for t in tweets:
replies += 1
print(f'___tweet #{replies}___\n')
print(f'___original tweet:___\n{t["full_text"]}\n')
words = sorted(re.split(r'[^a-zA-Z#]', t['full_text']),
key=lambda w: len(w),
reverse=True)
begin = None
for w in words:
if len(w) > 0 and w.lower() in chain.tree:
begin = w.lower()
break
elif len(w) == 0:
break
reply = chain.generate_tweet(start_with=begin,
append_tag='\n#YourWordFrequencies')
print(f'___reply:___\n{reply}\n')
try:
twit.statuses.update(status=reply,
in_reply_to_status_id=t['id'],
auto_populate_reply_metadata='true')
except Exception as e:
replies -= 1
print(f'{"!"*32}error{"!"*32}\n{e}\n')
print(f'{"—"*64}\n')
sleep(randint(2, 8))
print(f'search_term: {user}')
tweets = twit.statuses.user_timeline(screen_name=user, count=200, tweet_mode='extended', include_rts=False, trim_user=True)
for t in tweets:
if EXCLUDE_WORDS.search(t['full_text']) is None:
tweet = TEXT_ONLY.sub(' ', t['full_text'])
tweet = USER_NAME.sub(' ', tweet)
tweet = LINKS.sub(' ', tweet)
tweet = TYPO_HASHTAGS.sub(fix_hashtag, tweet)
tweet = TYPO_PERIOD.sub(fix_period, tweet)
tweet = TYPO_QUESTION.sub(fix_question, tweet)
tweet = TYPO_EXCLAMATION.sub(fix_exclamation, tweet)
tweet = LONE_PUNCTUATION.sub(' ', tweet)
tweet = AMPERSAND.sub('and', tweet)
tweet = GT.sub('>', tweet)
tweet = LT.sub('<', tweet)
chain.train(tweet)
# chain.train(t['full_text'])
print(f'len(chain.tree): {len(chain.tree)}')
chain.bulk_adjust_weights(fitness_functions=[aw_mult(aw_favor_complexity, .001), aw_mult(aw_favor_punctuation, .00015), aw_mult(dg_disfavor_consecutive_hashtags, .001)], iterations=len(chain.tree))
print('Sample tweet:', chain.generate_tweet())
# chain.save_training('bin/twitter/apologists.bin')
# chain.save_training('bin/twitter/atheists.bin')
chain.save_training('bin/twitter/news.bin')
# chain.save_training('bin/twitter/newagers.bin')
# chain.save_training('bin/twitter/churches.bin')
# chain.save_training('bin/twitter/trumpsterfire.bin')
# chain.save_training('bin/twitter/meta.bin')
next_id = re.split(r'\D+', tweets['search_metadata']['next_results'])[1]
try:
tweets = twit.search.tweets(q=query,
count=100,
lang='en',
result_type='recent',
tweet_mode='extended',
include_entities=False,
max_id=next_id)
except Exception as e:
print('____an error occurred____')
print(f'____search ended at i = {i+1}____')
break
for t in tweets['statuses']:
if EXCLUDE_WORDS.search(t['full_text']) is None:
tweet = clean_tweet(t['full_text'])
chain.train(tweet)
print(f'____len(chain.tree) = {len(chain.tree)}____')
print('____adjusting weights, this may take a moment____')
chain.bulk_adjust_weights(fitness_functions=[
aw_mult(aw_favor_complexity, .001),
aw_mult(dg_disfavor_consecutive_hashtags, .001)
],
iterations=len(chain.tree))
print('____done____')
chain.save_training('bin/twitter/beliefs.bin')
print('____sample tweet____:\n', chain.generate_tweet())
from math import sqrt
from random import random
from markov_chain import MarkovChain
test_chain = MarkovChain()
# file_name = './bin/new_testament.bin'
# file_name = './bin/quran.bin'
# file_name = './bin/quran_testament.bin'
# file_name = './bin/atheists.bin'
# file_name = './bin/twitter/news.bin'
file_name = './bin/star_trek/PICARD.bin'
# file_name = './bin/star_trek/DATA.bin'
test_chain.load_training(file_name)
print(f'{"_"*16} file_name: "{file_name}" {"_"*16}')
print(f'{"_"*16} len(test_chain.tree): {len(test_chain.tree)} {"_"*16}\n')
for i in range(11):
# print(test_chain.generate_tweet(start_with='amen', append_verse=True), '\n_\n')
print(
test_chain.generate_tweet(start_with=None,
append_tag='#MarkovProcess'), '\n_\n')
# that’s
from markov_chain import MarkovChain
from markov_algorithms import *
chain = MarkovChain()
chain.train_on_file(filename='training_txt/quran.txt', verbose=True)
chain.train_on_file(filename='training_txt/new_testament.csv', verbose=True)
print(f'len(chain.tree): {len(chain.tree)}\n')
# print('Adjusting weights. This may take a while.\n_\n')
# chain.bulk_adjust_weights(fitness_functions=[aw_mult(aw_favor_complexity, .001), aw_mult(aw_favor_punctuation, .00015), aw_mult(aw_favor_alternating_complexity, .1)], iterations=len(chain.tree))
chain.save_training('bin/quran_testament.bin')
for i in range(8):
print(chain.generate_tweet(append_tag=None, follow=False), '\n_\n')
# chain.load_training('bin/twitter/allgods.bin')
elif i % 7 == 4:
category = 'deepakchopra'
chain.load_training('bin/chopra.bin')
elif i % 7 == 5:
category = 'shakespeare'
chain.load_training('bin/shakespeare.bin')
else:
category = 'news'
chain.load_training('bin/twitter/news.bin')
# category = 'programming'
# chain.load_training('bin/programming.bin')
verse = True if category == 'bible' else False
tweet = chain.generate_tweet(
append_verse=verse,
append_tag=f'#MarkovChain.\n\n[Category: #{category}]')
print(f'-t: {tweet}')
twit.statuses.update(status=tweet)
# speak(tweet)
if i < num - 1:
delay = random.randint(1024, 2048)
delta = dt.timedelta(seconds=delay)
when = dt.datetime.now(tz=dt.timezone(dt.timedelta(hours=-7))) + delta
delay_text = f'delay: {delay} seconds (next tweet at {when.strftime("%H:%M:%S")})'
print(delay_text, '\n')
# speak(delay_text)
# time.sleep(delay - 12)
time.sleep(delay)
