机器学习python kNN算法

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):
    #inX为输入向量，dataSet为训练向量，labels为训练的标签向量，k为最近邻居的数目
    dataSetSize = dataSet.shape[0]
    diffMat = tile(inX,(dataSetSize,1)) - dataSet  #将输入向量拓展为训练向量规模一样
    pingfang = diffMat ** 2
    d_pingfang = pingfang.sum(axis=1) #逐行操作
    d = d_pingfang ** 0.5
    sortedDistIndicies = d.argsort()
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
    sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
    return sortedClassCount[0][0]

#将文本数据转化为Numpy的解析函数
def file2matrix(filename):
    fr = open(filename)
    arrayOLines = fr.readlines()
    numbersOfLines = len(arrayOLines)
    returnMat = zeros((numbersOfLines,3))
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

#归一化特征值
def autoNorm(dataSet):
    minVals = dataSet.min(0) #按照列寻找特征值
    maxVals = dataSet.max(0)
    ranges = maxVals - minVals
    m = dataSet.shape[0]
    normDataSet = zeros(shape(dataSet))
    normDataSet = dataSet - tile(minVals,(m,1))
    normDataSet = normDataSet / tile(ranges,(m,1))
    return normDataSet,ranges,minVals

def datingClassTest():
    hoRatio = 0.1
    datingDataMat,datingLabels = file2matrix('datingTestSet2.txt')       #load data setfrom file
    normMat, ranges, minVals = autoNorm(datingDataMat)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult = classify0(normMat[i,:],normMat[:m-numTestVecs,:],datingLabels[:m-numTestVecs],3)
        print ("the classifier came back with: %d, the real answer is: %d" % (classifierResult, datingLabels[i]))
        if (classifierResult != datingLabels[i]):
            errorCount += 1.0
    print ("the total error rate is: %f" % (errorCount/float(numTestVecs)))
    print(errorCount)