LDA على مقالات LiveJournal + التصور

stop=open('stop.txt')
stop_words=[]
for line in stop:
    stop_words.append(line)
for i in range(0,len(stop_words)):
    stop_words[i]=stop_words[i][:-1]
# specific regular expresion for this texts 
texts=[re.split( r' [\w\.\&\?!,_\-#)(:;*%$№"\@]* ' ,texts[i])[0].replace("\n","") for i in range(0,len(texts))]   
    # remove punctuation
texts=[test_re(line) for line in texts]
texts=[t.lower() for t in texts]
# remove stop words
texts = [[word for word in document.split() if word not in stop_words] for document in texts]
texts=[[word for word in document if len(word)>=3]for document in texts]

morph = pymorphy2.MorphAnalyzer()
for i in range(0,len(texts)):
    for j in range(0,len(texts[i])):
        texts[i][j] =  morph.parse(texts[i][j])[0].normal_form

counter = collections.Counter()
for t in texts:
    for r in t:
        counter[r]+=1
limit = len(texts)/5
too_common = [w for w in counter if counter[w] > limit]
too_common=set(too_common)
texts = [[word for word in document if word not in too_common] for document in texts]

texts=preposition_text_for_lda(my_r)
dictionary = gensim.corpora.Dictionary(texts)
corpus = [dictionary.doc2bow(text) for text in texts]
#lda = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=dictionary, num_topics=10, update_every=1, chunksize=1, passes=1)
lda = gensim.models.ldamodel.LdaModel(corpus=corpus, id2word=dictionary, num_topics=10)

lda.show_topic(i,topn=30)

from wordcloud import WordCloud, STOPWORDS
for i in range(0,10):
    a=lda.show_topic(i,topn=30)
    wordcloud = WordCloud(
                          relative_scaling = 1.0,
                          stopwords = too_common # set or space-separated string
                          ).generate_from_frequencies(dict(a))
    wordcloud.to_file('society'+str(i)+'.png')