机器学习实战 kNN算法

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

#Remove dict.iteritems(), dict.iterkeys(), and dict.itervalues().
#Instead: use dict.items(), dict.keys(), and dict.values() respectively.

# 线代和矩阵操作库
from numpy import *
import operator

#路径相关的
from os import listdir

#画图的
import matplotlib
import matplotlib.pyplot as plt

#测试数据 书上代码都只有2，3个特征
def createDataSet():
    group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]]) #array 遍于矩阵操作
    labels = ['A', 'A', 'B', 'B']
    return group, labels

# 分类器
def classify0(inx, dataSet, labels, k):
    dataSetSize = dataSet.shape[0] #获得一维长度
    diffMat = tile(inx, (dataSetSize,1)) - dataSet #获得二维长度
    sqDiffMat = diffMat**2 #平方
    sqDistances = sqDiffMat.sum(axis=1) # axis 1 代表行  0 代表 列
    distances = sqDistances**0.5 #同上
    sortedDistIndicies = distances.argsort() #排完序从小到大的索引值
    classCount={}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]
        classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1 #dir 计数
    sortedClassCount = sorted(classCount.items(), key = operator.itemgetter(1), reverse = True) #迭代， 从大到小 以第一个域大小为主
    return sortedClassCount[0][0]

#读数据
def file2matrix(filename):
    fr = open(filename)#打开文件
    arrayOLines = fr.readlines()#读取
    numberOfLines = len(arrayOLines) #一维长度
    returnMat = zeros((numberOfLines, 3)) # n * 3 的 0矩阵
    classLabelVector = []
    index = 0
    for line in arrayOLines:
        line = line.strip() #删除字符串前后空白符
        listFromLine  = line.split('\t') #以'\t' 切割
        returnMat[index,:] = listFromLine[0:3]
        classLabelVector.append(int(listFromLine[-1]))
        index += 1
    return returnMat,classLabelVector

#图形化
def picture():
    fig = plt.figure()
    ax = fig.add_subplot(111) #把图像分成1行1列 左到右 上到下 第1块
    #ax.scatter(datingDataMat[:,1], datingDataMat[:,2])#x 为 数组1， y为数组2
    ax.scatter(datingDataMat[:,1], datingDataMat[:,2], 15.0 * array(datingLabels), 15.0 * array(datingLabels)) # 形状 颜色
    plt.show()

#归一化
def autoNorm(dataSet):
    minVals = dataSet.min(0) #0 代表列
    maxVals = dataSet.max(0)
    range = maxVals -minVals
    normDataSet = zeros(shape(dataSet))
    m = dataSet.shape[0]
    normDataSet = dataSet - tile(minVals, (m,1))
    normDataSet = normDataSet/tile(range, (m,1)) #矩阵除法
    return normDataSet, range, minVals

#检验分类器错误率 %10的测试数据
def datingClassTest():
    hoRatio = 0.10
    datingDataMat,datingLabels = file2matrix("/Users/yinfeng/Downloads/rar/machinelearninginaction/Ch02/datingTestSet2.txt") #路径啊！！！
    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[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)))

#约会网站测试函数
def classifyPerson():
    resultList = ['not at all', 'in small doses', 'in large doses']
    percentTats = float(input("percentage of time spent playing video games?"))
    ffMiles = float(input("frequent flier miles earned per year?"))
    iceCream = float(input("liters of ice cream consumed per year?"))

    datingDataMat,datingLabels = file2matrix("/Users/yinfeng/Downloads/rar/machinelearninginaction/Ch02/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])

#把图像转换成特征值
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

#测试数字 mac os 有一个隐藏文件 .DS_Store
def handwritingClassTest():
    hwLabels = []
    trainingFileList = listdir("/Users/yinfeng/Downloads/rar/machinelearninginaction/Ch02/digits/trainingDigits")
    m = len(trainingFileList)
    #print(trainingFileList[1])
    trainingMat = zeros((m,1024))
    for i in range(m):
        if(trainingFileList[i] == ".DS_Store"): continue
        fileNameStr = trainingFileList[i]
        fileStr = fileNameStr.split('.')[0] #切割函数
        classNumStr = int(fileStr.split('_')[0])
        hwLabels.append(classNumStr)
        trainingMat[i,:] = img2vector("/Users/yinfeng/Downloads/rar/machinelearninginaction/Ch02/digits/trainingDigits/%s" % fileNameStr)
    testFileList = listdir('/Users/yinfeng/Downloads/rar/machinelearninginaction/Ch02/digits/testDigits')
    errorCount = 0.0
    mTest = len(testFileList)
    for i in range(mTest):
        if(testFileList[i] == ".DS_Store"): continue
        fileNameStr = testFileList[i]
        fileStr = fileNameStr.split('.')[0]
        classNumStr  = int(fileStr.split('_')[0])
        vectorUnderTest = img2vector('/Users/yinfeng/Downloads/rar/machinelearninginaction/Ch02/digits/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 += 1.0
    print("\nthe total number of errors is %d" % errorCount)
    print("\nthe total error rate is: %f" % (errorCount/float(mTest)))