def setUp(self):
word_scores = os.path.join(data_path, "test_word_scores_big.csv")
self.parallel_corpus = os.path.join(data_path, "parallel-en-es.txt")
# Documents
A, B = parallel_corpus_to_documents(self.parallel_corpus)
self.document_a = A[:30]
self.document_b = B[:30]
training = training_alignments_from_documents(self.document_a,
self.document_b)
# Word score
word_pair_score = WordPairScore(word_scores)
# Sentence Score
sentence_pair_score = SentencePairScore()
sentence_pair_score.train(training, word_pair_score)
# Yalign model
document_aligner = SequenceAligner(sentence_pair_score, 0.49)
self.model = YalignModel(document_aligner)
def setUp(self):
random.seed(hash("Y U NO?"))
base_path = os.path.dirname(os.path.abspath(__file__))
word_scores = os.path.join(base_path, "data",
"test_word_scores_big.csv")
parallel_corpus = os.path.join(base_path, "data", "parallel-en-es.txt")
A, B = parallel_corpus_to_documents(parallel_corpus)
A = A[:25]
B = B[:25]
self.alignments = list(training_alignments_from_documents(A, B))
self.A, self.B, self.correct_alignments = \
list(training_scrambling_from_documents(A, B))
# Word score
word_pair_score = WordPairScore(word_scores)
# Sentence Score
sentence_pair_score = SentencePairScore()
sentence_pair_score.train(self.alignments, word_pair_score)
# Yalign model
self.min_ = sentence_pair_score.min_bound
self.max_ = sentence_pair_score.max_bound
gap_penalty = (self.min_ + self.max_) / 2.0
document_aligner = SequenceAligner(sentence_pair_score, gap_penalty)
self.model = YalignModel(document_aligner, 1)
