4_Train_PCA+SVM.py 文件源码

def pca(dataMat,n):   
    print "Start to do PCA..."   
    t1 = time.time()   
    newData,meanVal=zeroMean(dataMat)   
    covMat=np.cov(newData,rowvar=0)   
    eigVals,eigVects=np.linalg.eig(np.mat(covMat)) # calculate feature value and feature vector   
    joblib.dump(eigVals,'./features/PCA/%s/eigVals_train_%s.eig' %(m,m),compress=3)    
    joblib.dump(eigVects,'./features/PCA/%s/eigVects_train_%s.eig' %(m,m),compress=3)  
    # eigVals = joblib.load('./features/PCA/%s/eigVals_train_%s.eig' %(m,m))  
    # eigVects = joblib.load('./features/PCA/%s/eigVects_train_%s.eig' %(m,m))   
    eigValIndice=np.argsort(eigVals) # sort feature value
    n_eigValIndice=eigValIndice[-1:-(n+1):-1] # take n feature value   
    n_eigVect=eigVects[:,n_eigValIndice] # take n feature vector 
    joblib.dump(n_eigVect,'./features/PCA/%s/n_eigVects_train_%s_%s.eig' %(m,m,n))    
    lowDDataMat=newData*n_eigVect # calculate low dimention data
    # reconMat=(lowDDataMat*n_eigVect.T)+meanVal   
    t2 = time.time()   
    print "PCA takes %f seconds" %(t2-t1)   
    return lowDDataMat