def test_load_pandas_df(
size,
num_samples,
num_movies,
movie_example,
title_example,
genres_example,
year_example,
tmp,
):
"""Test MovieLens dataset load as pd.DataFrame"""
# Test if correct data are loaded
header = ["a", "b", "c"]
df = load_pandas_df(size=size, local_cache_path=tmp, header=header)
assert len(df) == num_samples
assert len(df.columns) == len(header)
# Test if raw-zip file, rating file, and item file are cached
assert len(os.listdir(tmp)) == 3
# Test title, genres, and released year load
header = ["a", "b", "c", "d", "e"]
with pytest.warns(Warning):
df = load_pandas_df(
size=size,
header=header,
local_cache_path=tmp,
title_col="Title",
genres_col="Genres",
year_col="Year",
)
assert len(df) == num_samples
assert (
len(df.columns) == 7
) # 4 header columns (user, item, rating, timestamp) and 3 feature columns
assert "e" not in df.columns # only the first 4 header columns are used
# Get two records of the same items and check if the item-features are the same.
head = df.loc[df["b"] == movie_example][:2]
title = head["Title"].values
assert title[0] == title[1]
assert title[0] == title_example
genres = head["Genres"].values
assert genres[0] == genres[1]
assert genres[0] == genres_example
year = head["Year"].values
assert year[0] == year[1]
assert year[0] == year_example
# Test default arguments
df = load_pandas_df(size)
assert len(df) == num_samples
# user, item, rating and timestamp
assert len(df.columns) == 4
def test_load_pandas_df_mock_100__with_custom_param__succeed():
df = load_pandas_df(
"mock100", title_col=DEFAULT_TITLE_COL, genres_col=DEFAULT_GENRE_COL
)
assert type(df[DEFAULT_TITLE_COL]) == Series
assert type(df[DEFAULT_GENRE_COL]) == Series
assert len(df) == 100
assert "|" in df.loc[0, DEFAULT_GENRE_COL]
assert df.loc[0, DEFAULT_TITLE_COL] == "foo"
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
def test_load_pandas_df_mock_100__with_default_param__succeed():
df = load_pandas_df("mock100")
assert type(df) == pandas.DataFrame
assert len(df) == 100
assert not df[[DEFAULT_USER_COL, DEFAULT_ITEM_COL]].duplicated().any()