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 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))