graphssl.py 文件源码

def constructCovarianceMatrix(self):

        #this function constructs the covariance matrix for the dataset and then does a label propagation over it

        self.covarianceMatrix=np.cov(self.trainVectorsPCA.T) #as numpy treats them as column vetcors
        self.inverseCovarianceMatrix=np.linalg.inv(self.covarianceMatrix)

        #compute the cholesky decomposition and then transform the data into the new space

        self.L_cov=np.linalg.cholesky(self.covarianceMatrix)
        self.allDataCov=np.dot(self.allDataPCA,self.L_cov.T)
        self.pwdis=pairwise_distances(self.allDataCov)
        self.D=np.zeros(self.pwdis.shape)
        projectedDigits=TSNE(random_state=randomState).fit_transform(self.allDataCov)
        plt.figure()
        plt.scatter(projectedDigits[:,0],projectedDigits[:,1],c=self.labels)
        plt.title('Data projected by Covariance Matrix in Mahalanobis metric')
        plt.savefig(pp,format='pdf')
        plt.close()

        ks=[3,5,7,10,12,15,20,22,25,27,30,33,35,37,40,43,45,47,50,53,55,57,60,65]
        accs=[]
        for k in ks:
            for i in range(0,self.pwdis.shape[0]):
                l1=self.pwdis[i].tolist()
                #print 'l1 is ',l1,'\n\n'
                allnearestNeighbours=sorted(range(len(l1)),key=lambda i : l1[i])
                #now set the all the weights except for k+1 to 0
                self.pwdis[i,allnearestNeighbours[k:]]=0
                self.D[i,i]=sum(self.pwdis[i]+0.01)

            print 'accuracy by using Covariance Matrix for Mahalanobis Distance for k= ',k,'\n'
            accs.append(self.labelPropogation())

        plt.figure()
        plt.plot(ks,accs)
        plt.title('Plot of accuracy vs k using Covariance Matrix in  Mahalanobis metric')
        plt.savefig(pp,format='pdf')