1、KNN算法是分类算法，还是聚类算法？

2、K的取值是不是越大越好？

3、KNN算法怎么进行代码编程？

import numpy as np

from sklearn import datasets

from sklearn.model_selection import train_test_split   #数据切分

from sklearn.metrics import classification_report,confusion_matrix   #查准率、查全率、混淆矩阵

import random

#载入数据

iris = datasets.load_iris()

x_train,x_test,y_train,y_test = train_test_split(iris,iris.target,test_size = 0.2)

#由于鸢尾花数据都是按类别排列好了的，现在需要打乱数据

#相当于x_train,x_test,y_train,y_test = train_test_split(iris,iris.target,test_size = 0.2)  实现的功能

data_size = iris.data.shape[0]  

index = [i for i in np.arange(data_size)]

random.shuffle(index)

iris.data = iris.data[index]

iris.target = iris.target[index]

#切分数据集

test_size = int(data_size * 0.2)

x_train = iris.data[test_size:]

x_test = iris.data[:test_size]

y_train = iris.target[test_size:]

y_test = iris.target[:test_size]

prediction = []

#调用knn(x_test,x_data,y_data,k)函数

for i in range(x_test.shape[0]):

    prediction.append(knn(x_test[i],x_train,y_train,5))

print(classification_report(y_test,prediction))

print(confusion_matrix(y_test,prediction))