def test_init(self):
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map=OrderedDict(),
global_iid_map=OrderedDict(),
global_ui_set=set(),
verbose=True)
self.assertSequenceEqual(train_set.matrix.shape, (10, 10))
self.assertEqual(train_set.min_rating, 3)
self.assertEqual(train_set.max_rating, 5)
self.assertEqual(int(train_set.global_mean),
int((3 * 2 + 4 * 7 + 5) / 10))
npt.assert_array_equal(train_set.item_ppl_rank()[0],
np.asarray([7, 9, 6, 5, 3, 2, 1, 0, 8, 4]))
self.assertEqual(train_set.num_users, 10)
self.assertEqual(train_set.num_items, 10)
self.assertFalse(train_set.is_unk_user(7))
self.assertTrue(train_set.is_unk_user(13))
self.assertFalse(train_set.is_unk_item(3))
self.assertTrue(train_set.is_unk_item(16))
self.assertEqual(train_set.get_uid('768'), 1)
self.assertEqual(train_set.get_iid('195'), 7)
self.assertSequenceEqual(train_set.uid_list, range(10))
self.assertListEqual(train_set.raw_uid_list, [
'76', '768', '642', '930', '329', '633', '716', '871', '543', '754'
])
self.assertSequenceEqual(train_set.iid_list, range(10))
self.assertListEqual(train_set.raw_iid_list, [
'93', '257', '795', '709', '705', '226', '478', '195', '737', '282'
])
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map=OrderedDict(),
global_iid_map=OrderedDict(),
global_ui_set=set([('76', '93')]),
verbose=True)
self.assertEqual(train_set.num_users, 9)
self.assertEqual(train_set.num_items, 9)
def test_item_iter(self):
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map={},
global_iid_map={},
global_ui_set=set(),
verbose=True)
npt.assert_array_equal(
np.arange(10).reshape(10, 1), [i for i in train_set.item_iter()])
self.assertRaises(AssertionError, npt.assert_array_equal,
np.arange(10).reshape(10, 1),
[i for i in train_set.item_iter(shuffle=True)])
def test_matrix_trainset_uir_iter():
triplet_data = reader.read_uir('./tests/data.txt')
train_set = MatrixTrainSet.from_uir(triplet_data, global_uid_map={}, global_iid_map={},
global_ui_set=set(), verbose=True)
users = [batch_users for batch_users, _, _ in train_set.uir_iter()]
assert all([a == b for a, b in zip(users, range(10))])
items = [batch_items for _, batch_items, _ in train_set.uir_iter()]
assert all([a == b for a, b in zip(items, range(10))])
ratings = [batch_ratings for _, _, batch_ratings in train_set.uir_iter()]
assert all([a == b for a, b in zip(ratings, [4, 4, 4, 4, 3, 4, 4, 5, 3, 4])])
def test_matrix_trainset():
"""Test MatrixTrainSet"""
triplet_data = reader.read_uir('./tests/data.txt')
train_set = MatrixTrainSet.from_uir(triplet_data, global_uid_map={}, global_iid_map={}, global_ui_set=set(),
verbose=True)
assert train_set.matrix.shape == (10, 10)
assert train_set.min_rating == 3
assert train_set.max_rating == 5
assert int(train_set.global_mean) == int((3 * 2 + 4 * 7 + 5) / 10)
assert all([a == b for a, b in zip(train_set.item_ppl_rank,
[7, 9, 6, 5, 3, 2, 1, 0, 8, 4])])
assert train_set.num_users == 10
assert train_set.num_items == 10
assert train_set.is_unk_user(7) == False
assert train_set.is_unk_user(13) == True
assert train_set.is_unk_item(3) == False
assert train_set.is_unk_item(16) == True
assert train_set.get_uid('768') == 1
assert train_set.get_iid('195') == 7
assert all([a == b for a, b in zip(train_set.uid_list, range(10))])
assert all([a == b for a, b in zip(train_set.raw_uid_list,
['76', '768', '642', '930', '329', '633', '716', '871', '543', '754'])])
assert all([a == b for a, b in zip(train_set.iid_list, range(10))])
assert all([a == b for a, b in zip(train_set.raw_iid_list,
['93', '257', '795', '709', '705', '226', '478', '195', '737', '282'])])
train_set = MatrixTrainSet.from_uir(triplet_data, global_uid_map={}, global_iid_map={},
global_ui_set=set([('76', '93')]), verbose=True)
assert train_set.num_users == 9
assert train_set.num_items == 9
def test_matrix_trainset_uij_iter():
triplet_data = reader.read_uir('./tests/data.txt')
train_set = MatrixTrainSet.from_uir(triplet_data, global_uid_map={}, global_iid_map={},
global_ui_set=set(), verbose=True)
users = [batch_users for batch_users, _, _ in train_set.uij_iter()]
assert all([a == b for a, b in zip(users, range(10))])
pos_items = [batch_pos_items for _, batch_pos_items, _ in train_set.uij_iter()]
assert all([a == b for a, b in zip(pos_items, range(10))])
neg_items = [batch_neg_items for _, _, batch_neg_items in train_set.uij_iter()]
assert all([a != b for a, b in zip(neg_items, range(10))])
def test_uir_tuple():
triplet_data = reader.read_uir('./tests/data.txt')
train_set = MatrixTrainSet.from_uir(triplet_data,
global_uid_map=None,
global_iid_map=None,
global_ui_set=None,
verbose=True)
try:
train_set.uir_tuple = ([], [])
except ValueError:
assert True
assert 2 == train_set.num_batches(batch_size=5)
def test_idx_iter(self):
train_set = MatrixTrainSet.from_uir(self.triplet_data)
ids = [
batch_ids for batch_ids in train_set.idx_iter(
idx_range=10, batch_size=1, shuffle=False)
]
npt.assert_array_equal(ids, np.arange(10).reshape(10, 1))
ids = [
batch_ids for batch_ids in train_set.idx_iter(
idx_range=10, batch_size=1, shuffle=True)
]
npt.assert_raises(AssertionError, npt.assert_array_equal, ids,
np.arange(10).reshape(10, 1))
def test_uir_tuple(self):
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map=None,
global_iid_map=None,
global_ui_set=None,
verbose=True)
self.assertEqual(len(train_set.uir_tuple), 3)
self.assertEqual(len(train_set.uir_tuple[0]), 10)
try:
train_set.uir_tuple = ([], [])
except ValueError:
assert True
self.assertEqual(train_set.num_batches(batch_size=5), 2)
def test_uir_iter(self):
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map={},
global_iid_map={},
global_ui_set=set(),
verbose=True)
users = [batch_users for batch_users, _, _ in train_set.uir_iter()]
self.assertSequenceEqual(users, range(10))
items = [batch_items for _, batch_items, _ in train_set.uir_iter()]
self.assertSequenceEqual(items, range(10))
ratings = [
batch_ratings for _, _, batch_ratings in train_set.uir_iter()
]
self.assertListEqual(ratings, [4, 4, 4, 4, 3, 4, 4, 5, 3, 4])
def test_matrix(self):
from scipy.sparse import csr_matrix, csc_matrix, dok_matrix
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map=None,
global_iid_map=None,
global_ui_set=None,
verbose=True)
self.assertTrue(isinstance(train_set.matrix, csr_matrix))
self.assertEqual(train_set.csr_matrix[0, 0], 4)
self.assertTrue(train_set.csr_matrix.has_sorted_indices)
self.assertTrue(isinstance(train_set.csc_matrix, csc_matrix))
self.assertEqual(train_set.csc_matrix[4, 4], 3)
self.assertTrue(isinstance(train_set.dok_matrix, dok_matrix))
self.assertEqual(train_set.dok_matrix[7, 7], 5)
def test_uij_iter(self):
train_set = MatrixTrainSet.from_uir(self.triplet_data,
global_uid_map={},
global_iid_map={},
global_ui_set=set(),
verbose=True)
users = [batch_users for batch_users, _, _ in train_set.uij_iter()]
self.assertSequenceEqual(users, range(10))
pos_items = [
batch_pos_items for _, batch_pos_items, _ in train_set.uij_iter()
]
self.assertSequenceEqual(pos_items, range(10))
neg_items = [
batch_neg_items for _, _, batch_neg_items in train_set.uij_iter()
]
self.assertRaises(AssertionError, self.assertSequenceEqual, neg_items,
range(10))