def test_evalutate_decoding_complete_eng(self):
decoded_text = base_text = 'This is a sample text.'
alphabet = textstatistics.get_char_frequencies(base_text)
dictionary = textstatistics.get_word_frequencies(base_text)
language = textstatistics.Languauge(alphabet, dictionary)
result = decode.evalutate_decoding(decoded_text, language)
self.assertEqual(result, 1.0)
def test_evalutate_decoding_complete_eng(self):
decoded_text = base_text = 'This is a sample text.'
alphabet = textstatistics.get_char_frequencies(base_text)
dictionary = textstatistics.get_word_frequencies(base_text)
language = textstatistics.Languauge(alphabet, dictionary)
result = decode.evalutate_decoding(decoded_text, language)
self.assertEqual(result, 1.0)
def test_evalutate_decoding_almost_eng(self):
base_text = 'This is a sample text.'
decoded_text = 'Thas as i simple text.'
alphabet = textstatistics.get_char_frequencies(base_text)
dictionary = textstatistics.get_word_frequencies(base_text)
language = textstatistics.Languauge(alphabet, dictionary)
result = decode.evalutate_decoding(decoded_text, language)
self.assertTrue(result < 1.0 and result > 0.5)
def test_evalutate_decoding_almost_eng(self):
base_text = 'This is a sample text.'
decoded_text = 'Thas as i simple text.'
alphabet = textstatistics.get_char_frequencies(base_text)
dictionary = textstatistics.get_word_frequencies(base_text)
language = textstatistics.Languauge(alphabet, dictionary)
result = decode.evalutate_decoding(decoded_text, language)
self.assertTrue(result < 1.0 and result > 0.5)
def test_evalutate_decoding_subset_eng(self):
base_text = 'This is a sample text.'
base_text_words = textstatistics.split_to_words(base_text)
decoded_text = ' '.join(base_text_words[:len(base_text_words) // 2])
alphabet = textstatistics.get_char_frequencies(base_text)
dictionary = textstatistics.get_word_frequencies(base_text)
language = textstatistics.Languauge(alphabet, dictionary)
result = decode.evalutate_decoding(decoded_text, language)
self.assertEqual(result, 1.0)
def test_evalutate_decoding_subset_eng(self):
base_text = 'This is a sample text.'
base_text_words = textstatistics.split_to_words(base_text)
decoded_text = ' '.join(base_text_words[: len(base_text_words) / 2])
alphabet = textstatistics.get_char_frequencies(base_text)
dictionary = textstatistics.get_word_frequencies(base_text)
language = textstatistics.Languauge(alphabet, dictionary)
result = decode.evalutate_decoding(decoded_text, language)
self.assertEqual(result, 1.0)
def setUp(self):
original_alphabet = list(u'абвгдеёжзийклмнопрстуфхцчшщъыьэюя')
self.original_text = data.QUOTE_FROM_ILF_AND_PETROV
alphabet = textstatistics.get_char_frequencies(self.original_text)
alphabet = {char: frequency for (char, frequency) in
alphabet.iteritems() if char in original_alphabet}
dictionary = textstatistics.get_word_frequencies(self.original_text)
self.language = textstatistics.Languauge(alphabet, dictionary)
actual_original_alphabet = alphabet.keys()
shuffled_alphabet = list(actual_original_alphabet)
random.seed(1001)
random.shuffle(shuffled_alphabet)
self.code = dict(zip(actual_original_alphabet, shuffled_alphabet))
def test_get_word_frequencies_russian(self):
text = QUOTE_FROM_TOLSTOY
expected = {
u'Не': 1,
u'слушайте': 1,
u'тех': 1,
u'кто': 1,
u'говорит': 1,
u'дурно': 1,
u'о': 2,
u'других': 1,
u'и': 1,
u'хорошо': 1,
u'вас': 1
}
result = textstatistics.get_word_frequencies(text)
self.assertDictEqual(result, expected)
def test_get_word_frequencies_russian(self):
text = QUOTE_FROM_TOLSTOY
expected = {
u'Не': 1,
u'слушайте': 1,
u'тех': 1,
u'кто': 1,
u'говорит': 1,
u'дурно': 1,
u'о': 2,
u'других': 1,
u'и': 1,
u'хорошо': 1,
u'вас': 1
}
result = textstatistics.get_word_frequencies(text)
self.assertDictEqual(result, expected)
def setUp(self):
original_alphabet = list(u'абвгдеёжзийклмнопрстуфхцчшщъыьэюя')
self.original_text = data.QUOTE_FROM_ILF_AND_PETROV
alphabet = textstatistics.get_char_frequencies(self.original_text)
alphabet = {
char: frequency
for (char, frequency) in alphabet.items()
if char in original_alphabet
}
dictionary = textstatistics.get_word_frequencies(self.original_text)
self.language = textstatistics.Languauge(alphabet, dictionary)
actual_original_alphabet = alphabet.keys()
shuffled_alphabet = list(actual_original_alphabet)
random.seed(1001)
random.shuffle(shuffled_alphabet)
self.code = dict(zip(actual_original_alphabet, shuffled_alphabet))
def test_get_word_frequencies_english(self):
text = QUOTE_FROM_SHAKESPEARE
expected = {'To': 1, 'be': 2, 'or': 1, 'not': 1, 'to': 1}
result = textstatistics.get_word_frequencies(text)
self.assertDictEqual(result, expected)
def test_get_word_frequencies_empty(self):
text = ''
expected = {}
result = textstatistics.get_word_frequencies(text)
self.assertEqual(result, expected)
def test_get_word_frequencies_english(self):
text = QUOTE_FROM_SHAKESPEARE
expected = {'To': 1, 'be': 2, 'or': 1, 'not': 1, 'to': 1}
result = textstatistics.get_word_frequencies(text)
self.assertDictEqual(result, expected)
def test_get_word_frequencies_empty(self):
text = ''
expected = {}
result = textstatistics.get_word_frequencies(text)
self.assertEqual(result, expected)