gistfile1.py

kl = []
num = range(0,25000,10)
for i in num:
    lda = models.ldamodel.LdaModel(corpus=my_corpus,
        id2word=dictionary,num_topics=i,distributed=True)
    #Topic-word matrix
    m1 = lda.expElogbeta
    U,s,V = np.linalg.svd(p)
    cm1 = s
    #Document-topic matrix
    lda_topics = lda[my_corpus]
    m2 = matutils.corpus2dense(lda_topics, lda.num_topics)
    l = []
    for doc in my_corpus:
        x = []
        for i in range(len(doc)):
            x.append(doc[i][1])
        l.append(sum(x))
    l = np.array(l)
    cm2 = m2.dot(l)
    cm2norm = np.linalg.norm(l)
    cm2 = cm2/cm2norm
    div = sym_kl(cm1,cm2)
    kl.append(div)