python K-近邻分类器
通过python构建一个基本的近邻分类器。在这个例子中(案例来源:《机器学习实战》),我们希望帮助海伦在约会网站上找到自己合适的约会对象。凯伦的约会对象有三类人,分别是极具魅力的人,魅力一般的人,和不喜欢的人。海伦总共收集了一千组数据,每个数据占一行,每行数据有三个特征。
代码如下:
# -*- coding: utf-8 -*-
from numpy import *
import operator
import matplotlib
import matplotlib.pyplot as plt
import pylab
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 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
sortedDistIndices=distances.argsort()#将距离数组从小到大进行index排序
classCount={}
for i in range(k):
voteIlabel=labels[sortedDistIndices[i]]#获取前K个标签
classCount[voteIlabel] = classCount.get(voteIlabel,0) + 1#对前K个标签出现次数分别加总
sortedClassCount = sorted(classCount.iteritems(), key=operator.itemgetter(1), reverse=True)#对前K个标签出现次数进行排序
return sortedClassCount[0][0]#返回出现次数最多标签的标签类
def file2matrix(filename):#将原txt文本中的数据存储到矩阵中
fr=open(filename)
#arrayexp=fr.readline().strip().split('\t')
#numpara=len(arrayexp)
arrayOLines=fr.readlines()
numberOfLines=len(arrayOLines)
returnMat=zeros((numberOfLines,3))
classLabelVector=[]
index=0
for line in arrayOLines:
line=line.strip()
listFromLine=line.split('\t')
returnMat[index,:]=listFromLine[0:3]
classLabelVector.append(int(listFromLine[-1]))#负索引,很有实用意义
index +=1
return returnMat,classLabelVector
#fig=plt.figure(1)
#ax=fig.add_subplot(111)
#ax.scatter(datingDataMat[:,1],datingDataMat[:,2])
def autoNorm(dataSet):#特征值的归一化
minVal=dataSet.min(0)
maxVal=dataSet.max(0)
ranges=maxVal-minVal
normDataSet=zeros(shape(dataSet))
m=dataSet.shape[0]
normDataSet=dataSet-tile(minVal,(m,1))
normDataSet=dataSet/tile(ranges,(m,1))
return normDataSet,ranges,minVal
def datingClassTest(kvalue):#对测试集运行分类器
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):