写在开头的话:在学习《机器学习实战》的过程中发现书中很多代码并没有注释,这对新入门的同学是一个挑战,特此贴出我对代码做出的注释,仅供参考,欢迎指正。
1、导入数据:
#coding:gbk
from numpy import *
import operator
def createDataSet():
group = array([[1.0, 1.1], [1.0, 1.0], [0, 0],[0, 0.1]])#4*2维矩阵
labels = ['A', 'A', 'B', 'B']
return group, labels
注释:有中文注释必须加
#coding:gbk
2、k-近邻算法
def classify0(inX, dataSet, labels, k): dataSetSize = dataSet.shape[0]#dataSet一维长度 diffMat = tile(inX, (dataSetSize, 1)) - dataSet#将inx扩展成dataSet一样矩阵后相减 sqDiffMat = diffMat**2#平方 sqDistances = sqDiffMat.sum(axis = 1)#按行求和 distances = sqDistances**0.5#开根号 sortedDistIndicies = distances.argsort()#返回distances从小到大的索引值 classCount = {}#建立字典,用于指示labels数多少 for i in range(k): voteIlabel = labels[sortedDistIndicies[i]]#返回第i个label值 classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1#对每个label值出现的频率计数,0代表第一次计数,字典对应出现的字数为0 #对classCount按照值的大小从大到小进行排序,返回list sortedClassCount = sorted(classCount.iteritems(),#iteritems()表示将classCount以一个迭代器对象返回 key = operator.itemgetter(1), reverse = True)#operator.itemgetter(1)表示第2维数据即值,reverse = True表示从大大小排列 return sortedClassCount[0][0]
3、文本转换为Numpy矩阵
def file2matrix(filename): fr = open(filename) arrayOLines = fr.readlines() numberOfLines = len(arrayOLines)#文件行数 returnMat = zeros((numberOfLines,3))#创建空矩阵,表示训练样本矩阵 classLabelVector = []#创建空列表,表示类标签向量 index = 0#表示第index行 for line in arrayOLines: line = line.strip()#删除空白符(包括'\n', '\r', '\t', ' ') listFromLine = line.split('\t')#以'\t'分割字符串 returnMat[index,:] = listFromLine[0:3]#训练样本矩阵赋值 classLabelVector.append(int(listFromLine[-1]))#类标签向量赋值 index += 1 return returnMat, classLabelVector
4、归一化特征值
def autoNorm(dataSet): minVals = dataSet.min(0)#得每列最小值,返回1*m数组 maxVals = dataSet.max(0)#得每列最大值,返回1*m数组 ranges = maxVals - minVals normDataSet = zeros(shape(dataSet))#和dataSet一样维度的空矩阵 m = dataSet.shape[0]#得dataSet行数 normDataSet = dataSet - tile(minVals, (m, 1)) normDataSet = normDataSet/tile(ranges, (m, 1)) return normDataSet, ranges, minVals
5、约会网站测试代码
def datingClassTest(): hoRatio = 0.10#测试数据占10% datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')#导入数据 normMat, ranges, minVals = autoNorm(datingDataMat)#归一化数值 m = normMat.shape[0]#数据总量 numTestVecs = int(m*hoRatio)#测试数据量 errorCount = 0.0#错误分类计数变量 for i in range(numTestVecs):#对测试集中数据 classifierResult = classify0(normMat[i, :], normMat[numTestVecs:m, :],datingLabels[numTestVecs:m], 3) if (classifierResult != datingLabels[i]): errorCount += 1.0 print "the classfier came back with: %d, the real anwser is: %d" % (classifierResult, datingLabels[i]) print "the total error rate is: %f%%" % (100 * errorCount / float (numTestVecs))
6、约会网站预测函数
def classifyPerson(): resultList = ['not at all', 'in small doses', 'in large doses'] percentTats = float(raw_input("percentage of time spent playing video games?"))#输入...时间百分比 ffMiles = float(raw_input("frequent flier miles earned per year?"))#输入飞行公里数 iceCream = float(raw_input("liters of ice cream consumed per year?"))#输入冰激凌量 datingDataMat, datingLabels = file2matrix('datingTestSet2.txt')#导入数据 normMat, ranges, minVals = autoNorm(datingDataMat)#归一化数值 inArr = array([ffMiles, percentTats, iceCream])#需要预测数据 classifierResult = classify0((inArr - minVals) / ranges, normMat, datingLabels, 3) print "You will probably like this person: ", resultList[classifierResult - 1]
7、图像转换为Numpy矩阵
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
8、手写数字识别系统测试代码
def handwritingClassTest(): hwLabels = []#表示trainingMat代表的值,即类标签向量 trainingFileList = listdir('trainingDigits')#得trainingDigits文件夹里的文件名 m = len(trainingFileList)#trainingDigits文件夹里的文件数 trainingMat = zeros((m, 1024))#训练样本矩阵 for i in range(m): fileNameStr = trainingFileList[i] fileStr = fileNameStr.split('.')[0]#文件名里去除.txt classNumStr = int(fileStr.split('_')[0])#文件名里去除_i hwLabels.append(classNumStr)#类标签向量赋值 trainingMat[i, :] = img2vector('trainingDigits/%s' % fileNameStr)#训练样本矩阵赋值 testFileList = listdir('testDigits')#得testDigits文件夹里的文件名 errorCount = 0.0#错误分类计数变量 mTest = len(testFileList)#testDigits文件夹里的文件数,即测试数据量 for i in range(mTest): fileNameStr = testFileList[i] fileStr = fileNameStr.split('.')[0]#文件名里去除.txt classNumStr = int(fileStr.split('_')[0])#文件名里去除_i vectorUnderTest = img2vector('testDigits/%s' % fileNameStr)#测试样本矩阵赋值 classifierResult = classify0(vectorUnderTest, trainingMat, hwLabels, 3) if (classifierResult != classNumStr): errorCount += 1.0 print "%d: the classfier came back with: %d, the real anwser is: %d" % (errorCount, classifierResult, classNumStr) print "\nthe total error rate is: %f %%" % (100* errorCount / float(mTest))