import sqlite3 from sqlite3 import Error from markov_chain import MarkovChain chain = MarkovChain() database = '/home/drue/Deployment/star_trek_club/star_trek_db.sqlite3' connection = sqlite3.connect(database) cursor = connection.cursor() char_name = 'PICARD' cursor.execute('SELECT id FROM characters WHERE name=?', (char_name, )) char_id = cursor.fetchone()[0] cursor.execute('SELECT line FROM lines WHERE character_id=?', (char_id, )) for result in cursor.fetchall(): chain.train(result[0].replace('...', '').replace('--', '')) chain.save_training(f'bin/star_trek/{char_name}.bin')
max_id=next_id, lang='en') for t in tweets['statuses']: if EXCLUDE_WORDS.search(t['full_text']) is None: tweet = TEXT_ONLY.sub(' ', t['full_text']) tweet = RETWEET.sub(' ', tweet) tweet = USER_NAME.sub(' ', tweet) tweet = LINKS.sub(' ', tweet) tweet = AMPERSAND.sub('and', 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 = GT.sub('>', tweet) tweet = LT.sub('<', tweet) chain.train(tweet) 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(aw_favor_alternating_complexity, .1) ], iterations=len(chain.tree)) chain.save_training('bin/twitter/trending.bin') print( f'Sample tweet: {chain.generate_tweet(append_tag="Category: #trending")}')
break print(f'# of tweets: {len(tweets)}') for t in tweets: # if 'retweeted_status' in t: # continue # tweet = USER_NAME.sub(' ', t['full_text']) tweet = LINKS.sub(' ', t['full_text']) tweet = AMPERSAND.sub('&', tweet) tweet = GT.sub('>', tweet) tweet = LT.sub('<', tweet) chain.train(tweet) print(f'length of chain: {len(chain.tree)}\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(f'bin/twitter/{user}.bin') tweets = [tweets[i] for i in range(100)] tweets.reverse() print(f'{"—"*64}\n') replies = 0 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
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 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')