机器学习实战（1） ——K-近邻算法（python实现）

  这是学习机器学习算法实战这本书时，写的代码实战。让自己对各个算法有更直观的了解，不能一直不写啊。不管简单还是不简单都亲自一行一行的敲一遍啊。

具体的源码和和数据链接：https://pan.baidu.com/s/1G2S2pb5gfBnxGNNTFgTkEA 密码：fov0

# -*- coding: utf-8 -*-
# author: Yufeng Song

from numpy import*
import operator
import matplotlib
import matplotlib.pyplot as plt
import os

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]
    diffMat = tile(inX,(dataSetSize,1))-dataSet
    sqDiffMat = diffMat**2

    sqDistance = sqDiffMat.sum(axis=1)#
    distances = sqDistance**0.5
    sortedDistIndices = distances.argsort()
    classCount={}
    for i in range(k):
        votelabel = labels[sortedDistIndices[i]]
        classCount[votelabel] = classCount.get(votelabel,0)+1
    #sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True)
    sortedClassCount = sorted(classCount.items(),key=lambda item:item[1],reverse=True)
    return sortedClassCount[0][0]

def file2matrix(filename):
    fr = open(filename,"r")
    arrayOfLines =fr.readlines()
    numberOfLines = len(arrayOfLines)
    # print(numberOfLines)
    # returnMat = zeros(numberOfLines,3)
    returnMat = zeros((numberOfLines,3))#里面有个小括号，别忘了啊
    # a=eye(3) 单位矩阵
    # print(a)
    # print(returnMat)
    classLabelVector = []
    index = 0
    for line in arrayOfLines:
        line = line.strip() #删除左右两边的空格指定空格，默认是空字符串啊，lstrip(),rstrip()
        listFromLine = line.split('\t')
        returnMat[index,:] = listFromLine[0:3]#他是个二维数组所以要加这个啊
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

# def file2matrix(filename):
#     fr = open(filename)
#     numberOfLines = len(fr.readlines())         #get the number of lines in the file
#     returnMat = zeros((numberOfLines,3))        #prepare matrix to return
#     classLabelVector = []                       #prepare labels return
#     fr = open(filename)
#     index = 0
#     for line in fr.readlines():
#         line = line.strip()
#         listFromLine = line.split('\t')
#         returnMat[index,:] = listFromLine[0:3]
#         classLabelVector.append(int(listFromLine[-1]))
#         index += 1
#     return returnMat,classLabelVector

def autoNorm(dataSet):
    minVals = dataSet.min(0)#选取列的最小值，而不是行的最小值
    maxVals = dataSet.max(0)
    ranges=maxVals-minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals,(m,1))
    normDataSet = normDataSet/tile(ranges,(m,1))
    return normDataSet,ranges,minVals

def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels=file2matrix('datingTestSet2.txt')
    normMat,ranges,minVals=autoNorm(datingDataMat)
    print(normMat.shape)#(1000,3)
    m = normMat.shape[0]
    numTestVecs = int(m*hoRatio)#100
    errorCount = 0.0
    for i in range(numTestVecs):
        classifierResult =  classify0(normMat[i,:],normMat[numTestVecs:m,:],
                                      datingLabels[numTestVecs:m],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)))

def classifyPerson():
    resultList = ['not at all','in samll doses','in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))#python3不支持raw_input
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of ice cream consumed per year?"))
    datingDataMat,datingLabels = file2matrix("datingTestSet2.txt")
    normMat,ranges,minVals = autoNorm(datingDataMat)
    inArr = array([ffMiles,percentTats,iceCream])
    classifierResult = classify0(inArr-minVals/ranges,normMat,datingLabels,3)
    print("You will probably like this person:",resultList[classifierResult-1])


def img2vector(filename):
    returnVect = zeros((1,1024))
    fr = open(filename)
    for i in range(32):
        lineStr = fr.readline()
        for j in range(32):
            returnVect[0,32*i+j] = int(lineStr[j])
    return returnVect

def handwritingClassTest():
    hwlabels = []
    trainingFileList = os.listdir('trainingDigits')
    m = len(trainingFileList)
    trainingMat = zeros((m,1024))
    for i in range(m):
        fileNameStr = trainingFileList[i]#0_0.txt
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        hwlabels.append(classNumStr)
        trainingMat[i,:] = img2vector('trainingDigits/%s' %fileNameStr)
    testFileList = os.listdir('testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('testDigits/%s' %fileNameStr)
        classifierResult = classify0(vectorUnderTest,trainingMat,hwlabels,3)
        print("the classifier came back with: %d, the real answer is:%d"
              %(classifierResult,classNumStr))
        if(classifierResult != classNumStr): errorCount+=1
    print("\nthe total number of errors is: %d" % errorCount)
    print("\nthe total error rate is: %f" %(errorCount/float(mTest)))







if __name__ == '__main__':
    # group,labels = createDataSet()
    # print (classify0([0,0],group,labels,3))
    # print(file2matrix("datingTestSet2.txt"))
    # datingDataMat,datingLabels=file2matrix("datingTestSet2.txt")
    # normMat,ranges,minVals = autoNorm(datingDataMat)
    # fig = plt.figure()
    # ax = fig.add_subplot(211)#111,与121是左右的关系啊  这几个参数要弄明白啊
    # ax2 = fig.add_subplot(212)
    # # ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
    # # ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels))
    # ax.scatter(datingDataMat[:,0],datingDataMat[:,1],15.0*array(datingLabels),15.0*array(datingLabels))
    # ax2.scatter(normMat[:,0],normMat[:,1],15.0*array(datingLabels),15.0*array(datingLabels))
    # plt.show()
    # normMat,ranges,minVals = autoNorm(datingDataMat)
    # print(normMat,ranges,minVals)

    # y=pp.DS.Transac_open  # 设置y轴数据，以数组形式提供
    #res=[1,2,3]
    # x=len(res)         # 设置x轴，以y轴数组长度为宽度
    # x=range(x)   # 以0开始的递增序列作为x轴数据
    # plt.plot(x,res)  #  只提供x轴，y轴参数，画最简单图形
    # plt.show()

    # datingClassTest()
    # classifyPerson()
    # testVector = img2vector('testDigits/0_13.txt')
    # print(testVector[0,0:31])
    handwritingClassTest()