def from_params(cls, params: Params) -> 'CharacterTokenizer':
byte_encoding = params.pop('byte_encoding', None)
lowercase_characters = params.pop('lowercase_characters', False)
start_tokens = params.pop('start_tokens', None)
end_tokens = params.pop('end_tokens', None)
params.assert_empty(cls.__name__)
return cls(byte_encoding=byte_encoding,
lowercase_characters=lowercase_characters,
start_tokens=start_tokens,
end_tokens=end_tokens)
def pop_max_vocab_size(params: Params) -> Union[int, Dict[str, int]]:
"""
max_vocab_size is allowed to be either an int or a Dict[str, int] (or nothing).
but it could also be a string representing an int (in the case of environment variable
substitution). So we need some complex logic to handle it.
"""
size = params.pop("max_vocab_size", None)
if isinstance(size, Params):
# This is the Dict[str, int] case.
return size.as_dict()
elif size is not None:
# This is the int / str case.
return int(size)
else:
return None
def dict_from_params(
cls, params: Params) -> 'Dict[str, TokenIndexer]': # type: ignore
"""
We typically use ``TokenIndexers`` in a dictionary, with each ``TokenIndexer`` getting a
name. The specification for this in a ``Params`` object is typically ``{"name" ->
{indexer_params}}``. This method reads that whole set of parameters and returns a
dictionary suitable for use in a ``TextField``.
Because default values for token indexers are typically handled in the calling class to
this and are based on checking for ``None``, if there were no parameters specifying any
token indexers in the given ``params``, we return ``None`` instead of an empty dictionary.
"""
token_indexers = {}
for name, indexer_params in params.items():
token_indexers[name] = cls.from_params(indexer_params)
if token_indexers == {}:
token_indexers = None
return token_indexers
def from_params(cls, vocab: Vocabulary,
params: Params) -> 'Embedding': # type: ignore
"""
We need the vocabulary here to know how many items we need to embed, and we look for a
``vocab_namespace`` key in the parameter dictionary to know which vocabulary to use. If
you know beforehand exactly how many embeddings you need, or aren't using a vocabulary
mapping for the things getting embedded here, then you can pass in the ``num_embeddings``
key directly, and the vocabulary will be ignored.
In the configuration file, a file containing pretrained embeddings can be specified
using the parameter ``"pretrained_file"``.
It can be the path to a local file or an URL of a (cached) remote file.
Two formats are supported:
* hdf5 file - containing an embedding matrix in the form of a torch.Tensor;
* text file - an utf-8 encoded text file with space separated fields::
[word] [dim 1] [dim 2] ...
The text file can eventually be compressed with gzip, bz2, lzma or zip.
You can even select a single file inside an archive containing multiple files
using the URI::
"(archive_uri)#file_path_inside_the_archive"
where ``archive_uri`` can be a file system path or a URL. For example::
"(http://nlp.stanford.edu/data/glove.twitter.27B.zip)#glove.twitter.27B.200d.txt"
"""
# pylint: disable=arguments-differ
num_embeddings = params.pop_int('num_embeddings', None)
vocab_namespace = params.pop("vocab_namespace", "tokens")
if num_embeddings is None:
num_embeddings = vocab.get_vocab_size(vocab_namespace)
embedding_dim = params.pop_int('embedding_dim')
pretrained_file = params.pop("pretrained_file", None)
projection_dim = params.pop_int("projection_dim", None)
trainable = params.pop_bool("trainable", True)
padding_index = params.pop_int('padding_index', None)
max_norm = params.pop_float('max_norm', None)
norm_type = params.pop_float('norm_type', 2.)
scale_grad_by_freq = params.pop_bool('scale_grad_by_freq', False)
sparse = params.pop_bool('sparse', False)
params.assert_empty(cls.__name__)
if pretrained_file:
# If we're loading a saved model, we don't want to actually read a pre-trained
# embedding file - the embeddings will just be in our saved weights, and we might not
# have the original embedding file anymore, anyway.
weight = _read_pretrained_embeddings_file(pretrained_file,
embedding_dim, vocab,
vocab_namespace)
else:
weight = None
return cls(num_embeddings=num_embeddings,
embedding_dim=embedding_dim,
projection_dim=projection_dim,
weight=weight,
padding_index=padding_index,
trainable=trainable,
max_norm=max_norm,
norm_type=norm_type,
scale_grad_by_freq=scale_grad_by_freq,
sparse=sparse)
def from_params(cls, params: Params) -> 'Tokenizer':
choice = params.pop_choice('type',
cls.list_available(),
default_to_first_choice=True)
return cls.by_name(choice).from_params(params)
def from_params(
cls,
params: Params,
instances: Iterable['adi.Instance'] = None): # type: ignore
"""
there are two possible ways to build a vocabulary; from a
collection of instances, using :func:`Vocabulary.from_instances`, or
from a pre-saved vocabulary, using :func:`Vocabulary.from_files`.
you can also extend pre-saved vocabulary with collection of instances
using this method. This method wraps these options, allowing their
specification from a ``Params`` object, generated from a JSON
configuration file.
parameters
----------
params: Params, required.
instances: Iterable['adi.Instance'], optional
If ``params`` doesn't contain a ``directory_path`` key,
the ``Vocabulary`` can be built directly from a collection of
instances (i.e. a dataset). If ``extend`` key is set False,
dataset instances will be ignored and final vocabulary will be
one loaded from ``directory_path``. If ``extend`` key is set True,
dataset instances will be used to extend the vocabulary loaded
from ``directory_path`` and that will be final vocabulary used.
returns
-------
a ``Vocabulary``.
"""
# pylint: disable=arguments-differ
# Vocabulary is ``Registrable`` so that you can configure a custom subclass,
# but (unlike most of our registrables) almost everyone will want to use the
# base implementation. So instead of having an abstract ``VocabularyBase`` or
# such, we just add the logic for instantiating a registered subclass here,
# so that most users can continue doing what they were doing.
vocab_type = params.pop("type", None)
if vocab_type is not None:
return cls.by_name(vocab_type).from_params(params=params,
instances=instances)
extend = params.pop("extend", False)
vocabulary_directory = params.pop("directory_path", None)
if not vocabulary_directory and not instances:
raise ConfigurationError(
"You must provide either a Params object containing a "
"vocab_directory key or a Dataset to build a vocabulary from.")
if extend and not instances:
raise ConfigurationError(
"'extend' is true but there are not instances passed to extend."
)
if extend and not vocabulary_directory:
raise ConfigurationError(
"'extend' is true but there is not 'directory_path' to extend from."
)
if vocabulary_directory and instances:
if extend:
info("Loading Vocab from files and extending it with dataset.")
else:
info("Loading Vocab from files instead of dataset.")
if vocabulary_directory:
vocab = Vocabulary.from_files(vocabulary_directory)
if not extend:
params.assert_empty("Vocabulary - from files")
return vocab
if extend:
vocab.extend_from_instances(params, instances=instances)
return vocab
min_count = params.pop("min_count", None)
max_vocab_size = pop_max_vocab_size(params)
non_padded_namespaces = params.pop("non_padded_namespaces",
DEFAULT_NON_PADDED_NAMESPACES)
pretrained_files = params.pop("pretrained_files", {})
only_include_pretrained_words = params.pop_bool(
"only_include_pretrained_words", False)
tokens_to_add = params.pop("tokens_to_add", None)
params.assert_empty("Vocabulary - from dataset")
return Vocabulary.from_instances(
instances=instances,
min_count=min_count,
max_vocab_size=max_vocab_size,
non_padded_namespaces=non_padded_namespaces,
pretrained_files=pretrained_files,
only_include_pretrained_words=only_include_pretrained_words,
tokens_to_add=tokens_to_add)
def from_params(cls, params: Params) -> 'SingleIdTokenIndexer':
namespace = params.pop('namespace', 'tokens')
lowercase_tokens = params.pop_bool('lowercase_tokens', False)
params.assert_empty(cls.__name__)
return cls(namespace=namespace, lowercase_tokens=lowercase_tokens)
def from_params(cls, params: Params) -> 'Elmo':
# Add files to archive
params.add_file_to_archive('options_file')
params.add_file_to_archive('weight_file')
options_file = params.pop('options_file')
weight_file = params.pop('weight_file')
requires_grad = params.pop('requires_grad', False)
num_output_representations = params.pop('num_output_representations')
do_layer_norm = params.pop_bool('do_layer_norm', False)
keep_sentence_boundaries = params.pop_bool('keep_sentence_boundaries',
False)
dropout = params.pop_float('dropout', 0.5)
params.assert_empty(cls.__name__)
return cls(options_file=options_file,
weight_file=weight_file,
num_output_representations=num_output_representations,
requires_grad=requires_grad,
do_layer_norm=do_layer_norm,
keep_sentence_boundaries=keep_sentence_boundaries,
dropout=dropout)