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_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')
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 = ''
if root.tag == 'rss':