PCA降维

先利用xlrd_read_data函数读取数据，然后用pca降维，降维后的数据存放在lowDDataMat中

def xlrd_read_data(path):
    table = xlrd.open_workbook(path).sheets()[0] #读取第一个表格
    row = table.nrows  # 行数
    col = table.ncols  # 列数
    datamatrix = np.zeros((row, col))#生成一个nrows行ncols列，且元素均为0的初始矩阵
    for x in range(col):
        cols = np.matrix(table.col_values(x))  # 把list转换为矩阵进行矩阵操作
        datamatrix[:, x] = cols # 按列把数据存进矩阵中
    return datamatrix
def pca(dataMat,topNfeat=999999):
    meanVals=np.mean(dataMat,axis=0)
    meanRemoved=dataMat-meanVals
    covMat=np.cov(meanRemoved,rowvar=0)
    eigVals,eigVects=np.linalg.eig(np.mat(covMat))
    eigValInd=np.argsort(eigVals)
    eigValInd=eigValInd[:-(topNfeat+1):-1]
    redEigVects=eigVects[:,eigValInd]
    lowDDataMat=meanRemoved*redEigVects
    reconMat=(lowDDataMat*redEigVects.T)+meanVals
    return lowDDataMat,reconMat
   path= r'c:\Users\Liugengxin\Desktop\数学建模\2018E模拟\Data_For_Oneyear\16indicators.xlsx'
data=xlrd_read_data(path)
data_pca,recon=pca(data,5)
DataFrame(data_pca).to_excel(r'c:\Users\Liugengxin\Desktop\testpca.xlsx')