def file2matrix(filename): fr=open(filename)#打开文件 arrayOfLines=fr.readlines()#读取每一行 numberOfLines=len(arrayOfLines)#统计行数 returnMat=zeros((numberOfLines,3))#转换成矩阵 classLabelVector=[] index=0 for line in arrayOfLines: line=line.strip()#去掉转义符 listFromLine=line.split('\t')#截取字符串 returnMat[index:]=listFromLine[0:3]#取前三组数据 classLabelVector.append(int(listFromLine[-1]))#将最后一列数据存入 index+=1 return returnMat,classLabelVector datingDataMat,datingLabels=file2matrix('datingTestSet2.txt') print (datingDataMat) print (datingLabels) import matplotlib import matplotlib.pyplot as plt fig=plt.figure() ax=fig.add_subplot(111) ax.scatter(datingDataMat[:,1],datingDataMat[:,2],15.0*array(datingLabels),15.0*array(datingLabels)) plt.show()