clf.score(testX, testY)
            if scor > bestScore:
                bestScore = scor
                bestK = k
                bestWeight = "distance"
                
    print("the best n_neighbors", bestK)
    print("the best weights", bestWeight)
    print("the best p", p)