刚开始学习机器学习,先跟这《机器学习实战》学一些基本的算法
----------------------------------分割线--------------------------------------------
该算法是用来判定一个点的分类,首先先找到离该点最近的k个点,然后找出这k个点的哪种分类出现次数最多,就把该点设为那个分类
距离公式选用欧式距离公式:
下面给出例子(来自《机器学习实战》)
1.约会对象喜欢程度的判定:
现需要一个约会对象喜欢程度的分类器
给定数据集,属性包含
每年获得的飞行常客里程数,玩视频游戏所耗时间百分比,每周消费的冰淇淋公升数,是否喜欢且喜欢程度(不喜欢,一般喜欢,特别喜欢),四个属性
分类器代码:
先获取整个数据集的约会对象个数t,然后把我们要分类的矩阵复制t次
然后减去原数据集,得到xA0-xB0和xA1-xB1,然后对矩阵每个元素平方,行内求和,开根号,得到所有点的距离
统计前k个数据类别出现次数,返回次数最多的类别
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.iteritems(), key=operator.itemgetter(1), reverse=True)
return sortedClassCount[0][0]
先从文件中分别读前三个属性和喜欢程度到矩阵
然后进行归一化,最后分类得到结果统计一下就好了
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
2.数字识别
给定训练集包含32*32的01字符串,然后判定测试集的数字
对于把32*32每个数字都看作一个属性,然后直接算距离分类...
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('digits/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('digits/trainingDigits/%s' % fileNameStr)
testFileList = listdir('digits/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('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))