def list_datasets(name=None):
"""Get valid datasets and registered parameters.
Parameters
----------
name : str or None, default None
Return names and registered parameters of registered datasets. If name
is specified, only registered parameters of the respective dataset are
returned.
Returns
-------
dict:
A dict of all the valid keyword parameters names for the specified
dataset. If name is set to None, returns a dict mapping each valid name
to its respective keyword parameter dict. The valid names can be
plugged in `gluonnlp.model.word_evaluation_model.create(name)`.
"""
reg = registry.get_registry(Dataset)
if name is not None:
class_ = reg[name.lower()]
return _REGSITRY_NAME_KWARGS[class_]
else:
return {
dataset_name: _REGSITRY_NAME_KWARGS[class_]
for dataset_name, class_ in registry.get_registry(Dataset).items()
}
def list_datasets(name=None):
"""Get valid datasets and registered parameters.
Parameters
----------
name : str or None, default None
Return names and registered parameters of registered datasets. If name
is specified, only registered parameters of the respective dataset are
returned.
Returns
-------
dict:
A dict of all the valid keyword parameters names for the specified
dataset. If name is set to None, returns a dict mapping each valid name
to its respective keyword parameter dict. The valid names can be
plugged in `gluonnlp.model.word_evaluation_model.create(name)`.
"""
reg = registry.get_registry(Dataset)
if name is not None:
class_ = reg[name.lower()]
return _REGSITRY_NAME_KWARGS[class_]
else:
return {
dataset_name: _REGSITRY_NAME_KWARGS[class_]
for dataset_name, class_ in registry.get_registry(Dataset).items()
}
def list_evaluation_functions(kind=None):
"""Get valid word embedding functions names.
Parameters
----------
kind : ['similarity', 'analogy', None]
Return only valid names for similarity, analogy or both kinds of functions.
Returns
-------
dict or list:
A list of all the valid evaluation function names for the specified
kind. If kind is set to None, returns a dict mapping each valid name to
its respective output list. The valid names can be plugged in
`gluonnlp.model.word_evaluation_model.create(name)`.
"""
if kind is None:
kind = tuple(_REGSITRY_KIND_CLASS_MAP.keys())
if not isinstance(kind, tuple):
if kind not in _REGSITRY_KIND_CLASS_MAP.keys():
raise KeyError(
'Cannot find `kind` {}. Use '
'`list_evaluation_functions(kind=None).keys()` to get all the'
'valid kinds of evaluation functions.'.format(kind))
reg = registry.get_registry(_REGSITRY_KIND_CLASS_MAP[kind])
return list(reg.keys())
else:
return {name: list_evaluation_functions(kind=name) for name in kind}
def list_evaluation_functions(kind=None):
"""Get valid word embedding functions names.
Parameters
----------
kind : ['similarity', 'analogy', None]
Return only valid names for similarity, analogy or both kinds of functions.
Returns
-------
dict or list:
A list of all the valid evaluation function names for the specified
kind. If kind is set to None, returns a dict mapping each valid name to
its respective output list. The valid names can be plugged in
`gluonnlp.model.word_evaluation_model.create(name)`.
"""
if kind is None:
kind = tuple(_REGSITRY_KIND_CLASS_MAP.keys())
if not isinstance(kind, tuple):
if kind not in _REGSITRY_KIND_CLASS_MAP.keys():
raise KeyError(
'Cannot find `kind` {}. Use '
'`list_evaluation_functions(kind=None).keys()` to get all the'
'valid kinds of evaluation functions.'.format(kind))
reg = registry.get_registry(_REGSITRY_KIND_CLASS_MAP[kind])
return list(reg.keys())
else:
return {name: list_evaluation_functions(kind=name) for name in kind}
def list_sources(embedding_name=None):
"""Get valid token embedding names and their pre-trained file names.
To load token embedding vectors from an externally hosted pre-trained token embedding file,
such as those of GloVe and FastText, one should use
`gluonnlp.embedding.create(embedding_name, source)`. This method returns all the
valid names of `source` for the specified `embedding_name`. If `embedding_name` is set to
None, this method returns all the valid names of `embedding_name` with their associated
`source`.
Parameters
----------
embedding_name : str or None, default None
The pre-trained token embedding name.
Returns
-------
dict or list:
A list of all the valid pre-trained token embedding file names (`source`) for the
specified token embedding name (`embedding_name`). If the text embedding name is set to
None, returns a dict mapping each valid token embedding name to a list of valid pre-trained
files (`source`). They can be plugged into
`gluonnlp.embedding.create(embedding_name, source)`.
"""
text_embedding_reg = registry.get_registry(TokenEmbedding)
if embedding_name is not None:
embedding_name = embedding_name.lower()
if embedding_name not in text_embedding_reg:
raise KeyError(
'Cannot find `embedding_name` {}. Use '
'`list_sources(embedding_name=None).keys()` to get all the valid'
'embedding names.'.format(embedding_name))
return list(text_embedding_reg[embedding_name].source_file_hash.keys())
else:
return {
embedding_name: list(embedding_cls.source_file_hash.keys())
for embedding_name, embedding_cls in registry.get_registry(
TokenEmbedding).items()
}
def list_sources(embedding_name=None):
"""Get valid token embedding names and their pre-trained file names.
To load token embedding vectors from an externally hosted pre-trained token embedding file,
such as those of GloVe and FastText, one should use
`gluonnlp.embedding.create(embedding_name, source)`. This method returns all the
valid names of `source` for the specified `embedding_name`. If `embedding_name` is set to
None, this method returns all the valid names of `embedding_name` with their associated
`source`.
Parameters
----------
embedding_name : str or None, default None
The pre-trained token embedding name.
Returns
-------
dict or list:
A list of all the valid pre-trained token embedding file names (`source`) for the
specified token embedding name (`embedding_name`). If the text embeding name is set to None,
returns a dict mapping each valid token embedding name to a list of valid pre-trained files
(`source`). They can be plugged into
`gluonnlp.embedding.create(embedding_name, source)`.
"""
text_embedding_reg = registry.get_registry(TokenEmbedding)
if embedding_name is not None:
embedding_name = embedding_name.lower()
if embedding_name not in text_embedding_reg:
raise KeyError('Cannot find `embedding_name` {}. Use '
'`list_sources(embedding_name=None).keys()` to get all the valid'
'embedding names.'.format(embedding_name))
return list(text_embedding_reg[embedding_name].source_file_hash.keys())
else:
return {embedding_name: list(embedding_cls.source_file_hash.keys())
for embedding_name, embedding_cls in registry.get_registry(TokenEmbedding).items()}
def list_subword_functions():
"""Get valid subword function names."""
reg = registry.get_registry(SubwordFunction)
return list(reg.keys())
