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)