def test01_optimize(self):
space = Optimizable()._get_space({'x': ['uniform', ['x', 1, 10]]})
best = fmin(fn=lambda opt: opt['x']**2,
space=space,
algo=tpe.suggest,
max_evals=100)
self.assertEqual(int(best['x']), 1)
def __init__(self, opt_path=None, *args, **kwargs):
Algo.__init__(self, *args, **kwargs)
CFROption.__init__(self, *args, **kwargs)
Evaluable.__init__(self, *args, **kwargs)
Serializable.__init__(self, *args, **kwargs)
Optimizable.__init__(self, *args, **kwargs)
if opt_path is None:
opt_path = CFROption().get_default_option()
self.logger = log.get_logger('CFR')
# put options into cython class with type assertion
# see comments on options.py for the description of each parameter
self.opt, self.opt_path = self.get_option(opt_path)
self.obj = CyCFR()
# check the validity of option
self.is_valid_option(self.opt)
assert self.obj.init(self.opt_path.encode(
"utf8")), "putting parameter to cython object failed"
# ensure embedding matrix is initialzed for preventing segmentation fault
self.is_initialized = False
self.data = None
data = kwargs.get('data')
data_opt = self.opt.get('data_opt')
data_opt = kwargs.get('data_opt', data_opt)
if data_opt:
assert data_opt.data.internal_data_type == "matrix", \
f"internal data type is {data_opt.data.internal_data_type}, not matrix"
self.data = buffalo.data.load(data_opt)
assert self.data.data_type == 'stream'
self.data.create()
elif isinstance(data, Data):
self.data = data
self.logger.info('CFR ({})'.format(json.dumps(self.opt, indent=2)))
if self.data:
self.logger.info(self.data.show_info())
assert self.data.data_type in ['stream']
def __init__(self, opt_path=None, *args, **kwargs):
Algo.__init__(self, *args, **kwargs)
W2VOption.__init__(self, *args, **kwargs)
Evaluable.__init__(self, *args, **kwargs)
Serializable.__init__(self, *args, **kwargs)
Optimizable.__init__(self, *args, **kwargs)
if opt_path is None:
opt_path = W2VOption().get_default_option()
self.logger = log.get_logger('W2V')
self.opt, self.opt_path = self.get_option(opt_path)
self.obj = CyW2V()
assert self.obj.init(bytes(
self.opt_path, 'utf-8')), 'cannot parse option file: %s' % opt_path
self.data = None
data = kwargs.get('data')
data_opt = self.opt.get('data_opt')
data_opt = kwargs.get('data_opt', data_opt)
if data_opt:
self.data = buffalo.data.load(data_opt)
assert self.data.data_type == 'stream'
self.data.create()
elif isinstance(data, Data):
self.data = data
self.logger.info('W2V(%s)' % json.dumps(self.opt, indent=2))
if self.data:
self.logger.info(self.data.show_info())
assert self.data.data_type in ['stream']
self._vocab = aux.Option({
'size': 0,
'index': None,
'inv_index': None,
'scale': None,
'dist': None,
'total_word_count': 0
})
def test02_optimize(self):
def mock_fn(opt):
loss = 1.0 - opt['adaptive_reg'] / 1.0
loss += 1.0 / (opt['d']**2 + 1)
loss += 1.0 / opt['alpha']
loss += (opt['reg_i'] / 2.0)
loss += (opt['reg_u'] / 2.0)
return loss
option = ALSOption().get_default_optimize_option()
space = Optimizable()._get_space(option.space)
best = fmin(fn=mock_fn, space=space, algo=tpe.suggest, max_evals=600)
self.assertGreaterEqual(int(best['d']), 2) # this is shifted by 10
self.assertGreaterEqual(int(best['alpha']), 15)
self.assertLessEqual(best['reg_i'], 0.3)
self.assertLessEqual(best['reg_u'], 0.3)
self.assertEqual(best['adaptive_reg'], 1)
def test2_optimize(self):
def mock_fn(opt):
loss = 1.0 - opt['adaptive_reg'] / 1.0
loss += 1.0 / opt['d']
loss += 1.0 / opt['alpha']
loss += 1.0 / opt['reg_i']
loss += 1.0 / opt['reg_u']
return loss
option = ALSOption().get_default_optimize_option()
space = Optimizable()._get_space(option.space)
best = fmin(fn=mock_fn,
space=space,
algo=tpe.suggest,
max_evals=600)
self.assertGreaterEqual(int(best['d']), 16)
self.assertGreaterEqual(int(best['alpha']), 16)
self.assertGreaterEqual(best['reg_i'], 0.5)
self.assertGreaterEqual(best['reg_u'], 0.5)
self.assertEqual(best['adaptive_reg'], 1)
def test00_get_space(self):
Optimizable()._get_space({'x': ['uniform', ['x', 1, 10]]})
self.assertTrue(True)