# initialize objects
print('Initializing objects ...')
print('Initializing word embeddings ...')
t1 = time.time()
word_embeddings = WordEmbeddings(word_embeddings_file_path)
t2 = time.time()
print('\tTook %f seconds' % (t2 - t1))
print('Initializing tokenizer ...')
tokenizer = Tokenizer()
print('Initializing vectorizer ...')
vectorizer = Vectorizer(word_embeddings, tokenizer)
#### testing dataset ####
print('Vectorizing testing dataset ...')
ids, test_a_vectors, test_b_vectors, test_gold = vectorizer.vectorize_df(
test_df)
test_max_a_length = len(max(test_a_vectors, key=len))
test_max_b_length = len(max(test_b_vectors, key=len))
print('maximum number of tokens per sentence A in testing set is %d' %
test_max_a_length)
print('maximum number of tokens per sentence B in testing set is %d' %
test_max_b_length)
max_len = max([test_max_a_length, test_max_b_length])
# padding
print('Padding testing dataset ...')
test_a_vectors = pad_tensor(test_a_vectors, max_len)
test_b_vectors = pad_tensor(test_b_vectors, max_len)
print('Loading the model ...')
siamese = SiameseModel(False)
# initialize objects
print('Initializing objects ...')
print('Initializing word embeddings ...')
t1 = time.time()
word_embeddings = WordEmbeddings(word_embeddings_file_path)
t2 = time.time()
print('\tTook %f seconds' % (t2 - t1))
print('Initializing tokenizer ...')
tokenizer = Tokenizer()
print('Initializing vectorizer ...')
vectorizer = Vectorizer(word_embeddings, tokenizer)
#### training dataset ####
# vectorizing
ids, train_a_vectors, train_b_vectors, train_gold = vectorizer.vectorize_df(df)
train_max_a_length = len(max(train_a_vectors, key=len))
train_max_b_length = len(max(train_b_vectors, key=len))
print('maximum number of tokens per sentence A in training set is %d' %
train_max_a_length)
print('maximum number of tokens per sentence B in training set is %d' %
train_max_b_length)
max_len = max([train_max_a_length, train_max_b_length])
# padding
train_a_vectors = pad_tensor(train_a_vectors, max_len)
train_b_vectors = pad_tensor(train_b_vectors, max_len)
print('Training the model ...')
siamese = SiameseModel()
validation_data = None
# initialize objects
print('Initializing objects ...')
print('Initializing word embeddings ...')
t1 = time.time()
word_embeddings = WordEmbeddings(word_embeddings_file_path)
t2 = time.time()
print('\tTook %f seconds' % (t2 - t1))
print('Initializing tokenizer ...')
tokenizer = Tokenizer()
print('Initializing vectorizer ...')
vectorizer = Vectorizer(word_embeddings, tokenizer)
#### training dataset ####
# vectorizing
train_a_vectors, train_b_vectors, train_gold = vectorizer.vectorize_df(train_df)
train_max_a_length = len(max(train_a_vectors, key=len))
train_max_b_length = len(max(train_b_vectors, key=len))
print('maximum number of tokens per sentence A in training set is %d' % train_max_a_length)
print('maximum number of tokens per sentence B in training set is %d' % train_max_b_length)
max_len = max([train_max_a_length, train_max_b_length])
# padding
train_a_vectors = pad_tensor(train_a_vectors, max_len)
train_b_vectors = pad_tensor(train_b_vectors, max_len)
#### development dataset ####
# vectorizing
dev_a_vectors, dev_b_vectors, dev_gold = vectorizer.vectorize_df(dev_df)
dev_max_a_length = len(max(dev_a_vectors, key=len))
