def test_markov_with_higher_level(size=100, file_name="sample1.txt"):
markov = Markov()
mark = markov.train_model_higher(
normalize(os.getcwd() + "\\samples\\" + file_name))
text = markov.generate_sentence(size, mark)
save_text(text)
save_long_file(text, file_name)
print(text)
def main(argv):
update_data = False
generate_sentences = False
interactive_mode = False
if len(argv) < 2:
print("No params specified. Using default values.")
argv.extend(("-u", "-g"))
args_dict = { i : True for i in argv }
if "-u" in args_dict:
update_data = True
if "-g" in args_dict:
generate_sentences = True
if "-h" in args_dict:
print(get_help_info())
return
if "-a" in args_dict:
print(get_about_info())
return
if "-i" in args_dict:
interactive_mode = True
if update_data:
dirname = "rawdata"
shutil.rmtree(dirname, ignore_errors=True)
filename = "news.zip"
yesterday = datetime.date.today() - datetime.timedelta(days=1)
network.download_file(network.URL.format(yesterday), filename)
with zipfile.ZipFile(filename, 'r') as zip_ref:
zip_ref.extractall(dirname)
parse_files(dirname + "/day")
if generate_sentences:
markov = Markov(OUTFILE)
markov.get_sentences()
if interactive_mode:
markov = Markov(OUTFILE)
outfile = open(GOODFILE, 'a', encoding="utf-8") # TODO: post these news
while True:
sentence = markov.generate_sentence()
print(sentence)
user_input = getch()
if user_input == "\x1b":
break
elif user_input == "+":
outfile.write(sentence + "\n")
pass
outfile.close()
class TestMarkovMethods(unittest.TestCase):
"""Test the Markov-Chain."""
def setUp(self):
"""Set up a Markov Chain instance for testing."""
self.m = Markov()
def test_new_word_entry(self):
"""Make sure that a new word and its next word are properly entered."""
self.m.add_next_word('hello', 'world')
self.assertEqual(self.m.chain, {'hello': ['world']})
def test_additional_next_word_entry(self):
"""Test insertion of a new next word for an existing current word."""
self.m.add_next_word('hello', 'world')
self.m.add_next_word('hello', 'you')
self.assertEqual(self.m.chain, {'hello': ['world', 'you']})
def test_paragraph_entry(self):
"""
Test insertion of a paragraph into the chains.
Verify the logic concerning the period.
"""
self.m.add_text(['hello', 'world', '.', 'goodnight', 'moon', '.'])
self.assertEqual(self.m.chain, {
'.': ['hello', 'goodnight'],
'hello': ['world'],
'world': ['.'],
'goodnight': ['moon'],
'moon': ['.']})
def test_sentence_generation(self):
"""Test traversing through Markov-Chain dict to create sentence."""
self.m.add_text(['hello', 'world', '.'])
self.m.add_text(['hello', 'you', '.'])
self.assertIn(
self.m.generate_sentence(4), ['hello world.', 'hello you.'])
def gen_markov_higher(lst, size=100, file_name="sample1.txt"):
markov = Markov()
mark = markov.train_model_higher(normalize(os.getcwd() + "\\samples\\" + file_name))
for i in range(30):
lst.append(markov.generate_sentence(size, mark))
return lst
