经典机器学习算法系列8-PCA

PCA是经典的降维手段，降维的代码在《机器学习实战》里面有完整的python代码，现在将代码书写如下

写一个pca.py文件，将下面的代码复制到文件中。

'''
Created on Jun 1, 2011

@author: Peter Harrington
'''
from numpy import *

def 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 mean
    covMat = cov(meanRemoved, rowvar=0)
    eigVals,eigVects = linalg.eig(mat(covMat))
    eigValInd = argsort(eigVals)            #sort, sort goes smallest to largest
    eigValInd = eigValInd[:-(topNfeat+1):-1]  #cut off unwanted dimensions
    redEigVects = eigVects[:,eigValInd]       #reorganize eig vects largest to smallest
    lowDDataMat = meanRemoved * redEigVects#transform data into new dimensions
    reconMat = (lowDDataMat * redEigVects.T) + meanVals
    return lowDDataMat, reconMat

def replaceNanWithMean(): 
    datMat = loadDataSet('secom.data', ' ')
    numFeat = shape(datMat)[1]
    for i in range(numFeat):
        meanVal = mean(datMat[nonzero(~isnan(datMat[:,i].A))[0],i]) #values that are not NaN (a number)
        datMat[nonzero(isnan(datMat[:,i].A))[0],i] = meanVal  #set NaN values to mean
    return datMat

书写main.py文件，复制如下代码

import pca
lowDMat1,feature1 = pca.pca(feature,200);

这样就可以把一个向量降到200维度了