1 、k-n 邻近算法
from numpy import *
import operator
def classify0(inX, dataSet, labels, k):
dataSetSize = dataSet.shape[0]
print("dataSetSize",dataSetSize )
diffMat = tile(inX, (dataSetSize,1)) - dataSet
print("title",tile(inX, (dataSetSize,1)))
print("diffMat",diffMat)
sqDiffMat = diffMat**2
print("sqDiffMat",sqDiffMat)
sqDistances = sqDiffMat.sum(axis=1)
print ("sqDistances",sqDistances)
distances = sqDistances**0.5
print("distances",distances)
sortedDistIndicies = distances.argsort()
print ("sortedDistIndicies",sortedDistIndicies)
classCount={}
for i in range(k):
voteIlabel = labels[sortedDistIndicies[i]]
print('iiiii ',i)
print('voteIlabel=',voteIlabel)
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1
print("classCount.get(voteIlabel,0)",classCount.get(voteIlabel,0))
print("classCount[voteIlabel]", classCount[voteIlabel])
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)
print("sortedClassCount",sortedClassCount)
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
group,labels = createDataSet()
classify0([0,0],group,labels,3)
2、将文本记录解析为Numpy 的解析程序
def file2matrix(filename):
fr = open(filename)
numberOfLines = len(fr.readlines())
returnMat = zeros((numberOfLines, 3))
classLabelVector = []
fr = open(filename)
index = 0
for line in fr.readlines():
line = line.strip()
listFromLine = line.split('\t')
print('第一维中的数据第0列数据listFromLine=', listFromLine)
returnMat[index, :] = listFromLine[0:3]
print('listFromLine[0:3]', listFromLine[0:3])
print('returnMat[index,:]', returnMat[index, :])
classLabelVector.append(int(listFromLine[-1]))
index += 1
return returnMat, classLabelVector
3、归一化特征值函数
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))
return normDataSet, ranges, minVals
4、作为完整程序验证分类器
def datingClassTest():
hoRatio = 0.50
datingDataMat,datingLabels = file2matrix('D:\\yls\\learn\\machinelearninginaction\\Ch02\\datingTestSet2.txt')
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
2-6 手写数字识别系统的测试代码
def handwritingClassTest():
hwLabels = []
trainingFileList = listdir('D:\\yls\\learn\\machinelearninginaction\\Ch02\\digits\\trainingDigits')
m = len(trainingFileList)
trainingMat = zeros((m,1024))
for i in range(m):
fileNameStr = trainingFileList[i]
fileStr = fileNameStr.split('.')[0]
classNumStr = int(fileStr.split('_')[0])
hwLabels.append(classNumStr)
trainingMat[i,:] = img2vector('D:\\yls\\learn\\machinelearninginaction\\Ch02\\digits\\trainingDigits\\%s' % fileNameStr)
testFileList = listdir('D:\\yls\\learn\\machinelearninginaction\\Ch02\\digits\\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('D:\\yls\\learn\\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)))