主成分分析(PCA)实现代码

摘自《机器学习实践》第13章：

from numpy import *
import matplotlib
import matplotlib.pyplot as plt

def loadDataSet(fileName, delim='	'):
    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 = 999999):
    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('testSet.txt')
    lowDMat, reconMat = pca(dataMat, 1)
    fig = plt.figure()
    ax = fig.add_subplot(111)
    ax.scatter(dataMat[:, 0].flatten().A[0], dataMat[:, 1].flatten().A[0], marker='^', s = 90)
    ax.scatter(reconMat[:, 0].flatten().A[0], reconMat[:, 1].flatten().A[0], marker='o', s = 50, c='red')
    plt.show()

输入数据格式： 文本文件，每行是两个以TAB键分隔的浮点数。

附运行结果：