def perform_lda(dictionary, corpus, num_topics, wiki_path=None, passes=1, iterations=50, chunksize=200):
"""
:param dictionary:
:param corpus:
:param wiki_path:
:param num_topics:
:param passes:
:param iterations:
:param chunksize:
:return:
"""
if wiki_path is not None:
logging.info('Generating wiki corpus...')
wikis = unpickle(wiki_path)
wiki_corpus = [dictionary.doc2bow(wiki) for wiki in wikis]
logging.info('Combining original corpus and wiki corpus...')
corpus = corpus + wiki_corpus # wiki_corpus is merged after the original corpus
lda_model = LdaModel(corpus=corpus, id2word=dictionary, num_topics=num_topics, passes=passes,
iterations=iterations, alpha='auto', chunksize=chunksize)
corpus_ids = get_corpus_ids(dictionary.corpus_id2orig_id)
# doc_vector_ids = dictionary.corpus_id2orig_id[corpus_ids]
doc_vector_ids = [dictionary.corpus_id2orig_id[corpus_id] for corpus_id in corpus_ids]
doc_vectors = lda_model.inference(corpus)[0]
doc_vectors = doc_vectors[corpus_ids, :]
doc_vectors = doc_vectors / doc_vectors.sum(axis=1).reshape(doc_vectors.shape[0], 1)
return lda_model, doc_vectors, doc_vector_ids
def write_doc_topics(vector_path, id_path, csv_name):
vectors = unpickle(vector_path)
ids = unpickle(id_path)
writer = csv.writer(file(csv_name, 'w'))
# 1st row
row = ['']
for topic_id in range(vectors.shape[1]):
row.append('z = ' + str(topic_id))
writer.writerow(row)
# 2nd row and onwards
for row_num, id in enumerate(ids):
row = [id]
for topic_id in range(vectors.shape[1]):
row.append(vectors[row_num, topic_id])
writer.writerow(row)
corpus = [w for w in corpus if not w in stopwords and 2 <= len(w) <= 15 and w.islower()]
processed_corpora.append(corpus)
corpus_id2orig_id.append(index)
print '\n'
logging.info('Creating dictionary and corpus...')
dictionary = Dictionary(processed_corpora)
dictionary.corpus_id2orig_id = corpus_id2orig_id
logging.info('Filtering unimportant terms...')
dictionary.filter_extremes(no_below=no_below, no_above=no_above, keep_n=keep_n)
dictionary.compactify()
logging.info('Generating corpus...')
dictionary.corpus = [dictionary.doc2bow(corpus) for corpus in processed_corpora]
dictionary.id2token = revdict(dictionary.token2id)
return dictionary
if __name__ == '__main__':
# logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)
logging.info('Loading corpora...')
tweets_corpora = unpickle('data/processed/tweets.pkl')
logging.info('Preprocessing corpora...')
dictionary = preprocess_corpora(corpora=tweets_corpora, stopwords=stopwords, allowed_pos=re.compile('(NN)'))
dictionary.save('data/dictionary/tweets.dict')
if __name__ == '__main__':
# hyper-parameters
allowed_pos = re.compile('(NN)')
crawl = True
# target = 'user'
# topic_num = 100
model_path = 'data/model/tweets_100.lda'
# logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.DEBUG)
if crawl is True:
logging.info('Crawling wikipedia...')
wikis = crawl_wiki(model_path=model_path)
else:
wikis = unpickle('data/others/wikis.pkl')
logging.info('Lemmatizing wikipedia texts...')
count = 0
doc_num = len(wikis)
new_wikis = []
keywords = []
for keyword, wiki in wikis.items():
count += 1
print '\r', count, '/', doc_num,
text = wiki['text']
cleaned = clean_text(text) # delete irrelevant characters
wiki = []
tokens = lemmatize(content=cleaned, allowed_tags=allowed_pos) # lemmatize