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 test01_most_similar(self):
set_log_level(2)
data_opt = self.get_ml100k_mm_opt()
opt = ALSOption().get_default_option()
opt.d = 20
opt.num_workers = 1
als = ALS(opt, data_opt=data_opt)
als.initialize()
als.train()
pals = ParALS(als)
random_keys = [
k for k, _ in als.most_similar('49.Star_Wars_(1977)', topk=128)
]
random_indexes = als.get_index_pool(random_keys)
naive = [als.most_similar(k, topk=10) for k in random_keys]
topks0 = [[k for k, _ in result] for result in naive]
scores0 = np.array([[v for _, v in result] for result in naive])
self.assertEqual(scores0.shape, (
128,
10,
), msg='check even size')
scores0 = scores0.reshape(len(naive), 10)
pals.num_workers = 1
topks1, scores1 = pals.most_similar(random_keys, topk=10, repr=True)
topks2, scores2 = pals.most_similar(random_indexes, topk=10, repr=True)
for a, b in combinations([topks0, topks1, topks2], 2):
self.assertEqual(a, b)
for a, b in combinations([scores0, scores1, scores2], 2):
self.assertTrue(np.allclose(a, b))
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 test05_topk_MT(self):
set_log_level(2)
data_opt = self.get_ml100k_mm_opt()
opt = ALSOption().get_default_option()
opt.d = 20
opt.num_workers = 1
als = ALS(opt, data_opt=data_opt)
als.initialize()
als.train()
als.build_userid_map()
all_keys = als._idmanager.userids
start_t = time.time()
naive = als.topk_recommendation(all_keys, topk=5)
naive_elapsed = time.time() - start_t
pals = ParALS(als)
pals.num_workers = 4
start_t = time.time()
qkeys1, topks1, scores1 = pals.topk_recommendation(all_keys,
topk=5,
repr=True)
par_elapsed = time.time() - start_t
self.assertEqual(len(qkeys1), len(naive))
for q, t in zip(qkeys1, topks1):
self.assertEqual(naive[q], t)
self.assertTrue(naive_elapsed > par_elapsed * 1.5)
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 _test10_fast_most_similar(self, cls, opt):
set_log_level(1)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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 = cls(opt, data_opt=data_opt)
c.initialize()
c.train()
keys = [x for x, _ in c.most_similar('49.Star_Wars_(1977)', topk=100)]
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 _test6_topk(self, cls, opt):
set_log_level(2)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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 = cls(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('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_a)
c.normalize()
ret_b = [
x for x, _ in c.most_similar('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_b)
self.assertEqual(ret_a[:10], ret_b[:10])
def _test9_compact_serialization(self, cls, opt):
set_log_level(1)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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 = cls(opt, data_opt=data_opt)
c.initialize()
c.train()
ret_a = [
x for x, _ in c.most_similar('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_a)
c.save('model.bin', with_userid_map=False)
c = cls(opt)
c.load('model.bin', data_fields=['Q', '_idmanager'])
ret_a = [
x for x, _ in c.most_similar('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_a)
self.assertFalse(hasattr(c, 'P'))
c.normalize(group='item')
ret_a = [
x for x, _ in c.most_similar('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_a)
def _test8_serialization(self, cls, opt):
set_log_level(1)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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 = cls(opt, data_opt=data_opt)
c.initialize()
c.train()
ret_a = [
x for x, _ in c.most_similar('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_a)
c.save('model.bin')
c.load('model.bin')
os.remove('model.bin')
ret_a = [
x for x, _ in c.most_similar('180.Return_of_the_Jedi_(1983)',
topk=100)
]
self.assertIn('49.Star_Wars_(1977)', ret_a)
def test02_most_similar(self):
num_cpu = psutil.cpu_count()
if num_cpu < 2:
return
set_log_level(1)
als = ALS()
mp = MockParallel(als)
R = 1000000
Q = self.get_factors(1000000, 12)
indexes = np.random.choice(range(R), 1024).astype(np.int32)
pool = np.array([], dtype=np.int32)
elapsed = []
results = []
for num_workers in [1] + [i * 2
for i in range(1, num_cpu + 1)
if i * 2 < num_cpu][:3]:
mp.num_workers = num_workers
start_t = time.time()
ret = mp._most_similar('item', indexes, Q, 10, pool, -1, True)
elapsed.append(time.time() - start_t)
results.append(ret)
for i in range(1, len(elapsed)):
self.assertTrue(elapsed[i - 1] > elapsed[i] * 1.2)
self.assertTrue(np.allclose(results[i - 1][0], results[i][0], atol=1e-07))
self.assertTrue(np.allclose(results[i - 1][1], results[i][1], atol=1e-07))
def test01_most_similar(self):
set_log_level(1)
model = self.load_text8_model()
index = HnswIndex(model.L0.shape[1])
model.normalize('item')
for f in model.L0:
index.add_data(f)
index.build(n_threads=4)
index.save('n2.bin')
par = ParW2V(model)
model.opt.num_workers = 1
all_keys = model._idmanager.itemids[::][:10000]
start_t = time.time()
[model.most_similar(k, topk=10) for k in all_keys]
naive_elapsed = time.time() - start_t
par.num_workers = 4
start_t = time.time()
par.most_similar(all_keys, topk=10, repr=True)
par_elapsed = time.time() - start_t
start_t = time.time()
par.set_hnsw_index('n2.bin', 'item')
par.most_similar(all_keys, topk=10, repr=True)
ann_elapsed = time.time() - start_t
self.assertTrue(naive_elapsed > par_elapsed * 1.5 > ann_elapsed * 5.0,
msg=f'{naive_elapsed} > {par_elapsed} > {ann_elapsed}')
index.unload()
os.remove('n2.bin')
def test1_early_stopping(self):
set_log_level(2)
algo = MockAlgo()
algo.initialize()
algo.set_losses([1.0 + i / 1.0 for i in range(100)])
algo.opt.early_stopping_rounds = 5
algo.train()
self.assertEqual(algo.last_iteration, 5)
def test03_pool(self):
set_log_level(1)
als = ALS()
mp = MockParallel(als)
Q = self.get_factors(128, 5)
indexes = np.array([0, 1, 2, 3, 4], dtype=np.int32)
pool = np.array([5, 6, 7], dtype=np.int32)
topks, scores = mp._most_similar(indexes, Q, 10, pool)
self.assertTrue(set(topks[::].reshape(10 * 5)), set([5, 6, 7, -1]))
def test01_most_similar(self):
set_log_level(1)
als = ALS()
mp = MockParallel(als)
Q = self.get_factors(128, 5)
indexes = np.array([0, 1, 2, 3, 4], dtype=np.int32)
pool = np.array([], dtype=np.int32)
topks1, scores1 = mp._most_similar(indexes, Q, 10, pool)
topks2, scores2 = self.get_most_similar(indexes, Q, 10)
self.assertTrue(np.allclose(topks1, topks2))
self.assertTrue(np.allclose(scores1, scores2))
def _test4_train(self, cls, opt):
set_log_level(3)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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 = cls(opt, data_opt=data_opt)
c.initialize()
c.train()
self.assertTrue(True)
def test04_topk(self):
set_log_level(1)
als = ALS()
mp = MockParallel(als)
P = self.get_factors(512, 5)
Q = self.get_factors(128, 5)
q_indexes = np.array([312, 313, 314, 315, 316], dtype=np.int32)
pool = np.array([], dtype=np.int32)
topks1, scores1 = mp._topk_recommendation(q_indexes, P, Q, 10, pool)
topks2, scores2 = self.get_topk(q_indexes, P, Q, 10)
self.assertTrue(np.allclose(topks1, topks2))
self.assertTrue(np.allclose(scores1, scores2))
def _test3_init(self, cls, opt):
set_log_level(3)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
data_opt.data.path = './ml100k.h5py'
c = cls(opt, data_opt=data_opt)
self.assertTrue(True)
c.init_factors()
self.assertEqual(c.P.shape, (943, 20))
self.assertEqual(c.Q.shape, (1682, 20))
def _test7_train_ml_20m(self, cls, opt):
set_log_level(3)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_20m + 'main'
data_opt.input.uid = self.ml_20m + 'uid'
data_opt.input.iid = self.ml_20m + 'iid'
data_opt.data.path = './ml20m.h5py'
data_opt.data.use_cache = True
c = cls(opt, data_opt=data_opt)
c.initialize()
c.train()
self.assertTrue(True)
def test2_most_similar(self):
set_log_level(2)
opt = ALSOption().get_default_option()
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
data_opt.input.uid = self.ml_100k + 'uid'
data_opt.input.iid = self.ml_100k + 'iid'
als = ALS(opt, data_opt=data_opt)
als.initialize()
als.train()
q1, q2, q3 = '49.Star_Wars_(1977)', '180.Return_of_the_Jedi_(1983)', '171.Empire_Strikes_Back,_The_(1980)'
self._test_most_similar(als, q1, q2, q3)
def example1():
log.set_log_level(log.DEBUG)
als_option = ALSOption().get_default_option()
als_option.validation = aux.Option({'topk': 10})
data_option = MatrixMarketOptions().get_default_option()
data_option.input.main = '../tests/ext/ml-100k/main'
data_option.input.iid = '../tests/ext/ml-100k/iid'
als = ALS(als_option, data_opt=data_option)
als.initialize()
als.train()
print('MovieLens 100k metrics for validations\n%s' % json.dumps(als.get_validation_results(), indent=2))
print('Similar movies to Star_Wars_(1977)')
for rank, (movie_name, score) in enumerate(als.most_similar('49.Star_Wars_(1977)')):
print(f'{rank + 1:02d}. {score:.3f} {movie_name}')
print('Run hyper parameter optimization for val_ndcg...')
als.opt.num_workers = 4
als.opt.evaluation_period = 10
als.opt.optimize = aux.Option({
'loss': 'val_ndcg',
'max_trials': 100,
'deployment': True,
'start_with_default_parameters': True,
'space': {
'd': ['randint', ['d', 10, 128]],
'reg_u': ['uniform', ['reg_u', 0.1, 1.0]],
'reg_i': ['uniform', ['reg_i', 0.1, 1.0]],
'alpha': ['randint', ['alpha', 1, 10]],
}
})
log.set_log_level(log.INFO)
als.opt.model_path = './example1.ml100k.als.optimize.bin'
print(json.dumps({'alpha': als.opt.alpha, 'd': als.opt.d,
'reg_u': als.opt.reg_u, 'reg_i': als.opt.reg_i}, indent=2))
als.optimize()
als.load('./example1.ml100k.als.optimize.bin')
print('Similar movies to Star_Wars_(1977)')
for rank, (movie_name, score) in enumerate(als.most_similar('49.Star_Wars_(1977)')):
print(f'{rank + 1:02d}. {score:.3f} {movie_name}')
optimization_res = als.get_optimization_data()
best_parameters = optimization_res['best_parameters']
print(json.dumps(optimization_res['best'], indent=2))
print(json.dumps({'alpha': int(best_parameters['alpha']), 'd': int(best_parameters['d']),
'reg_u': best_parameters['reg_u'], 'reg_i': best_parameters['reg_i']}, indent=2))
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 _test5_validation(self, cls, opt, ndcg=0.06, map=0.04):
set_log_level(2)
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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 = cls(opt, data_opt=data_opt)
c.initialize()
c.train()
results = c.get_validation_results()
self.assertTrue(results['ndcg'] > ndcg, msg='NDCG Test')
self.assertTrue(results['map'] > map, msg='MAP Test')
def example2():
log.set_log_level(log.INFO)
als_option = ALSOption().get_default_option()
data_option = MatrixMarketOptions().get_default_option()
data_option.input.main = '../tests/ext/ml-20m/main'
data_option.input.iid = '../tests/ext/ml-20m/iid'
data_option.data.path = './ml20m.h5py'
data_option.data.use_cache = True
als = ALS(als_option, data_opt=data_option)
als.initialize()
als.train()
als.normalize('item')
als.build_itemid_map()
print(
'Make item recommendation on als.ml20m.par.top10.tsv with Paralell(Thread=4)'
)
par = ParALS(als)
par.num_workers = 4
all_items = als._idmanager.itemids
start_t = time.time()
with open('als.ml20m.par.top10.tsv', 'w') as fout:
for idx in range(0, len(all_items), 128):
topks, _ = par.most_similar(all_items[idx:idx + 128], repr=True)
for q, p in zip(all_items[idx:idx + 128], topks):
fout.write('%s\t%s\n' % (q, '\t'.join(p)))
print('took: %.3f secs' % (time.time() - start_t))
from n2 import HnswIndex
index = HnswIndex(als.Q.shape[1])
for f in als.Q:
index.add_data(f)
index.build(n_threads=4)
index.save('ml20m.n2.index')
index.unload()
print(
'Make item recommendation on als.ml20m.par.top10.tsv with Ann(Thread=1)'
)
par.set_hnsw_index('ml20m.n2.index', 'item')
par.num_workers = 4
start_t = time.time()
with open('als.ml20m.ann.top10.tsv', 'w') as fout:
for idx in range(0, len(all_items), 128):
topks, _ = par.most_similar(all_items[idx:idx + 128], repr=True)
for q, p in zip(all_items[idx:idx + 128], topks):
fout.write('%s\t%s\n' % (q, '\t'.join(p)))
print('took: %.3f secs' % (time.time() - start_t))
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 test04_text8_most_similar(self):
set_log_level(1)
model = self.load_text8_model()
par = ParW2V(model)
model.opt.num_workers = 1
all_keys = model._idmanager.itemids[::][:10000]
start_t = time.time()
[model.most_similar(k, topk=10) for k in all_keys]
naive_elapsed = time.time() - start_t
par.num_workers = 4
start_t = time.time()
par.most_similar(all_keys, topk=10, repr=True)
par_elapsed = time.time() - start_t
self.assertTrue(naive_elapsed > par_elapsed * 3.0)
def test07_topk_pool(self):
set_log_level(2)
data_opt = self.get_ml100k_mm_opt()
opt = BPRMFOption().get_default_option()
opt.d = 20
opt.num_workers = 1
model = BPRMF(opt, data_opt=data_opt)
model.initialize()
model.train()
par = ParBPRMF(model)
pool = np.array([i for i in range(5)], dtype=np.int32)
model.build_userid_map()
all_keys = model._idmanager.userids[::][:10]
naive = model.topk_recommendation(all_keys, topk=10, pool=pool)
qkeys1, topks1, scores1 = par.topk_recommendation(all_keys, topk=10, pool=pool, repr=True)
for q, t in zip(qkeys1, topks1):
self.assertEqual(naive[q], t)
def test4_optimize(self):
set_log_level(2)
opt = ALSOption().get_default_option()
opt.d = 5
opt.num_workers = 2
opt.model_path = 'als.bin'
opt.validation = aux.Option({'topk': 10})
optimize_option = aux.Option({
'loss': 'val_rmse',
'max_trials': 10,
'deployment': True,
'start_with_default_parameters': True,
'space': {
'd': ['randint', ['d', 10, 20]],
'reg_u': ['uniform', ['reg_u', 0.1, 0.3]],
'reg_i': ['uniform', ['reg_i', 0.1, 0.3]],
'alpha': ['randint', ['alpha', 8, 10]]
}
})
opt.optimize = optimize_option
opt.evaluation_period = 1
opt.tensorboard = aux.Option({'root': './tb',
'name': 'als'})
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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'})
als = ALS(opt, data_opt=data_opt)
als.init_factors()
als.train()
default_result = als.get_validation_results()
als.optimize()
base_loss = default_result['rmse'] # val_rmse
optimize_loss = als.get_optimization_data()['best']['val_rmse']
self.assertTrue(base_loss > optimize_loss)
als.load('als.bin')
loss = als.get_validation_results()
self.assertAlmostEqual(loss['rmse'], optimize_loss)
os.remove('als.bin')
def test00_tensorboard(self):
set_log_level(2)
opt = ALSOption().get_default_option()
opt.d = 5
opt.validation = aux.Option({'topk': 10})
opt.tensorboard = aux.Option({'root': './tb', 'name': 'als'})
data_opt = MatrixMarketOptions().get_default_option()
data_opt.input.main = self.ml_100k + 'main'
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'})
als = ALS(opt, data_opt=data_opt)
als.initialize()
als.train()
results = als.get_validation_results()
self.assertTrue(results['ndcg'] > 0.025)
self.assertTrue(results['map'] > 0.015)
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 test02_most_similar(self):
set_log_level(1)
als = ALS()
mp = MockParallel(als)
R = 1000000
Q = self.get_factors(1000000, 12)
indexes = np.random.choice(range(R), 1024).astype(np.int32)
pool = np.array([], dtype=np.int32)
elapsed = []
results = []
for num_workers in [1, 2, 4, 8]:
mp.num_workers = num_workers
start_t = time.time()
ret = mp._most_similar(indexes, Q, 10, pool)
elapsed.append(time.time() - start_t)
results.append(ret)
for i in range(1, len(elapsed)):
self.assertTrue(elapsed[i - 1] > elapsed[i] * 1.5)
self.assertTrue(np.allclose(results[i - 1][0], results[i][0]))
self.assertTrue(np.allclose(results[i - 1][1], results[i][1]))
