kNN算法改进约会网站的配对效果

#coding = utf-8
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt

def createDataset():
	group = array([[1.0, 1.1], [1.0, 1.0], [0, 0], [0, 0.1]]) #生成一个数组
	labels = ['A', 'A', 'B', 'B']#标签向量
	return group, labels

def classify0(inX, dataSet, labels, k): #分别为待分类向量，数据集，标签向量，k
	dataSetSize = dataSet.shape[0] #计算数据集行数
	diffMat = tile(inX, (dataSetSize, 1)) - dataSet
	sqDiffMat = diffMat ** 2
	sqDistances = sqDiffMat.sum(axis = 1)
	distances = sqDistances ** 0.5 #计算待分类向量和数据集每个向量的距离
	sortedDistIndicies = distances.argsort() #排序且返回的是升序元素的索引
	classCount = {} #创建空字典
	for i in range(k):
		voteIlabel = labels[sortedDistIndicies[i]]
		classCount[voteIlabel] = classCount.get(voteIlabel, 0) + 1 #记录不同类别的分别有几个
	sortedClassCount = sorted(classCount.iteritems(), key = operator.itemgetter(1), reverse = True) #按照键值对的第二维降序排
	return sortedClassCount[0][0] #分类结果

def file2matrix(filename):
	fr = open(filename)
	arrayOLines = fr.readlines() #一次性读取文件所有行
	numberOfLines = len(arrayOLines) #共有多少行
	returnMat = zeros((numberOfLines, 3)) 
	classLabelVector = []
	index = 0
	for line in arrayOLines:
		line = line.strip() #去除开头结尾的空格制表等
		listFromLine = line.split('\t') #按照制表分割
		returnMat[index,:] = listFromLine[0:3] #赋值
		classLabelVector.append(int(listFromLine[-1])) #赋值
		index += 1
	return returnMat, classLabelVector
group, labels = createDataset()
sortedClassCount = classify0([0, 0], group, labels, 3)
returnMat, classLabelVector = file2matrix('datingTestSet2.txt')
fig = plt.figure()
ax = fig.add_subplot(111)
ax.scatter(returnMat[:,1], returnMat[:,2], 15.0*array(classLabelVector), 15.0*array(classLabelVector))

def autoNorm(dataSet): #归一化特征值new = (old - min)/(max - min)
	minVals = dataSet.min(0) #求每一列的最小值
	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
normDataSet, ranges, minVals = autoNorm(returnMat)

def datingClassTest(): #测试分类器错误率
	hoRatio = 0.10 #使用％10的数据进行测试即可
	datingDataMat, datingLabels = file2matrix('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))
datingClassTest()