def create(embedding_name, **kwargs):
"""Creates an instance of token embedding.
Creates a token embedding instance by loading embedding vectors from an externally hosted
pre-trained token embedding file, such as those of GloVe and FastText. To get all the valid
`embedding_name` and `source`, use :func:`gluonnlp.embedding.list_sources`.
Parameters
----------
embedding_name : str
The token embedding name (case-insensitive).
Returns
-------
An instance of :class:`gluonnlp.embedding.TokenEmbedding`:
A token embedding instance that loads embedding vectors from an externally hosted
pre-trained token embedding file.
"""
create_text_embedding = registry.get_create_func(TokenEmbedding,
'token embedding')
return create_text_embedding(embedding_name, **kwargs)
def create(kind, name, **kwargs):
"""Creates an instance of a registered word embedding evaluation function.
Parameters
----------
kind : ['similarity', 'analogy']
Return only valid names for similarity, analogy or both kinds of
functions.
name : str
The evaluation function name (case-insensitive).
Returns
-------
An instance of
:class:`gluonnlp.embedding.evaluation.WordEmbeddingAnalogyFunction`:
or
:class:`gluonnlp.embedding.evaluation.WordEmbeddingSimilarityFunction`:
An instance of the specified evaluation function.
"""
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))
create_ = registry.get_create_func(
_REGSITRY_KIND_CLASS_MAP[kind],
'word embedding {} evaluation function'.format(kind))
return create_(name, **kwargs)
def create(embedding_name, **kwargs):
"""Creates an instance of token embedding.
Creates a token embedding instance by loading embedding vectors from an externally hosted
pre-trained token embedding file, such as those of GloVe and FastText. To get all the valid
`embedding_name` and `source`, use :func:`gluonnlp.embedding.list_sources`.
Parameters
----------
embedding_name : str
The token embedding name (case-insensitive).
kwargs : dict
All other keyword arguments are passed to the initializer of token
embedding class. For example `create(embedding_name='fasttext',
source='wiki.simple', load_ngrams=True)` will return
`FastText(source='wiki.simple', load_ngrams=True)`.
Returns
-------
An instance of :class:`gluonnlp.embedding.TokenEmbedding`:
A token embedding instance that loads embedding vectors from an externally hosted
pre-trained token embedding file.
"""
create_text_embedding = registry.get_create_func(TokenEmbedding,
'token embedding')
return create_text_embedding(embedding_name, **kwargs)
def create(embedding_name, **kwargs):
"""Creates an instance of token embedding.
Creates a token embedding instance by loading embedding vectors from an externally hosted
pre-trained token embedding file, such as those of GloVe and FastText. To get all the valid
`embedding_name` and `source`, use :func:`gluonnlp.embedding.list_sources`.
Parameters
----------
embedding_name : str
The token embedding name (case-insensitive).
kwargs : dict
All other keyword arguments are passed to the initializer of token
embedding class. For example `create(embedding_name='fasttext',
source='wiki.simple', load_ngrams=True)` will return
`FastText(source='wiki.simple', load_ngrams=True)`.
Returns
-------
An instance of :class:`gluonnlp.embedding.TokenEmbedding`:
A token embedding instance that loads embedding vectors from an externally hosted
pre-trained token embedding file.
"""
create_text_embedding = registry.get_create_func(TokenEmbedding, 'token embedding')
return create_text_embedding(embedding_name, **kwargs)
def create(kind, name, **kwargs):
"""Creates an instance of a registered word embedding evaluation function.
Parameters
----------
kind : ['similarity', 'analogy']
Return only valid names for similarity, analogy or both kinds of
functions.
name : str
The evaluation function name (case-insensitive).
Returns
-------
An instance of
:class:`gluonnlp.embedding.evaluation.WordEmbeddingAnalogyFunction`:
or
:class:`gluonnlp.embedding.evaluation.WordEmbeddingSimilarityFunction`:
An instance of the specified evaluation function.
"""
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))
create_ = registry.get_create_func(
_REGSITRY_KIND_CLASS_MAP[kind],
'word embedding {} evaluation function'.format(kind))
return create_(name, **kwargs)
def create(name, **kwargs):
"""Creates an instance of a registered dataset.
Parameters
----------
name : str
The dataset name (case-insensitive).
Returns
-------
An instance of :class:`mxnet.gluon.data.Dataset` constructed with the
keyword arguments passed to the create function.
"""
create_ = registry.get_create_func(Dataset, 'dataset')
return create_(name, **kwargs)
def create(name, **kwargs):
"""Creates an instance of a registered dataset.
Parameters
----------
name : str
The dataset name (case-insensitive).
Returns
-------
An instance of :class:`mxnet.gluon.data.Dataset` constructed with the
keyword arguments passed to the create function.
"""
create_ = registry.get_create_func(Dataset, 'dataset')
return create_(name, **kwargs)
def create_subword_function(subword_function_name, **kwargs):
"""Creates an instance of a subword function."""
create_ = registry.get_create_func(SubwordFunction, 'token embedding')
return create_(subword_function_name, **kwargs)
Returns
-------
list of tuples
A (name, value) tuple list.
"""
name, value = self.get()
if not isinstance(name, list):
name = [name]
if not isinstance(value, list):
value = [value]
return list(zip(name, value))
# pylint: disable=invalid-name
register = registry.get_register_func(EvalMetric, 'metric')
alias = registry.get_alias_func(EvalMetric, 'metric')
_create = registry.get_create_func(EvalMetric, 'metric')
# pylint: enable=invalid-name
def create(metric, *args, **kwargs):
"""Creates evaluation metric from metric names or instances of EvalMetric
or a custom metric function.
Parameters
----------
metric : str or callable
Specifies the metric to create.
This argument must be one of the below:
- Name of a metric.
- An instance of `EvalMetric`.
- A list, each element of which is a metric or a metric name.
- An evaluation function that computes custom metric for a given batch of
