graphssl.py 文件源码

def constructSimilartyMatrixCosinePCA(self):
        #This is a simpole k nearest neighbour approach based on the cosine distance
        #for this takefrom modshogun import RealFeatures, MulticlassLabels
        #then find the k nearest neighbours for each node 
        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:
            self.pwdis=pairwise_distances(self.allDataPCA,metric='cosine')
            #now we have all the pairwise cosine distances between all the sentences
            #now we need to do a knnNeighbour search
            #now we can construct the diagonal weight marix , which has the sum of all the weights
            self.D=np.zeros(self.pwdis.shape)
            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])

            print 'Now computing accuracy for cosine metric on PCA data'
            accs.append(self.labelPropogation())

        plt.figure()
        plt.plot(ks,accs)
        plt.title('Plot of accuracy vs k using cosine  PCA data')
        plt.savefig(pp,format='pdf')    
        plt.close()

        #now we have the weight matrix graph based on the cosine distance
        #print 'self.D is ',self.D