weeks = list()
dist = list()
lamb = list()
inicial = 1
final = 603
for line in data_file:
tweet = json.loads(line)
created = int(tweet['created_at'])
if(days2time(inicial) <= created < days2time(final)):
doc_tw.add(tweet['text'])
doc_set.append(tweet)
texts = tp.text_process(doc_tw)
corpus, dic = tp.create_corpus(texts)
ldamodel = tp.generate_lda(corpus, dic, 5)
#ldamodel = tp.generate_hdp(corpus, dic)
print(tp.print_topics(ldamodel))
with open(lamb_dir) as l_file:
for line in l_file:
i = int(line.split('|')[2])
w = int(line.split('|')[0])
lamb.append(w)
for s in range(i-1):
lamb.append(w)
for k in range(inicial, final, 7):
doc = set()
for tw in doc_set:
if(days2time(k) <= tw['created_at'] < days2time(k+7)):
doc.add(tw['text'])
documents = tp.text_process(doc)
