机器学习实战---KNN代码详解

from numpy import *
import operator

def classify0(inX, dataSet, labels, k):
    dataSetSize = dataSet.shape[0]
    print tile(inX, (dataSetSize, 1))  # generate array([[0,0],[0,0],[0,0],[0,0]])
    diffMat = tile(inX, (dataSetSize, 1)) - dataSet
    sqDiffMat = diffMat ** 2  # array calculate:(elements of array)^2
    sqDistances = sqDiffMat.sum(axis=1)
    distances = sqDistances ** 0.5
    sortedDistIndices = distances.argsort()
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndices[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1
    sortedClassCount  = sorted(classCount.iteritems(), key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

if __name__ == "__main__":
    group = array([[1.0,1.1],[1.0,1.0],[0,0],[0,0.1]])
    labels = ['A','A','B','B']
    print classify0([0,0], group, labels, 3)

二维数组，axis=0，按列求和，axis=1，按行求和

numpy的array中的sum():

https://blog.csdn.net/wangxiao7474/article/details/78867390

这里根据distance的内容升序排序，返回内容的索引

关于numpy的argsort()的用法：

https://blog.csdn.net/maoersong/article/details/21875705

# -*- coding: UTF-8 -*-