def __init__(self,
data_pack: mz.DataPack,
mode='point',
num_dup: int = 1,
num_neg: int = 1,
resample: bool = True,
batch_size: int = 128,
shuffle: bool = True,
callbacks: typing.List[Callback] = None):
"""Init."""
if callbacks is None:
callbacks = []
if mode not in ('point', 'pair', 'list'):
raise ValueError(f"{mode} is not a valid mode type."
f"Must be one of `point`, `pair` or `list`.")
self._mode = mode
self._num_dup = num_dup
self._num_neg = num_neg
self._batch_size = batch_size
self._shuffle = shuffle
self._resample = resample
self._orig_relation = data_pack.relation
self._callbacks = callbacks
if mode == 'pair':
data_pack.relation = self._reorganize_pair_wise(data_pack.relation,
num_dup=num_dup,
num_neg=num_neg)
self._data_pack = data_pack
self._batch_indices = None
self.reset_index()
def __init__(
self,
data_pack: mz.DataPack,
mode='point',
num_dup: int = 1,
num_neg: int = 1,
batch_size: int = 32,
resample: bool = False,
shuffle: bool = True,
sort: bool = False,
callbacks: typing.List[BaseCallback] = None
):
"""Init."""
if callbacks is None:
callbacks = []
if mode not in ('point', 'pair', 'list'):
raise ValueError(f"{mode} is not a valid mode type."
f"Must be one of `point`, `pair` or `list`.")
if shuffle and sort:
raise ValueError(f"parameters `shuffle` and `sort` conflict, "
f"should not both be `True`.")
data_pack = data_pack.copy()
self._mode = mode
self._num_dup = num_dup
self._num_neg = num_neg
self._batch_size = batch_size
self._resample = (resample if mode != 'point' else False)
self._shuffle = shuffle
self._sort = sort
self._orig_relation = data_pack.relation
self._callbacks = callbacks
if mode == 'pair':
data_pack.relation = self._reorganize_pair_wise(
relation=self._orig_relation,
num_dup=num_dup,
num_neg=num_neg
)
self._data_pack = data_pack
self._batch_indices = None
self.reset_index()