机器学习kNN

from numpy import *
import operator

def createDataSet():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]])
    labels = ['A', 'A', 'B', 'B']
    return group, labels

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

if __name__=="__main__":
    group, labels = createDataSet()
    res = classify0([0,0], group, labels, 3)
    print res

kNN算法，找出距离最近的k个，label出现次数最多的
1. 需要手工标注部分数据，表明数据集是哪些分类

2. 计算(x1, x2, ...xn)到每个点的距离， 找出距离最近的， 距离最近的分类为计算点的分类