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_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)
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)
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)
model_name = model_type + '_ckpt'
model.fit(train_news_file, train_behaviors_file, valid_news_file, valid_behaviors_file,
model_path=model_path, model_name=model_name)
res_syn = model.run_eval(valid_news_file, valid_behaviors_file)
logging.info(res_syn)
# ## Reference
# \[1\] Wu et al. "Neural News Recommendation with Multi-Head Self-Attention." in Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)<br>
# \[2\] Wu, Fangzhao, et al. "MIND: A Large-scale Dataset for News Recommendation" Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. https://msnews.github.io/competition.html <br>
# \[3\] GloVe: Global Vectors for Word Representation. https://nlp.stanford.edu/projects/glove/
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"))
group_impr_indexes, group_labels, group_preds = model.run_fast_eval(