def test3_id_list(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = np.array([[1, 2], [1, 2], [2, 1]])
opt.input.uid = [1, 2.0, '3']
opt.input.iid = np.array(['1', 'a'])
mm = MatrixMarket(opt)
mm.create()
self.assertTrue(True)
def test2_create(self):
set_log_level(3)
opt = MatrixMarketOptions().get_default_option()
opt.input.main = self.mm_path
opt.input.uid = self.uid_path
opt.input.iid = self.iid_path
mm = MatrixMarket(opt)
mm.create()
self.temp_files.append(opt.data.path)
self.assertTrue(True)
db = mm.handle
self.assertEqual(sorted(db.keys()),
sorted(['vali', 'idmap', 'rowwise', 'colwise']))
header = mm.get_header()
self.assertEqual(header['num_nnz'], 5)
self.assertEqual(header['num_users'], 5)
self.assertEqual(header['num_items'], 3)
data = [(u, kk, vv) for u, kk, vv in mm.iterate()]
self.assertEqual(len(data), 5)
self.assertEqual([int(kk) for _, kk, _ in data], [0, 0, 2, 1, 1])
self.assertEqual(data[2], (2, 2, 1.0))
data = [(u, kk, vv) for u, kk, vv in mm.iterate(axis='colwise')]
self.assertEqual([int(kk) for _, kk, _ in data], [0, 1, 3, 4, 2])
def test1_minmax(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = self.mm_path
opt.input.uid = self.uid_path
opt.input.iid = self.iid_path
opt.data.value_prepro = aux.Option({
'name': 'MinMaxScalar',
'min': 3,
'max': 5.0
})
mm = MatrixMarket(opt)
mm.create()
self.assertTrue(True)
db = mm.handle
self.assertEqual(sorted(db.keys()),
sorted(['vali', 'idmap', 'rowwise', 'colwise']))
header = mm.get_header()
self.assertEqual(header['num_nnz'], 5)
self.assertEqual(header['num_users'], 5)
self.assertEqual(header['num_items'], 3)
data = [(u, kk, vv) for u, kk, vv in mm.iterate()]
self.assertEqual(len(data), 5)
self.assertEqual([int(kk) for _, kk, _ in data], [0, 0, 2, 1, 1])
self.assertEqual([int(vv) for _, _, vv in data], [3, 5, 3, 3, 4])
self.assertEqual(data[2], (2, 2, 3.0))
def load(opt):
from buffalo.data.mm import MatrixMarket
from buffalo.data.stream import Stream
if isinstance(opt, (str, )):
opt = aux.Option(opt)
assert isinstance(
opt, (dict, aux.Option
)), 'opt must be either str, or dict/aux.Option but {}'.format(
type(opt))
if opt['type'] == 'matrix_market':
return MatrixMarket(opt)
if opt['type'] == 'stream':
return Stream(opt)
raise RuntimeError('Unexpected data.type: {}'.format(opt['type']))
def test0_onebased(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = self.mm_path
opt.input.uid = self.uid_path
opt.input.iid = self.iid_path
opt.data.value_prepro = aux.Option({'name': 'OneBased'})
mm = MatrixMarket(opt)
mm.create()
self.temp_files.append(opt.data.path)
self.assertTrue(True)
db = mm.handle
self.assertEqual(sorted(db.keys()),
sorted(['vali', 'idmap', 'rowwise', 'colwise']))
header = mm.get_header()
self.assertEqual(header['num_nnz'], 5)
self.assertEqual(header['num_users'], 5)
self.assertEqual(header['num_items'], 3)
data = [(u, kk, vv) for u, kk, vv in mm.iterate()]
self.assertEqual(len(data), 5)
self.assertEqual([int(kk) for _, kk, _ in data], [0, 0, 2, 1, 1])
self.assertEqual([int(vv) for _, _, vv in data], [1, 1, 1, 1, 1])
self.assertEqual(data[2], (2, 2, 1.0))
def test2_implicit_als(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = self.mm_path
opt.input.uid = self.uid_path
opt.input.iid = self.iid_path
opt.data.value_prepro = aux.Option({
'name': 'ImplicitALS',
'epsilon': 0.5
})
mm = MatrixMarket(opt)
mm.create()
self.assertTrue(True)
db = mm.handle
self.assertEqual(sorted(db.keys()),
sorted(['vali', 'idmap', 'rowwise', 'colwise']))
header = mm.get_header()
self.assertEqual(header['num_nnz'], 5)
self.assertEqual(header['num_users'], 5)
self.assertEqual(header['num_items'], 3)
data = [(u, kk, vv) for u, kk, vv in mm.iterate()]
self.assertEqual(len(data), 5)
self.assertEqual([int(kk) for _, kk, _ in data], [0, 0, 2, 1, 1])
self.assertAlmostEqual(data[2][2], math.log(1 + 1.0 / 0.5))
def test3_id_list_except(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = np.array([[1, 2], [1, 2], [2, 1]])
opt.input.uid = [1, 2.0] # size should be 3
mm = MatrixMarket(opt)
self.assertRaises(TypeError, mm.create)
def test3_list(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = [[10, 123], [1, 2]]
mm = MatrixMarket(opt)
self.assertRaises(RuntimeError, opt.is_valid_option)
self.assertRaises(RuntimeError, mm.create)
def test2_dense(self):
opt = MatrixMarketOptions().get_default_option()
opt.input.main = self.mm_dense
mm = MatrixMarket(opt)
mm.create()
self.assertTrue(True)
def get_buffalo_db(db):
from buffalo.data.mm import MatrixMarket
db_opt = BuffaloLib().get_database(db)
db = MatrixMarket(db_opt)
db.create()
return db