def test_Interactions_with_0_ratings(interactions_pandas, df_for_interactions_with_0_ratings):
with pytest.warns(UserWarning):
interactions_with_0s = Interactions(users=df_for_interactions_with_0_ratings['user_id'],
items=df_for_interactions_with_0_ratings['item_id'],
ratings=df_for_interactions_with_0_ratings['ratings'],
check_num_negative_samples_is_valid=False)
assert np.array_equal(interactions_pandas.toarray(), interactions_with_0s.toarray())
def test_Interactions(ratings_matrix_for_interactions,
sparse_ratings_matrix_for_interactions,
df_for_interactions):
interactions_1 = Interactions(mat=ratings_matrix_for_interactions,
check_num_negative_samples_is_valid=False)
interactions_2 = Interactions(mat=sparse_ratings_matrix_for_interactions,
check_num_negative_samples_is_valid=False)
interactions_3 = Interactions(users=df_for_interactions['user_id'],
items=df_for_interactions['item_id'],
ratings=df_for_interactions['rating'],
check_num_negative_samples_is_valid=False)
np.testing.assert_equal(interactions_1.toarray(), interactions_2.toarray())
np.testing.assert_equal(interactions_1.toarray(), interactions_3.toarray())
assert interactions_1.num_users == interactions_2.num_users == interactions_3.num_users
assert interactions_1.num_items == interactions_2.num_items == interactions_3.num_items
assert (interactions_1.num_interactions == interactions_2.num_interactions
== interactions_3.num_interactions)
def test_stratified_split(interactions_to_split):
train_expected_df = pd.DataFrame(
data={
'user_id': [0, 0, 0, 0, 0, 0, 1, 1, 2, 2, 3, 4, 4],
'item_id': [1, 2, 3, 4, 6, 8, 1, 2, 3, 4, 2, 4, 5],
'rating': [2, 3, 4, 5, 3, 1, 1, 2, 4, 5, 5, 5, 4],
})
train_expected = Interactions(
mat=coo_matrix(
(
train_expected_df['rating'],
(train_expected_df['user_id'], train_expected_df['item_id']),
),
shape=(interactions_to_split.num_users,
interactions_to_split.num_items),
),
allow_missing_ids=True,
check_num_negative_samples_is_valid=False,
)
validate_expected_df = pd.DataFrame(
data={
'user_id': [0, 1, 2, 3, 4],
'item_id': [7, 3, 2, 1, 2],
'rating': [2, 3, 3, 1, 3],
})
validate_expected = Interactions(
mat=coo_matrix(
(
validate_expected_df['rating'],
(validate_expected_df['user_id'],
validate_expected_df['item_id']),
),
shape=(interactions_to_split.num_users,
interactions_to_split.num_items),
),
allow_missing_ids=True,
check_num_negative_samples_is_valid=False,
)
test_expected_df = pd.DataFrame(
data={
'user_id': [0, 0, 1, 2, 3, 4],
'item_id': [0, 5, 4, 1, 4, 1],
'rating': [1, 4, 4, 2, 4, 2],
})
test_expected = Interactions(
mat=coo_matrix(
(
test_expected_df['rating'],
(test_expected_df['user_id'], test_expected_df['item_id']),
),
shape=(interactions_to_split.num_users,
interactions_to_split.num_items),
),
allow_missing_ids=True,
check_num_negative_samples_is_valid=False,
)
(train_actual, validate_actual,
test_actual) = stratified_split(interactions=interactions_to_split,
val_p=0.1,
test_p=0.2,
seed=46)
np.testing.assert_array_equal(train_actual.toarray(),
train_expected.toarray())
np.testing.assert_array_equal(validate_actual.toarray(),
validate_expected.toarray())
np.testing.assert_array_equal(test_actual.toarray(),
test_expected.toarray())
assert (train_actual.num_users == train_expected.num_users ==
validate_actual.num_users == validate_expected.num_users ==
test_actual.num_users == test_expected.num_users)
assert (train_actual.num_items == train_expected.num_items ==
validate_actual.num_items == validate_expected.num_items ==
test_actual.num_items == test_expected.num_items)