def test_model_nrms(mind_resource_path):
train_news_file = os.path.join(mind_resource_path, "train", r"news.tsv")
train_behaviors_file = os.path.join(mind_resource_path, "train",
r"behaviors.tsv")
valid_news_file = os.path.join(mind_resource_path, "valid", r"news.tsv")
valid_behaviors_file = os.path.join(mind_resource_path, "valid",
r"behaviors.tsv")
wordEmb_file = os.path.join(mind_resource_path, "utils", "embedding.npy")
userDict_file = os.path.join(mind_resource_path, "utils", "uid2index.pkl")
wordDict_file = os.path.join(mind_resource_path, "utils", "word_dict.pkl")
yaml_file = os.path.join(mind_resource_path, "utils", r"nrms.yaml")
if not os.path.exists(train_news_file):
download_deeprec_resources(
r"https://recodatasets.z20.web.core.windows.net/newsrec/",
os.path.join(mind_resource_path, "train"),
"MINDdemo_train.zip",
)
if not os.path.exists(valid_news_file):
download_deeprec_resources(
r"https://recodatasets.z20.web.core.windows.net/newsrec/",
os.path.join(mind_resource_path, "valid"),
"MINDdemo_dev.zip",
)
if not os.path.exists(yaml_file):
download_deeprec_resources(
r"https://recodatasets.z20.web.core.windows.net/newsrec/",
os.path.join(mind_resource_path, "utils"),
"MINDdemo_utils.zip",
)
hparams = prepare_hparams(
yaml_file,
wordEmb_file=wordEmb_file,
wordDict_file=wordDict_file,
userDict_file=userDict_file,
epochs=1,
)
assert hparams is not None
iterator = MINDIterator
model = NRMSModel(hparams, iterator)
assert model.run_eval(valid_news_file, valid_behaviors_file) is not None
assert isinstance(
model.fit(train_news_file, train_behaviors_file, valid_news_file,
valid_behaviors_file),
BaseModel,
)
def test_nrms_component_definition(mind_resource_path):
wordEmb_file = os.path.join(mind_resource_path, "utils", "embedding.npy")
userDict_file = os.path.join(mind_resource_path, "utils", "uid2index.pkl")
wordDict_file = os.path.join(mind_resource_path, "utils", "word_dict.pkl")
yaml_file = os.path.join(mind_resource_path, "utils", r"nrms.yaml")
if not os.path.exists(yaml_file):
download_deeprec_resources(
r"https://recodatasets.z20.web.core.windows.net/newsrec/",
os.path.join(mind_resource_path, "utils"),
"MINDdemo_utils.zip",
)
hparams = prepare_hparams(
yaml_file,
wordEmb_file=wordEmb_file,
wordDict_file=wordDict_file,
userDict_file=userDict_file,
epochs=1,
)
iterator = MINDIterator
model = NRMSModel(hparams, iterator)
assert model.model is not None
assert model.scorer is not None
assert model.loss is not None
assert model.train_optimizer is not None
def test_model_nrms(tmp):
yaml_file = os.path.join(tmp, "nrms.yaml")
train_file = os.path.join(tmp, "train.txt")
valid_file = os.path.join(tmp, "test.txt")
wordEmb_file = os.path.join(tmp, "embedding.npy")
if not os.path.exists(yaml_file):
download_deeprec_resources(
"https://recodatasets.blob.core.windows.net/newsrec/", tmp,
"nrms.zip")
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, epochs=1)
assert hparams is not None
iterator = NewsIterator
model = NRMSModel(hparams, iterator)
assert model.run_eval(valid_file) is not None
assert isinstance(model.fit(train_file, valid_file), BaseModel)
def dist_eval(args):
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed)
model.model.load_weights(
os.path.join(model_dir, "ckpt_ep{}".format(args.ep)))
test_news_file = os.path.join(data_path, "valid", 'news.tsv')
test_behaviors_file = os.path.join(data_path, "valid",
'behaviors.{}.tsv'.format(args.fsplit))
group_impr_indexes, group_labels, group_preds = model.run_slow_eval(
test_news_file, test_behaviors_file)
with open(
os.path.join(
data_path,
'results/nrms-valid-prediction.{}.txt'.format(args.fsplit)),
'w') as f:
for labels, preds in tqdm(zip(group_labels, group_preds)):
label_str = ",".join([str(x) for x in labels])
pred_str = ",".join([str(x) for x in preds])
f.write("{}\t{}\n".format(label_str, pred_str))
def test(args):
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed, test_mode=True)
model.model.load_weights(
os.path.join(model_dir, "ckpt_ep{}".format(args.ep)))
test_news_file = os.path.join(data_path, "test", 'news.tsv')
test_behaviors_file = os.path.join(data_path, "test",
'behaviors.{}.tsv'.format(args.fsplit))
group_impr_indexes, group_labels, group_preds = model.run_slow_eval(
test_news_file, test_behaviors_file)
with open(
os.path.join(
data_path,
'results/nrms-test-prediction.{}.txt'.format(args.fsplit)),
'w') as f:
for impr_index, preds in tqdm(zip(group_impr_indexes, group_preds)):
impr_index += 1
pred_rank = (np.argsort(np.argsort(preds)[::-1]) + 1).tolist()
pred_rank = '[' + ','.join([str(i) for i in pred_rank]) + ']'
f.write(' '.join([str(impr_index), pred_rank]) + '\n')
def test_nrms_component_definition(tmp):
yaml_file = os.path.join(tmp, "nrms.yaml")
wordEmb_file = os.path.join(tmp, "embedding.npy")
if not os.path.exists(yaml_file):
download_deeprec_resources(
"https://recodatasets.blob.core.windows.net/newsrec/", tmp,
"nrms.zip")
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, epochs=1)
iterator = NewsIterator
model = NRMSModel(hparams, iterator)
assert model.model is not None
assert model.scorer is not None
assert model.loss is not None
assert model.train_optimizer is not None
userDict_file = os.path.join(data_path, "utils", "uid2index.pkl")
wordDict_file = os.path.join(data_path, "utils", "word_dict_all.pkl")
yaml_file = os.path.join(data_path, "utils", r'nrms.yaml')
entityDict_file = os.path.join(data_path, "utils", "entity_dict_all.pkl")
entity_embedding_file = os.path.join(data_path, "utils", "entity_embeddings_5w_100_all.npy")
context_embedding_file = os.path.join(data_path, "utils", "context_embeddings_5w_100_all.npy")
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, \
wordDict_file=wordDict_file, userDict_file=userDict_file, \
epochs=epochs, entityEmb_file=entity_embedding_file, contextEmb_file=context_embedding_file, \
entityDict_file=entityDict_file,
show_step=10)
print(hparams)
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed)
model_path = os.path.join(data_path, "model")
model.model.load_weights(os.path.join(model_path, "my_nrms_ckpt"))
f = open(test_behaviors_file)
print('total test samples:', len(f.readlines()))
f.close()
group_impr_indexes, group_labels, group_preds = model.run_fast_eval(test_news_file, test_behaviors_file, test=1)
import numpy as np
from tqdm import tqdm
with open(os.path.join(data_path, 'my_prediction.txt'), 'w') as f:
for impr_index, preds in tqdm(zip(group_impr_indexes, group_preds)):
impr_index += 1
pred_rank = (np.argsort(np.argsort(preds)[::-1]) + 1).tolist()
download_deeprec_resources(mind_url, os.path.join(data_path, 'train'),
mind_train_dataset)
if not os.path.exists(valid_news_file):
download_deeprec_resources(mind_url, \
os.path.join(data_path, 'valid'), mind_dev_dataset)
if not os.path.exists(yaml_file):
download_deeprec_resources(r'https://recodatasets.blob.core.windows.net/newsrec/', \
os.path.join(data_path, 'utils'), mind_utils)
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, \
wordDict_file=wordDict_file, userDict_file=userDict_file, \
epochs=epochs,
show_step=10)
print("[NRMS] Config,", hparams)
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed)
print("[NRMS] First run:",
model.run_eval(valid_news_file, fast_valid_behaviors_file))
model.fit(train_news_file,
train_behaviors_file,
valid_news_file,
fast_valid_behaviors_file,
model_save_path=model_dir)
# res_syn = model.run_eval(valid_news_file, valid_behaviors_file)
# print(res_syn)
os.path.join(data_path, 'test'), mind_test_dataset)
if not os.path.exists(yaml_file):
download_deeprec_resources(r'https://recodatasets.blob.core.windows.net/newsrec/', \
os.path.join(data_path, 'utils'), mind_utils)
hparams = prepare_hparams(yaml_file,
wordEmb_file=wordEmb_file,
wordDict_file=wordDict_file,
userDict_file=userDict_file,
batch_size=batch_size,
epochs=epochs,
show_step=10)
print(hparams)
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed)
# print(model.run_eval(valid_news_file, valid_behaviors_file))
model.fit(train_news_file, train_behaviors_file, valid_news_file, valid_behaviors_file)
# res_syn = model.run_eval(valid_news_file, valid_behaviors_file)
# print(res_syn)
# pm.record("res_syn", res_syn)
model_path = os.path.join(model_path, "model")
os.makedirs(model_path, exist_ok=True)
model.model.save_weights(os.path.join(model_path, "nrms_ckpt"))
group_impr_indexes, group_labels, group_preds = model.run_slow_eval(test_news_file, test_behaviors_file)
wordDict_file=wordDict_file,
userDict_file=userDict_file,
vertDict_file=vertDict_file,
subvertDict_file=subvertDict_file,
batch_size=batch_size,
epochs=epochs,
show_step=10)
logging.info(hparams)
# ## Train the NRMS model
if model_type == 'nrms':
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed)
elif model_type == 'naml':
iterator = MINDAllIterator
model = NAMLModel(hparams, iterator, seed=seed)
elif model_type == 'npa':
iterator = MINDIterator
model = NPAModel(hparams, iterator, seed=seed)
elif model_type == 'nrmma':
iterator = MINDAllIterator
model = NRMMAModel(hparams, iterator, seed=seed)
else:
raise NotImplementedError(f"{exp_name} is not implemented")
# In[8]:
model_path = os.path.join(exp_path, model_type)
download_deeprec_resources(
r'https://recodatasets.blob.core.windows.net/newsrec/',
os.path.join(data_root, 'utils'), mind_utils)
hparams = prepare_hparams(yaml_file,
wordEmb_file=wordEmb_file,
wordDict_file=wordDict_file,
userDict_file=userDict_file,
batch_size=batch_size,
epochs=epochs,
show_step=10)
logger.debug(f"hparams: {hparams}")
iterator = MINDIterator
model = NRMSModel(hparams, iterator, seed=seed)
logger.info(model.run_eval(valid_news_file, valid_behaviors_file))
model.fit(train_news_file, train_behaviors_file, valid_news_file,
valid_behaviors_file)
res_syn = model.run_eval(valid_news_file, valid_behaviors_file)
logger.debug(f"res_syn: {res_syn}")
sb.glue("res_syn", res_syn)
model_path = os.path.join(BASE_DIR, "ckpt")
os.makedirs(model_path, exist_ok=True)
model.model.save_weights(os.path.join(model_path, "nrms_ckpt"))
# subvertDict_file = os.path.join(data_path, "utils", "subvert_dict.pkl")
# vertDict_file = os.path.join(data_path, "utils", "vert_dict.pkl")
yaml_file = os.path.join(data_path, "utils", '{}.yaml'.format(opt.model_name))
hparams = prepare_hparams(yaml_file,
wordEmb_file=wordEmb_file,
wordDict_file=wordDict_file,
userDict_file=userDict_file,
batch_size=batch_size,
epochs=epochs,
show_step=10)
print(hparams)
iterator = MINDIterator
if opt.model_name == 'nrms':
model = NRMSModel(hparams, iterator, seed=seed)
elif opt.model_name == 'npa': # model can not save
model = NPAModel(hparams, iterator, seed=seed)
elif opt.model_name == 'lstur':
model = LSTURModel(hparams, iterator, seed=seed)
elif opt.model_name == 'naml': # problematic
model = NAMLModel(hparams, iterator, seed=seed)
# print(model.run_slow_eval(news_file, valid_behaviors_file))
model.fit(news_file, train_behaviors_file, news_file, valid_behaviors_file)
# model_path = os.path.join(model_path, "model")
# os.makedirs(model_path, exist_ok=True)
# model.model.save_weights(os.path.join(model_path, "nrms_ckpt"))