def train():
model = CNN(num_used_hists, num_words, num_word_embedding_dims)
model.create_model()
model.get_model_summary()
print('loading doc embedding...')
mp_doc_embedding = my_utils.read_pkl(
config['DEFAULT']['path_all_news_doc_embedding'])
print('constructing input data...')
train_news_ids = get_train_news_ids()
user_in = []
article_in = []
truth = []
for user_id, clicked_news_ids in tqdm(mp_train_hist.items()):
user_embedding = []
if len(clicked_news_ids) > num_used_hists:
for news_id in clicked_news_ids[:num_used_hists]:
user_embedding.append(mp_doc_embedding[news_id])
for news_id in clicked_news_ids[num_used_hists:]:
article_in.append(mp_doc_embedding[news_id])
user_in.append(user_embedding)
truth.append(1)
for i in range(num_train_negatives):
article_in.append(mp_doc_embedding[get_negative_news_id(
train_news_ids, user_id)])
user_in.append(user_embedding)
truth.append(0)
else:
for news_id in clicked_news_ids[:-1]:
user_embedding.append(mp_doc_embedding[news_id])
num_paddings = num_used_hists - len(user_embedding)
for i in range(num_paddings):
user_embedding.append(
np.zeros((num_words, num_word_embedding_dims)))
article_in.append(mp_doc_embedding[clicked_news_ids[-1]])
user_in.append(user_embedding)
truth.append(1)
for i in range(num_train_negatives):
article_in.append(mp_doc_embedding[get_negative_news_id(
train_news_ids, user_id)])
user_in.append(user_embedding)
truth.append(0)
print('reshaping input data...')
user_in = np.array(user_in)
article_in = np.array(article_in)
user_in = np.resize(user_in, (user_in.shape[0], 1) + user_in.shape[1:])
article_in = np.resize(article_in,
(article_in.shape[0], 1) + article_in.shape[1:])
print('start training...')
model.fit_model([user_in, article_in], np.array(truth), sample_batch_size,
num_epochs)
