PCAWithRaw.py

from numpy import *


# PCA降维数据

def loadDataSet(fileName, delim='\t'):
    fr = open(fileName)
    stringArr = [line.strip().split(delim) for line in fr.readlines()]
    datArr = [list(map(float, line)) for line in stringArr]
    return mat(datArr)


def pca(dataMat, topNfeat=9999):
    meanVals = mean(dataMat, axis=0)
    meanRemoved = dataMat - meanVals
    covMat = cov(meanRemoved, rowvar=0)
    eigVals, eigVects = linalg.eig(mat(covMat))
    eigValInd = argsort(eigVals)
    eigValInd = eigValInd[:-(topNfeat+1):-1]
    redEigVects = eigVects[:,eigValInd]
    lowDDataMat = meanRemoved * redEigVects
    reconMat = (lowDDataMat * redEigVects.T) + meanVals
    return lowDDataMat, reconMat


if __name__ == '__main__':
    dataMat = loadDataSet('../data/kmeanstestSet.txt')
    lowDMat, reconMat = pca(dataMat, 1)
    print(lowDMat)