def test_model_npa(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"lstur.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 = LSTURModel(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_lstur_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"lstur.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, "mind", "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 = LSTURModel(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_lstur(tmp):
yaml_file = os.path.join(tmp, "lstur.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,
"lstur.zip")
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, epochs=1)
assert hparams is not None
iterator = NewsIterator
model = LSTURModel(hparams, iterator)
assert model.run_eval(valid_file) is not None
assert isinstance(model.fit(train_file, valid_file), BaseModel)
def test_lstur_component_definition(tmp):
yaml_file = os.path.join(tmp, "lstur.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,
"lstur.zip")
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, epochs=1)
iterator = NewsIterator
model = LSTURModel(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
if not os.path.exists(yaml_file):
print("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)
## Create hyper-parameters
hparams = prepare_hparams(yaml_file, wordEmb_file=wordEmb_file, \
wordDict_file=wordDict_file, userDict_file=userDict_file, epochs=epochs)
print('hparams:', hparams)
# We generate a word_dict file to tranform words in news title to word indexes, and a embedding matrix is initted from pretrained glove embeddings.
# 我们生成一个word_dict文件，将新闻标题中的单词转换为单词索引，并从预先训练的glove嵌入中初始化embedding矩阵。
iterator = MINDIterator
## Train the LSTUR model
model = LSTURModel(hparams, iterator, seed=seed)
print(
model.run_eval(valid_news_file,
valid_behaviors_file)) # news:18723, behaviors:7538(多了第一列)
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)
## Save the model
model_path = os.path.join(data_path, "model")
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"))
# group_impr_indexes, group_labels, group_preds = model.run_slow_eval(test_news_file, test_behaviors_file)
# res = cal_metric(group_labels, group_preds, hparams.metrics)