def test10_fast_most_similar(self):
set_log_level(1)
opt = CFROption().get_default_option()
data_opt = StreamOptions().get_default_option()
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.value_prepro = aux.Option({'name': 'OneBased'})
c = CFR(opt, data_opt=data_opt)
c.initialize()
c.train()
keys = [x for x, _ in c.most_similar('49.Star_Wars_(1977)', 10)]
start_t = time.time()
for i in range(100):
for key in keys:
c.most_similar(key)
elapsed_a = time.time() - start_t
c.normalize(group='item')
start_t = time.time()
for i in range(100):
for key in keys:
c.most_similar(key)
elapsed_b = time.time() - start_t
self.assertTrue(elapsed_a > elapsed_b)
def test9_compact_serialization(self):
set_log_level(1)
opt = CFROption().get_default_option()
data_opt = StreamOptions().get_default_option()
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.value_prepro = aux.Option({'name': 'OneBased'})
c = CFR(opt, data_opt=data_opt)
c.initialize()
c.train()
ret_a = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_a)
c.save('model.bin', with_userid_map=False)
c = CFR(opt)
c.load('model.bin', data_fields=['I', '_idmanager'])
ret_a = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_a)
self.assertFalse(hasattr(c, 'U'))
c.normalize(group='item')
ret_a = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_a)
def test4_train(self):
set_log_level(3)
opt = CFROption().get_default_option()
data_opt = StreamOptions().get_default_option()
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.value_prepro = aux.Option({'name': 'OneBased'})
c = CFR(opt, data_opt=data_opt)
c.initialize()
c.train()
self.assertTrue(True)
def test3_init(self):
set_log_level(3)
opt = CFROption().get_default_option()
opt.d = 20
data_opt = StreamOptions().get_default_option()
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.path = './ml100k.h5py'
c = CFR(opt, data_opt=data_opt)
self.assertTrue(True)
c.initialize()
self.assertEqual(c.U.shape, (943, 20))
self.assertEqual(c.I.shape, (1682, 20))
def test5_validation(self, ndcg=0.06, map=0.04):
set_log_level(3)
opt = CFROption().get_default_option()
opt.validation = aux.Option({'topk': 10})
opt.tensorboard = aux.Option({'root': './tb', 'name': 'cfr'})
data_opt = StreamOptions().get_default_option()
data_opt.data.validation.name = "sample"
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.value_prepro = aux.Option({'name': 'OneBased'})
c = CFR(opt, data_opt=data_opt)
c.initialize()
c.train()
results = c.get_validation_results()
self.assertTrue(results['ndcg'] > ndcg)
self.assertTrue(results['map'] > map)
def test8_serialization(self):
set_log_level(1)
opt = CFROption().get_default_option()
data_opt = StreamOptions().get_default_option()
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.value_prepro = aux.Option({'name': 'OneBased'})
c = CFR(opt, data_opt=data_opt)
c.initialize()
c.train()
ret_a = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_a)
c.save('model.bin')
c.load('model.bin')
os.remove('model.bin')
ret_a = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_a)
def test6_topk(self):
set_log_level(1)
opt = CFROption().get_default_option()
opt.validation = aux.Option({'topk': 10})
data_opt = StreamOptions().get_default_option()
data_opt.data.validation.name = "sample"
data_opt.data.sppmi = {"windows": 5, "k": 10}
data_opt.data.internal_data_type = "matrix"
data_opt.input.main = self.ml_100k + 'stream'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.value_prepro = aux.Option({'name': 'OneBased'})
c = CFR(opt, data_opt=data_opt)
c.initialize()
c.train()
self.assertTrue(len(c.topk_recommendation('1', 10)), 10)
ret_a = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_a)
c.normalize()
ret_b = [x for x, _ in c.most_similar('49.Star_Wars_(1977)')]
self.assertIn('180.Return_of_the_Jedi_(1983)', ret_b)
self.assertEqual(ret_a, ret_b)