机器学习2—K近邻算法学习笔记
Python3.6.3下修改代码中def classify0(inX,dataSet,labels,k)函数的classCount.iteritems()为classCount.items(),另外print在Python新版本下是函数,print后面需加上一对括号,否则执行会报错。
import numpy as np #用于分类的输入向量是inX,输入的训练样本集为dataSet, #标签向量为 labels ,最后的参数 k 表示用于选择最近邻居的数目,其中标签向量的元素数目和矩 #阵 dataSet 的行数相同。 def classify0(inX,dataSet,labels,k): # 获取 数组 形状的 第一个 参数 a=[[1,2],[1,2],[1,2]] a.shape = [3,2] a.shape[0] = 3 # 一、 dataSetSize = dataSet.shape[0] # tile 代表了inX,复制为dataSetSize行,1列的数组 # 二、 diffMat = np.tile(inX,(dataSetSize,1))-dataSet # 平方 sqDiffMat = diffMat**2 # axis 等于 1 是将 矩阵的每一行 相加 sqDistances = sqDiffMat.sum(axis=1) # 开方 distances = sqDistances**0.5 # 三、 # 从小到大 排列,argsort : 将distacnces中的元素从小到大排列,提取其对应的index(索引),然后输出到sortedDistances sortedDistances = distances.argsort() classCount = {} # 四、求出来 最低距离 的 labels结果,存放在classCount 中 for i in range(k): #取第i+1个邻近的样本对应的类别标签 voteIlabel =labels[sortedDistances[i]] #以标签为key,标签出现的次数为value将统计到的标签及出现次数写进字典 classCount[voteIlabel] = classCount.get(voteIlabel,0)+1 #对字典按value从大到小排序 sortedClassCount = sorted(classCount.items(),key=operator.itemgetter(1),reverse=True) #返回排序后字典中最大value对应的key return sortedClassCount[0][0]
#将文本记录转换为Numpy的解析程序 def file2matrix(filename): fr=open(filename) #打开文件 arrayOLines=fr.readlines() #获取文件所有行 numberOfLines=len(arrayOLines) #得到文件行数 returnMat=zeros((numberOfLines,3)) #先用零元素创建需要返回的numpy矩阵,(行数,列数) classLabelVector=[] # 创建空的标签列表 index=0 for line in arrayOLines: line=line.strip() #截取掉尾部的回车字符 listFromLine=line.split('\t') #用‘\t’作为分隔符将整行元素分割成元素列表,将一行数据按空进行分割, returnMat[index,:]=listFromLine[0:3] #选取列表前三个元素到=矩阵中 classLabelVector.append(listFromLine[-1]) #将列表的最后一列存储到向量中 index += 1 return returnMat,classLabelVector #返回数据集矩阵和对应的标签向量
#归一化特征值 def autoNorm(dataSet): minVals = dataSet.min(0) #找到数据集中的最小值(实际上应该是样本数据中的一列中的最小值,参数0就代表这个,下同),这样说的话minVals和maxVals都应该是一个行向量(1*n) maxVals = dataSet.max(0) #找到数据集中的最大值 ranges = maxVals - minVals #得到数据的范围差值 normDataSet = zeros(shape(dataSet)) # 定义空的要返回的归一化后的矩阵,该矩阵和传入的数据集是一样的大小 m = dataSet.shape[0] #得到矩阵第一行的数据个数,也就是维数 normDataSet = dataSet - tile(minVals, (m,1)) #数据集与最小值相减(title()函数将按照括号中的参数制作对应大小的矩阵,用给定的minVals内容来填充 normDataSet = normDataSet/tile(ranges, (m,1)) #除以范围值之后就是归一化的值了。(注意是矩阵除法) return normDataSet, ranges, minVals
#分类器针对约会网站的测试代码 def datingClassTest(): hoRatio = 0.10 #测试所占的比例 datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') #将文件中的数据转换为矩阵形式和提取出标签矩阵 normMat, ranges, minVals = autoNorm(datingDataMat) #对提取出的矩阵数据归一化处理 m = normMat.shape[0] #获得数据总的条数 numTestVecs = int(m*hoRatio) #得出作为测试的数据个数 errorCount = 0.0 #初始化错误个数为0 for i in range(numTestVecs): #对测试的数据进行遍历 classifierResult = classify0(normMat[i,:],normMat[numTestVecs:m,:],datingLabels[numTestVecs:m],3) # 对数据进行分类 print("the classifier came back with: %s, the real answer is: %s" % (classifierResult, datingLabels[i])) #输出分类结果和实际的类别(之前的代码有问题啊,要将%d,改为%s) if (int(classifierResult) != int(datingLabels[i])): errorCount += 1.0 # 如果分类结果与实际结果不一致 ,错误数加1 print("the total error rate is: %f" % (errorCount/float(numTestVecs))) # 输出错误率 print(errorCount) #输出错误总数
#约会网站预测函数 def classiyPerson(): resultList = ['not at all','in small doses','in large doses'] # 定义分类结果的类别 percentTats = float(raw_input("percentage of time spent playing video games?")) # 读取输入数据 ffMiles = float(raw_input("frequent flier miles earned per year?")) # 读取输入数据 iceCream = float(raw_input("liters of ice cream consumed per year?")) # 读取输入数据 datingDataMat,datingLabels = file2matrix('datingTestSet2.txt') # 从文件中读取已有数据 normMat,ranges,minVals = autoNorm(datingDataMat) # 对数据进行归一化 inArr =array([ffMiles,percentTats,iceCream]) # 将单个输入数据定义成一条数据 classifierResult = classify0(inArr,datingDataMat,datingLabels,3) # 对输入数据进行分类 print('You will probably like this person: %s' % (resultList[int(classifierResult) - 1])) # 输出预测的分类类别
# 将单个手写字符文件变成向量 def img2vector(filename): returnVect = zeros((1,1024)) #创建要返回的1*1024的矩阵并初始化为0 fr = open(filename) # 打开文件 for i in range(32): #从0到31行遍历 lineStr = fr.readline() #读取一行(自动成为一个列表) for j in range(32): #从0到31列 returnVect[0,32*i+j] = int(lineStr[j]) #将一行中的每个元素复制到要返回的矩阵中 return returnVect #返回该1*1024的矩阵
# 手写字符识别测试 def handwritingClassTest(): hwLabels = [] # 定义手写字符标签(类别) trainingFileList = listdir('trainingDigits') # 列出目录下所有的文件 m = len(trainingFileList) # 计算训练文件的数目 trainingMat = zeros((m,1024)) # 定义手写字符数据矩阵 for i in range(m): # 依次读取每个文件 fileNameStr = trainingFileList[i] # 依次获得文件名 fileStr = fileNameStr.split('.')[0] # 对文件名进行分割 classNumStr = int(fileStr.split('_')[0]) # 获得文件名中的类标签 hwLabels.append(classNumStr) # 把类标签放到hwLabels中 trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr) # 把文件变成向量并赋值到trainingMat这个矩阵中 testFileList = listdir('testDigits') # 列出测试目录下的所有文件 errorCount = 0.0 # 定义错误数 mTest = len(testFileList) # 获得测试文件数目 for i in range(mTest): # 遍历测试文件 fileNameStr = testFileList[i] # 定义测试文件名 fileStr = fileNameStr.split('.')[0] # 对测试文件名进行分割 classNumStr = int(fileStr.split('_')[0]) # 获得测试文件的类标签 vectorUnderTest = img2vector('testDigits/%s' % fileNameStr) # 将测试文件转换成向量 classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3) # 进行分类 print("the classifier came back with: %d, the real answer is: %d" % (int(classifierResult), int(classNumStr))) # 输出预测类别和实际类别 if (int(classifierResult) != int(classNumStr)): errorCount += 1.0 # 如果二者不一致,累加错误数量 print("\nthe total number of errors is: %d" % errorCount) # 输出分类错误的数目 print("\nthe total error rate is: %f" % (errorCount/float(mTest))) # 输出分类的错误率
第二章代码修改如下:
from numpy import * import operator from os import listdir def classify0(inX, dataSet, labels, k): dataSetSize = dataSet.shape[0] 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 sortedClassCount = sorted(classCount.items(), key=operator.itemgetter(1), reverse=True) return sortedClassCount[0][0] 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 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) 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)) #element wise divide return normDataSet, ranges, minVals def datingClassTest(): hoRatio = 0.50 #hold out 10% 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[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))) print(errorCount) 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 = listdir('trainingDigits') #load the training set m = len(trainingFileList) trainingMat = zeros((m,1024)) for i in range(m): fileNameStr = trainingFileList[i] fileStr = fileNameStr.split('.')[0] #take off .txt classNumStr = int(fileStr.split('_')[0]) hwLabels.append(classNumStr) trainingMat[i,:] = img2vector('trainingDigits/%s' % fileNameStr) testFileList = listdir('testDigits') #iterate through the test set errorCount = 0.0 mTest = len(testFileList) for i in range(mTest): fileNameStr = testFileList[i] fileStr = fileNameStr.split('.')[0] #take off .txt 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 += 1.0 print("\nthe total number of errors is: %d" % errorCount) print("\nthe total error rate is: %f" % (errorCount/float(mTest)))