def extend_from_instances(self,
params: Params,
instances: Iterable['adi.Instance'] = ()) -> None:
"""
Extends an already generated vocabulary using a collection of instances.
"""
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", {})
min_pretrained_embeddings = params.pop("min_pretrained_embeddings", None)
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")
logger.info("Fitting token dictionary from dataset.")
namespace_token_counts: Dict[str, Dict[str, int]] = defaultdict(lambda: defaultdict(int))
for instance in Tqdm.tqdm(instances):
instance.count_vocab_items(namespace_token_counts)
self._extend(counter=namespace_token_counts,
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,
min_pretrained_embeddings=min_pretrained_embeddings)
def from_params(
cls, vocab: Vocabulary,
params: Params) -> 'TokenCharactersEncoder': # type: ignore
# pylint: disable=arguments-differ
embedding_params: Params = params.pop("embedding")
# Embedding.from_params() uses "tokens" as the default namespace, but we need to change
# that to be "token_characters" by default.
embedding_params.setdefault("vocab_namespace", "token_characters")
embedding = Embedding.from_params(vocab, embedding_params)
encoder_params: Params = params.pop("encoder")
encoder = Seq2VecEncoder.from_params(encoder_params)
dropout = params.pop_float("dropout", 0.0)
params.assert_empty(cls.__name__)
return cls(embedding, encoder, dropout)
def from_params(
cls, vocab: Vocabulary,
params: Params) -> 'BasicTextFieldEmbedder': # type: ignore
# pylint: disable=arguments-differ,bad-super-call
# The original `from_params` for this class was designed in a way that didn't agree
# with the constructor. The constructor wants a 'token_embedders' parameter that is a
# `Dict[str, TokenEmbedder]`, but the original `from_params` implementation expected those
# key-value pairs to be top-level in the params object.
#
# This breaks our 'configuration wizard' and configuration checks. Hence, going forward,
# the params need a 'token_embedders' key so that they line up with what the constructor wants.
# For now, the old behavior is still supported, but produces a DeprecationWarning.
embedder_to_indexer_map = params.pop("embedder_to_indexer_map", None)
if embedder_to_indexer_map is not None:
embedder_to_indexer_map = embedder_to_indexer_map.as_dict(
quiet=True)
allow_unmatched_keys = bool(params.pop("allow_unmatched_keys", False))
token_embedder_params = params.pop('token_embedders', None)
if token_embedder_params is not None:
# New way: explicitly specified, so use it.
token_embedders = {
name: Embedding.from_params(vocab=vocab, params=subparams)
for name, subparams in token_embedder_params.items()
}
else:
# Warn that the original behavior is deprecated
warnings.warn(
DeprecationWarning(
"the token embedders for BasicTextFieldEmbedder should now "
"be specified as a dict under the 'token_embedders' key, "
"not as top-level key-value pairs"))
token_embedders = {}
keys = list(params.keys())
for key in keys:
embedder_params = params.pop(key)
token_embedders[key] = Embedding.from_params(
vocab=vocab, params=embedder_params)
# TODO(pitrack): replace this line?
# params.assert_empty(cls.__name__)
return cls(token_embedders, embedder_to_indexer_map,
allow_unmatched_keys)
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.
try:
return int(size)
except:
return size
else:
return None
def create_kwargs(cls: Type[T], params: Params, **extras) -> Dict[str, Any]:
"""
Given some class, a `Params` object, and potentially other keyword arguments,
create a dict of keyword args suitable for passing to the class's constructor.
The function does this by finding the class's constructor, matching the constructor
arguments to entries in the `params` object, and instantiating values for the parameters
using the type annotation and possibly a from_params method.
Any values that are provided in the `extras` will just be used as is.
For instance, you might provide an existing `Vocabulary` this way.
"""
# Get the signature of the constructor.
signature = inspect.signature(cls.__init__)
kwargs: Dict[str, Any] = {}
# Iterate over all the constructor parameters and their annotations.
for name, param in signature.parameters.items():
# Skip "self". You're not *required* to call the first parameter "self",
# so in theory this logic is fragile, but if you don't call the self parameter
# "self" you kind of deserve what happens.
if name == "self":
continue
# If the annotation is a compound type like typing.Dict[str, int],
# it will have an __origin__ field indicating `typing.Dict`
# and an __args__ field indicating `(str, int)`. We capture both.
annotation = remove_optional(param.annotation)
origin = getattr(annotation, '__origin__', None)
args = getattr(annotation, '__args__', [])
# The parameter is optional if its default value is not the "no default" sentinel.
default = param.default
optional = default != _NO_DEFAULT
# Some constructors expect extra non-parameter items, e.g. vocab: Vocabulary.
# We check the provided `extras` for these and just use them if they exist.
if name in extras:
kwargs[name] = extras[name]
# The next case is when the parameter type is itself constructible from_params.
elif hasattr(annotation, 'from_params'):
if name in params:
# Our params have an entry for this, so we use that.
subparams = params.pop(name)
if takes_arg(annotation.from_params, 'extras'):
# If annotation.params accepts **extras, we need to pass them all along.
# For example, `BasicTextFieldEmbedder.from_params` requires a Vocabulary
# object, but `TextFieldEmbedder.from_params` does not.
subextras = extras
else:
# Otherwise, only supply the ones that are actual args; any additional ones
# will cause a TypeError.
subextras = {
k: v
for k, v in extras.items()
if takes_arg(annotation.from_params, k)
}
# In some cases we allow a string instead of a param dict, so
# we need to handle that case separately.
if isinstance(subparams, str):
kwargs[name] = annotation.by_name(subparams)()
else:
kwargs[name] = annotation.from_params(params=subparams,
**subextras)
elif not optional:
# Not optional and not supplied, that's an error!
raise ConfigurationError(
f"expected key {name} for {cls.__name__}")
else:
kwargs[name] = default
# If the parameter type is a Python primitive, just pop it off
# using the correct casting pop_xyz operation.
elif annotation == str:
kwargs[name] = (params.pop(name, default)
if optional else params.pop(name))
elif annotation == int:
kwargs[name] = (params.pop_int(name, default)
if optional else params.pop_int(name))
elif annotation == bool:
kwargs[name] = (params.pop_bool(name, default)
if optional else params.pop_bool(name))
elif annotation == float:
kwargs[name] = (params.pop_float(name, default)
if optional else params.pop_float(name))
# This is special logic for handling types like Dict[str, TokenIndexer], which it creates by
# instantiating each value from_params and returning the resulting dict.
elif origin in (Dict, dict) and len(args) == 2 and hasattr(
args[-1], 'from_params'):
value_cls = annotation.__args__[-1]
value_dict = {}
for key, value_params in params.pop(name, Params({})).items():
value_dict[key] = value_cls.from_params(params=value_params,
**extras)
kwargs[name] = value_dict
else:
# Pass it on as is and hope for the best. ¯\_(ツ)_/¯
if optional:
kwargs[name] = params.pop(name, default)
else:
kwargs[name] = params.pop(name)
params.assert_empty(cls.__name__)
return kwargs
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:
logger.info("Loading Vocab from files and extending it with dataset.")
else:
logger.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", {})
min_pretrained_embeddings = params.pop("min_pretrained_embeddings", None)
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,
min_pretrained_embeddings=min_pretrained_embeddings)
