def test_model_dkn(resource_path):
data_path = os.path.join(resource_path, "..", "resources", "deeprec",
"dkn")
yaml_file = os.path.join(data_path, "dkn.yaml")
train_file = os.path.join(data_path, "final_test_with_entity.txt")
valid_file = os.path.join(data_path, "final_test_with_entity.txt")
wordEmb_file = os.path.join(data_path, "word_embeddings_100.npy")
entityEmb_file = os.path.join(data_path, "TransE_entity2vec_100.npy")
if not os.path.exists(yaml_file):
download_deeprec_resources(
"https://recodatasets.blob.core.windows.net/deeprec/",
data_path,
"dknresources.zip",
)
hparams = prepare_hparams(
yaml_file,
wordEmb_file=wordEmb_file,
entityEmb_file=entityEmb_file,
epochs=1,
learning_rate=0.0001,
)
input_creator = DKNTextIterator
model = DKN(hparams, input_creator)
assert isinstance(model.fit(train_file, valid_file), BaseModel)
assert model.run_eval(valid_file) is not None
def test_model_dkn(resource_path):
data_path = os.path.join(resource_path, "..", "resources", "deeprec",
"dkn")
yaml_file = os.path.join(data_path, r'dkn.yaml')
train_file = os.path.join(data_path, r'train_mind_demo.txt')
valid_file = os.path.join(data_path, r'valid_mind_demo.txt')
test_file = os.path.join(data_path, r'test_mind_demo.txt')
news_feature_file = os.path.join(data_path, r'doc_feature.txt')
user_history_file = os.path.join(data_path, r'user_history.txt')
wordEmb_file = os.path.join(data_path, r'word_embeddings_100.npy')
entityEmb_file = os.path.join(data_path, r'TransE_entity2vec_100.npy')
contextEmb_file = os.path.join(data_path, r'TransE_context2vec_100.npy')
download_deeprec_resources(
"https://recodatasets.blob.core.windows.net/deeprec/",
data_path,
"mind-demo.zip",
)
hparams = prepare_hparams(yaml_file,
news_feature_file=news_feature_file,
user_history_file=user_history_file,
wordEmb_file=wordEmb_file,
entityEmb_file=entityEmb_file,
contextEmb_file=contextEmb_file,
epochs=1,
learning_rate=0.0001)
input_creator = DKNTextIterator
model = DKN(hparams, input_creator)
assert isinstance(model.fit(train_file, valid_file), BaseModel)
assert model.run_eval(valid_file) is not None
def test_model_dkn(resource_path):
data_path = os.path.join(resource_path, "..", "resources", "deeprec", "dkn")
yaml_file = os.path.join(data_path, "dkn.yaml")
train_file = os.path.join(data_path, "final_test_with_entity.txt")
valid_file = os.path.join(data_path, "final_test_with_entity.txt")
wordEmb_file = os.path.join(data_path, "word_embeddings_100.npy")
entityEmb_file = os.path.join(data_path, "TransE_entity2vec_100.npy")
if not os.path.exists(yaml_file):
download_deeprec_resources(
"https://recodatasets.blob.core.windows.net/deeprec/",
data_path,
"dknresources.zip",
)
hparams = prepare_hparams(
yaml_file,
wordEmb_file=wordEmb_file,
entityEmb_file=entityEmb_file,
epochs=1,
learning_rate=0.0001,
)
input_creator = DKNTextIterator
model = DKN(hparams, input_creator)
assert isinstance(model.fit(train_file, valid_file), BaseModel)
assert model.run_eval(valid_file) is not None
def test_model_dkn(resource_path):
data_path = os.path.join(resource_path, '../resources/deeprec/dkn')
yaml_file = os.path.join(data_path, r'dkn.yaml')
train_file = os.path.join(data_path, r'final_test_with_entity.txt')
valid_file = os.path.join(data_path, r'final_test_with_entity.txt')
wordEmb_file = os.path.join(data_path, r'word_embeddings_100.npy')
entityEmb_file = os.path.join(data_path, r'TransE_entity2vec_100.npy')
if not os.path.exists(yaml_file):
download_deeprec_resources(
r'https://recodatasets.blob.core.windows.net/deeprec/', data_path,
'dknresources.zip')
hparams = prepare_hparams(yaml_file,
wordEmb_file=wordEmb_file,
entityEmb_file=entityEmb_file,
epochs=1,
learning_rate=0.0001)
input_creator = DKNTextIterator
model = DKN(hparams, input_creator)
assert (isinstance(model.fit(train_file, valid_file), BaseModel))
assert model.run_eval(valid_file) is not None
# news_entities,
# train_entities,
# valid_entities,
# max_sentence=10,
# word_embedding_dim=100,
# )
news_feature_file = os.path.join(data_path, 'doc_feature.txt')
word_embeddings_file = os.path.join(data_path, 'word_embeddings_5w_100.npy')
user_history_file = os.path.join(data_path, 'user_history.txt')
entity_embeddings_file = os.path.join(data_path,
'entity_embeddings_5w_100.npy')
yaml_file = os.path.join(data_path, 'dkn_MINDlarge.yaml')
# yaml_file = maybe_download(url="https://recodatasets.blob.core.windows.net/deeprec/deeprec/dkn/dkn_MINDsmall.yaml",
# work_directory=data_path)
hparams = prepare_hparams(yaml_file,
news_feature_file=news_feature_file,
user_history_file=user_history_file,
wordEmb_file=word_embeddings_file,
entityEmb_file=entity_embeddings_file,
epochs=epochs,
history_size=history_size,
MODEL_DIR=os.path.join(data_path, 'save_models'),
batch_size=batch_size)
model = DKN(hparams, DKNTextIterator)
model.fit(train_file, valid_file)
res = model.run_eval(valid_file)
print(res)
if not os.path.exists(yaml_file):
download_deeprec_resources(r'https://recodatasets.blob.core.windows.net/deeprec/', data_path1, 'mind-demo-dkn.zip')
## Create hyper-parameters
epochs = 10
history_size = 50
batch_size = 100
hparams = prepare_hparams(yaml_file,
news_feature_file = news_feature_file,
user_history_file = user_history_file,
wordEmb_file=wordEmb_file,
entityEmb_file=entityEmb_file,
contextEmb_file=contextEmb_file,
epochs=epochs,
history_size=history_size,
batch_size=batch_size)
print(hparams)
## Train the DKN model
model = DKN(hparams, DKNTextIterator)
print(model.run_eval(valid_file))
model.fit(train_file, valid_file)
## Evaluate the DKN model
res = model.run_eval(test_file)
print(res)
pm.record("res", res)