'''
@author: Garvin
'''
from numpy import *
import matplotlib.pyplot as pltdef loadDataSet(fileName, delim='\t'):fr = open(fileName)stringArr = [line.strip().split(delim) for line in fr.readlines()]datArr = [map(float,line) for line in stringArr]return mat(datArr)def pca(dataMat, topNfeat=9999999):meanVals = mean(dataMat, axis=0)meanRemoved = dataMat - meanVals #remove meancovMat = cov(meanRemoved, rowvar=0)eigVals,eigVects = linalg.eig(mat(covMat))eigValInd = argsort(eigVals)            #sort, sort goes smallest to largesteigValInd = eigValInd[:-(topNfeat+1):-1]  #cut off unwanted dimensionsredEigVects = eigVects[:,eigValInd]       #reorganize eig vects largest to smallestlowDDataMat = meanRemoved * redEigVects#transform data into new dimensionsreconMat = (lowDDataMat * redEigVects.T) + meanValsreturn lowDDataMat, reconMatdef plotBestFit(dataSet1,dataSet2):      dataArr1 = array(dataSet1)dataArr2 = array(dataSet2)n = shape(dataArr1)[0] n1=shape(dataArr2)[0]xcord1 = []; ycord1 = []xcord2 = []; ycord2 = []xcord3=[];ycord3=[]j=0for i in range(n):xcord1.append(dataArr1[i,0]); ycord1.append(dataArr1[i,1])xcord2.append(dataArr2[i,0]); ycord2.append(dataArr2[i,1])                  fig = plt.figure()ax = fig.add_subplot(111)ax.scatter(xcord1, ycord1, s=30, c='red', marker='s')ax.scatter(xcord2, ycord2, s=30, c='green')plt.xlabel('X1'); plt.ylabel('X2');plt.show()    if __name__=='__main__':mata=loadDataSet('/Users/hakuri/Desktop/testSet.txt')  a,b= pca(mata, 2)

loadDataSet函数是导入数据集。