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 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 als(self, database, **kwargs):
from buffalo.algo.als import ALS
opts = self.get_option('buffalo', 'als', **kwargs)
data_opt = self.get_database(database, **kwargs)
als = ALS(opts, data_opt=data_opt)
als.initialize()
if kwargs.get('return_instance_before_train'):
return als
elapsed, mem_info = self.run(als.train)
als = None
return elapsed, mem_info
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 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 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 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 test06_topk_pool(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)
pool = np.array([i for i in range(5)], dtype=np.int32)
als.build_userid_map()
all_keys = als._idmanager.userids[::][:10]
naive = als.topk_recommendation(all_keys, topk=10, pool=pool)
qkeys1, topks1, scores1 = pals.topk_recommendation(all_keys, topk=10, pool=pool, repr=True)
for q, t in zip(qkeys1, topks1):
self.assertEqual(naive[q], t)
def test02_most_similar(self):
set_log_level(1)
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_itemid_map()
pals = ParALS(als)
all_keys = als._idmanager.itemids[::]
start_t = time.time()
[als.most_similar(k, topk=10) for k in all_keys]
naive_elapsed = time.time() - start_t
pals.num_workers = 4
start_t = time.time()
pals.most_similar(all_keys, topk=10, repr=True)
parals_elapsed = time.time() - start_t
self.assertTrue(naive_elapsed > parals_elapsed * 3.0)
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 als(self, database, **kwargs):
from pyspark.sql import SparkSession
from pyspark.ml.recommendation import ALS
from pyspark import SparkConf, SparkContext
opts = self.get_option('pyspark', 'als', **kwargs)
conf = SparkConf()\
.setAppName("pyspark")\
.setMaster('local[%s]' % kwargs.get('num_workers'))\
.set('spark.local.dir', './tmp/')\
.set('spark.worker.cleanup.enabled', 'true')\
.set('spark.driver.memory', '32G')
context = SparkContext(conf=conf)
context.setLogLevel('WARN')
spark = SparkSession(context)
data = self.get_database(database, spark=spark, context=context)
print(opts)
als = ALS(**opts)
elapsed, memory_usage = self.run(als.fit, data)
spark.stop()
return elapsed, memory_usage
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]))
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 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': best_parameters['alpha'],
'd': best_parameters['d'],
'reg_u': best_parameters['reg_u'],
'reg_i': best_parameters['reg_i']
},
indent=2))
def test04_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 test2_init_with_dict(self):
set_log_level(3)
opt = ALSOption().get_default_option()
ALS(opt)
self.assertTrue(True)
app = Flask(__name__)
users = pd.read_json('./model/users.json', typ='frame')
books = pd.read_json('./model/books.json', typ='frame')
#books = pd.read_excel('./model/books.xlsx')
books['ISBN'] = books['ISBN'].astype(str)
books['권'] = books['권'].fillna('')
userbook_map = hp.get_userbook_map(users)
user_items, uid_to_idx, idx_to_uid, mid_to_idx, idx_to_mid = hp.df_to_matrix(
userbook_map, 'user_id', 'book_id')
iid = list(idx_to_mid.values())
uid = list(idx_to_uid.values())
#model = ALS(opt, data_opt=data_opt)
model = ALS()
model.load('./model/als.optimize.bin')
headers = {
'X-Naver-Client-Id': '',
'X-Naver-Client-Secret': '',
}
def get_bookimage(params):
response = requests.get('https://openapi.naver.com/v1/search/book_adv.xml',
headers=headers,
params=params)
root = ElementTree.fromstring(response.text)
img_url = ''
def test00_init(self):
set_log_level(1)
als = ALS()
MockParallel(als)
self.assertTrue(True)