def __init__(self, opt_path=None, *args, **kwargs):
Algo.__init__(self, *args, **kwargs)
BPRMFOption.__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 = BPRMFOption().get_default_option()
self.logger = log.get_logger('BPRMF')
self.opt, self.opt_path = self.get_option(opt_path)
self.obj = CyBPRMF()
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)
self.data.create()
elif isinstance(data, Data):
self.data = data
self.logger.info('BPRMF(%s)' % json.dumps(self.opt, indent=2))
if self.data:
self.logger.info(self.data.show_info())
assert self.data.data_type in ['matrix']
def __init__(self, opt_path=None, *args, **kwargs):
Algo.__init__(self, *args, **kwargs)
ALSOption.__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 = ALSOption().get_default_option()
self.logger = log.get_logger('ALS')
self.opt, self.opt_path = self.get_option(opt_path)
if self.opt.accelerator and not inited_CUALS:
self.logger.error("ImportError CuALS, no cuda library exists.")
raise RuntimeError()
self.obj = CuALS() if self.opt.accelerator else CyALS()
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)
self.data.create()
elif isinstance(data, Data):
self.data = data
self.logger.info('ALS(%s)' % json.dumps(self.opt, indent=2))
if self.data:
self.logger.info(self.data.show_info())
assert self.data.data_type in ['matrix']
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 __init__(self, opt_path=None, *args, **kwargs):
Algo.__init__(self, *args, **kwargs)
WARPOption.__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 = WARPOption().get_default_option()
self.logger = log.get_logger('WARP')
self.opt, self.opt_path = self.get_option(opt_path)
# TODO:GPU Implementation
if self.opt.accelerator is True:
raise NotImplementedError(
"GPU version WARP is not implemented yet")
self.obj = CyWARP()
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)
self.data.create()
elif isinstance(data, Data):
self.data = data
self.logger.info('WARP(%s)' % json.dumps(self.opt, indent=2))
if self.data:
self.logger.info(self.data.show_info())
assert self.data.data_type in ['matrix']
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']