def markov_test():
print("### Markov Test")
m = Markov(3, "word")
m.train("../data/texts/lotr_clean.txt")
generated = m.generate(10)
pp.pprint(generated)
print("\n")
def lambda_handler(event, context):
"""Entrypoint for AWS Lambda. Event contains the payload from the AWS Lambda
call."""
user_text = event['userText']
mixin = event['mixin']
length = int(event['length'])
full_text = user_text + load_mixin(mixin)
markover = Markov(full_text)
return markover.generate(length)
def lambda_handler(event, context):
"""Entrypoint for AWS Lambda. Event contains the payload from the AWS Lambda
call."""
user_text = event['userText']
mixin = event['mixin']
length = int(event['length'])
full_text = user_text + load_mixin(mixin)
markover = Markov(full_text)
return markover.generate(length)
class TestMarkovClass(unittest.TestCase):
"""
Test that the Markov wrapper class behaves as expected
"""
def setUp(self):
self.markov = Markov(prefix="testclass", db=11)
def test_add_line_to_index(self):
line = ['i', 'ate', 'a', 'peach']
line1 = ['i', 'ate', 'one', 'peach']
line2 = ['i', 'ate', 'a', 'sandwich']
self.markov.add_line_to_index(line)
self.markov.add_line_to_index(line1)
self.markov.add_line_to_index(line2)
self.assertEqual(self.markov.client.zscore("testclass:i:ate", "a"),
2.0)
self.assertEqual(self.markov.client.zscore("testclass:ate:a", "peach"),
1.0)
def test_score_for_line(self):
self.test_add_line_to_index()
line = ['i', 'ate', 'a', 'peach']
self.assertEqual(self.markov.score_for_line(line), 100)
def test_generate(self):
self.test_add_line_to_index()
generated = self.markov.generate(max_words=3)
assert len(generated) >= 2
assert len(generated) <= 3
generated = self.markov.generate(seed=['ate', 'one'], max_words=3)
assert 'peach' in generated
assert 'sandwich' not in generated
def tearDown(self):
"""
clean up our redis keys
"""
keys = self.markov.client.keys(self.markov.prefix + "*")
for key in keys:
self.markov.client.delete(key)
class TestMarkovClass(unittest.TestCase):
"""
Test that the Markov wrapper class behaves as expected
"""
def setUp(self):
self.markov = Markov(prefix="testclass",db=11)
def test_add_line_to_index(self):
line = ['i','ate','a','peach']
line1 = ['i','ate','one','peach']
line2 = ['i','ate','a', 'sandwich']
self.markov.add_line_to_index(line)
self.markov.add_line_to_index(line1)
self.markov.add_line_to_index(line2)
self.assertEqual(self.markov.client.zscore("testclass:i:ate", "a"), 2.0)
self.assertEqual(self.markov.client.zscore("testclass:ate:a", "peach"), 1.0)
def test_score_for_line(self):
self.test_add_line_to_index()
line = ['i','ate','a','peach']
self.assertEqual(self.markov.score_for_line(line), 100)
def test_generate(self):
self.test_add_line_to_index()
generated = self.markov.generate(max_words=3)
assert len(generated) >= 2
assert len(generated) <= 3
generated = self.markov.generate(seed=['ate','one'], max_words=3)
assert 'peach' in generated
assert 'sandwich' not in generated
def tearDown(self):
"""
clean up our redis keys
"""
keys = self.markov.client.keys(self.markov.prefix+"*")
for key in keys:
self.markov.client.delete(key)
def caption(username, start, end):
scraper = Scraper(username, start, end)
text = scraper.text
try:
markov = Markov(text)
except:
if len(text) < 1:
return "Username not found or private account"
return "Not enough captions found to generate new text"
text = markov.generate()
if text == None or len(text) < 1:
text = "Not enough captions found to generate new text"
return text
def newTweet():
tweet_data = Markov(prefix="tweets")
tweetline = tweet_data.generate()
tweet = ""
for word in tweetline:
tweet += word + " "
tweet = tweet.rstrip()
if len(tweet) > 140:
return newTweet()
else:
return tweet
def newTweet():
tweet_data = Markov(prefix="tweets")
tweetline = tweet_data.generate()
tweet = ""
for word in tweetline:
tweet += word + " "
tweet = tweet.rstrip()
if len(tweet)>140:
return newTweet()
else:
return tweet
class TestMarkov(unittest.TestCase):
"""test class of markov.py"""
def setUp(self):
print('*** setup ***')
self.markov = Markov()
def test_add_sentense(self):
self.__add_sentense_bocchan()
self.assertTrue(len(self.markov.starts) > 0)
self.assertTrue(len(self.markov.dic) > 0)
def test_generate(self):
self.__add_sentense_bocchan()
input_texts = [
'初めまして、坊ちゃん', 'あら、ご病気ですか', 'あらあら、大変ですね', 'いたずらして病気になっちゃったんですか？',
'そんな威張らなくてもいいでしょう', 'はあ、そんなもんですか', '遅刻しちゃだめですね', 'よく覚えてないんですか？',
'ターナー？', 'どなたですか？'
]
for input_text in input_texts:
with self.subTest():
tokens = Morph.analyze(input_text)
keyword = 'N/A'
for token in tokens:
if Morph.is_keyword(token):
keyword = token.surface
generated = self.markov.generate(keyword)
print('you > ' + input_text)
print('generated > ' + generated)
print('************')
self.assertTrue(len(generated) > 0)
# private method
def __add_sentense_bocchan(self):
sample_file = '../KOISURU_PROGRAM/sample/markov/bocchan.txt'
content = ''
original_content = codecs.open(sample_file, 'r', 'shift_jis')
for row in original_content:
content += row.rstrip()
original_content.close()
texts = re.split(r'[。?？!！ ]+', content)
for text in texts:
if text == '':
continue
tokens = Morph.analyze(text)
self.markov.add_sentence(tokens)
print('.', end='')
print('')
def tweet(userName):
twitter = OAuth1Session(settings.CONSUMER_KEY, settings.CONSUMER_SECRET,
settings.ACCESS_TOKEN,
settings.ACCESS_TOKEN_SECRET)
markov = Markov()
tweets = markov.generate()
randomtweet = tweets
#randomtweet = tweets[random.randrange(len(tweets))]
params = {"status": randomtweet}
#params = {"status": '@' + userName + ' ' + randomtweet + ' ' + str(datetime.datetime.today())}
req = twitter.post("https://api.twitter.com/1.1/statuses/update.json",
params=params)
def response(self, parts):
markov = Markov()
keyword = next((w for w, p in parts if is_keyword(p)), '')
response = markov.generate(keyword)
return response
class TestMarkovClass(unittest.TestCase):
"""
Test that the Markov wrapper class behaves as expected
"""
def setUp(self):
self.markov = Markov(prefix="testclass", db=11)
def test_add_line_to_index(self):
line = ['i', 'ate', 'a', 'peach']
line1 = ['i', 'ate', 'one', 'peach']
line2 = ['i', 'ate', 'a', 'sandwich']
self.markov.add_line_to_index(line)
self.markov.add_line_to_index(line1)
self.markov.add_line_to_index(line2)
self.assertEqual(self.markov.client.zscore("testclass:i:ate", "a"),
2.0)
self.assertEqual(self.markov.client.zscore("testclass:ate:a", "peach"),
1.0)
def test_score_for_line(self):
self.test_add_line_to_index()
line = ['i', 'ate', 'a', 'peach']
self.assertEqual(self.markov.score_for_line(line), 100)
def test_generate(self):
self.test_add_line_to_index()
generated = self.markov.generate(max_words=3)
assert len(generated) >= 2
assert len(generated) <= 3
generated = self.markov.generate(seed=['ate', 'one'], max_words=3)
assert 'peach' in generated
assert 'sandwich' not in generated
def test_flush(self):
m1 = Markov(prefix="one", db=5)
m2 = Markov(prefix="two", db=5)
line = ['i', 'ate', 'a', 'peach']
line1 = ['i', 'ate', 'one', 'peach']
line2 = ['i', 'ate', 'a', 'sandwich']
m1.add_line_to_index(line)
m1.add_line_to_index(line1)
m1.add_line_to_index(line2)
important_line = ['we', 'all', 'have', 'phones']
m2.add_line_to_index(important_line)
r = redis.Redis(db=5)
assert len(r.keys("one:*")) == 6
assert len(r.keys("two:*")) == 3
m1.flush(prefix="one")
assert len(r.keys("one:*")) == 0
assert len(r.keys("two:*")) == 3
m2.flush(prefix="two")
assert len(r.keys("one:*")) == 0
assert len(r.keys("two:*")) == 0
def tearDown(self):
"""
clean up our redis keys
"""
keys = self.markov.client.keys(self.markov.prefix + "*")
for key in keys:
self.markov.client.delete(key)
send(str(random.randint(fd, sd)), '', event.chat_id)
else:
send('Хочешь наебать меня, дешёвка?', '',
event.chat_id)
else:
send('Хочешь наебать меня, дешёвка?', '', event.chat_id)
elif (newMessageLower[:12] == "мойша марков"):
n = newMessageLower[13:]
if n.isdigit():
n = int(n)
if (n < 1) or (n > 9):
send('Неверный размер окна, иди нахуй, дешёвка', '',
event.chat_id)
else:
moysha = Markov('dict', n)
answer = moysha.generate(n)
send(answer, '', event.chat_id)
else:
moysha = Markov('dict', 4)
answer = moysha.generate(query=newMessageLower[13:])
send(
'> ' + newMessageLower[13:].capitalize() + '\n> ' + answer,
'', event.chat_id)
elif (random.randint(0, 10) <= -3) and (newMessageLower[-1] == '?'):
send('Мойша услышал Ваш вопрос... Мойша думает...', '',
event.chat_id)
moysha = Markov('dict', 4)
answer = moysha.generate(query=newMessageLower[:-1])
send('> ' + newMessageLower.capitalize() + '\n> ' + answer, '',
event.chat_id)
elif (newMessageLower[:9] == "расшифруй"): # Расшифровка
class TestMarkovClass(unittest.TestCase):
"""
Test that the Markov wrapper class behaves as expected
"""
def setUp(self):
self.markov = Markov(prefix="testclass", db=11)
def test_add_line_to_index(self):
line = ['i','ate','a','peach']
line1 = ['i','ate','one','peach']
line2 = ['i','ate','a', 'sandwich']
self.markov.add_line_to_index(line)
self.markov.add_line_to_index(line1)
self.markov.add_line_to_index(line2)
self.assertEqual(self.markov.client.zscore("testclass:i:ate", "a"), 2.0)
self.assertEqual(self.markov.client.zscore("testclass:ate:a", "peach"), 1.0)
def test_score_for_line(self):
self.test_add_line_to_index()
line = ['i','ate','a','peach']
self.assertEqual(self.markov.score_for_line(line), 100)
def test_generate(self):
self.test_add_line_to_index()
generated = self.markov.generate(max_words=3)
assert len(generated) >= 2
assert len(generated) <= 3
generated = self.markov.generate(seed=['ate','one'], max_words=3)
assert 'peach' in generated
assert 'sandwich' not in generated
def test_flush(self):
m1 = Markov(prefix="one", db=5)
m2 = Markov(prefix="two", db=5)
line = ['i','ate','a','peach']
line1 = ['i','ate','one','peach']
line2 = ['i','ate','a', 'sandwich']
m1.add_line_to_index(line)
m1.add_line_to_index(line1)
m1.add_line_to_index(line2)
important_line = ['we', 'all', 'have', 'phones']
m2.add_line_to_index(important_line)
r = redis.Redis(db=5)
assert len(r.keys("one:*")) == 6
assert len(r.keys("two:*")) == 3
m1.flush(prefix="one")
assert len(r.keys("one:*")) == 0
assert len(r.keys("two:*")) == 3
m2.flush(prefix="two")
assert len(r.keys("one:*")) == 0
assert len(r.keys("two:*")) == 0
def tearDown(self):
"""
clean up our redis keys
"""
keys = self.markov.client.keys(self.markov.prefix+"*")
for key in keys:
self.markov.client.delete(key)
def make_tweet(target): target_data = Markov(target) output_tweet = target_data.generate(max_words=10) return output_tweet
