def test_stratified_splitter(test_specs, python_dataset):
splits = python_stratified_split(python_dataset,
ratio=test_specs["ratio"],
min_rating=10,
filter_by="user")
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratio"], test_specs["tolerance"])
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
1 - test_specs["ratio"], test_specs["tolerance"])
for split in splits:
assert set(split.columns) == set(python_dataset.columns)
# Test if both contains the same user list. This is because stratified split is stratified.
users_train = splits[0][DEFAULT_USER_COL].unique()
users_test = splits[1][DEFAULT_USER_COL].unique()
assert set(users_train) == set(users_test)
splits = python_stratified_split(python_dataset,
ratio=test_specs["ratios"],
min_rating=10,
filter_by="user")
assert len(splits) == 3
assert len(splits[0]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][0], test_specs["tolerance"])
assert len(splits[1]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][1], test_specs["tolerance"])
assert len(splits[2]) / test_specs["number_of_rows"] == pytest.approx(
test_specs["ratios"][2], test_specs["tolerance"])
for split in splits:
assert set(split.columns) == set(python_dataset.columns)
def test_model_lightgcn(deeprec_resource_path, deeprec_config_path):
data_path = os.path.join(deeprec_resource_path, "dkn")
yaml_file = os.path.join(deeprec_config_path, "lightgcn.yaml")
user_file = os.path.join(data_path, r"user_embeddings.csv")
item_file = os.path.join(data_path, r"item_embeddings.csv")
df = movielens.load_pandas_df(size="100k")
train, test = python_stratified_split(df, ratio=0.75)
data = ImplicitCF(train=train, test=test)
hparams = prepare_hparams(yaml_file, epochs=1)
model = LightGCN(hparams, data)
assert model.run_eval() is not None
model.fit()
assert model.recommend_k_items(test) is not None
model.infer_embedding(user_file, item_file)
assert os.path.getsize(user_file) != 0
assert os.path.getsize(item_file) != 0
def test_lightgcn_component_definition(deeprec_config_path):
yaml_file = os.path.join(deeprec_config_path, "lightgcn.yaml")
df = movielens.load_pandas_df(size="100k")
train, test = python_stratified_split(df, ratio=0.75)
data = ImplicitCF(train=train, test=test)
embed_size = 64
hparams = prepare_hparams(yaml_file, embed_size=embed_size)
model = LightGCN(hparams, data)
assert model.norm_adj is not None
assert model.ua_embeddings.shape == [data.n_users, embed_size]
assert model.ia_embeddings.shape == [data.n_items, embed_size]
assert model.u_g_embeddings is not None
assert model.pos_i_g_embeddings is not None
assert model.neg_i_g_embeddings is not None
assert model.batch_ratings is not None
assert model.loss is not None
assert model.opt is not None
seed = args.seed
logger.debug(f"Received parameters:")
logger.debug(f"Ratio: {ratio}")
logger.debug(f"User: {col_user}")
logger.debug(f"Item: {col_item}")
logger.debug(f"Seed: {seed}")
logger.debug(f"Input path: {args.input_path}")
logger.debug(f"Shape of loaded DataFrame: {input_df.shape}")
logger.debug(f"Cols of DataFrame: {input_df.columns}")
output_train, output_test = python_stratified_split(
input_df,
ratio=args.ratio,
col_user=args.col_user,
col_item=args.col_item,
seed=args.seed,
)
logger.debug(f"Output path: {args.output_train}")
logger.debug(f"Output path: {args.output_test}")
save_data_frame_to_directory(
args.output_train,
output_train,
schema=DataFrameSchema.data_frame_to_dict(output_train),
)
save_data_frame_to_directory(
args.output_test,
output_test,