spaCy/website/docs/api/pipe.md
2020-07-29 15:14:07 +02:00

18 KiB

title tag teaser
Pipe class Base class for trainable pipeline components

This class is a base class and not instantiated directly. Trainable pipeline components like the EntityRecognizer or TextCategorizer inherit from it and it defines the interface that components should follow to function as trainable components in a spaCy pipeline.

https://github.com/explosion/spaCy/blob/develop/spacy/pipeline/pipe.pyx

Pipe.__init__

Example

from spacy.pipeline import Pipe
from spacy.language import Language

class CustomPipe(Pipe):
    ...

@Language.factory("your_custom_pipe", default_config={"model": MODEL})
def make_custom_pipe(nlp, name, model):
    return CustomPipe(nlp.vocab, model, name)

Create a new pipeline instance. In your application, you would normally use a shortcut for this and instantiate the component using its string name and nlp.add_pipe.

This method needs to be overwritten with your own custom __init__ method.

Name Type Description
vocab Vocab The shared vocabulary.
model Model The Thinc Model powering the pipeline component.
name str String name of the component instance. Used to add entries to the losses during training.
**cfg Additional config parameters and settings.

Pipe.__call__

Apply the pipe to one document. The document is modified in place, and returned. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order. Both __call__ and pipe delegate to the predict and set_annotations methods.

Example

doc = nlp("This is a sentence.")
pipe = nlp.add_pipe("your_custom_pipe")
# This usually happens under the hood
processed = pipe(doc)
Name Type Description
doc Doc The document to process.
RETURNS Doc The processed document.

Pipe.pipe

Apply the pipe to a stream of documents. This usually happens under the hood when the nlp object is called on a text and all pipeline components are applied to the Doc in order. Both __call__ and pipe delegate to the predict and set_annotations methods.

Example

pipe = nlp.add_pipe("your_custom_pipe")
for doc in pipe.pipe(docs, batch_size=50):
    pass
Name Type Description
stream Iterable[Doc] A stream of documents.
keyword-only
batch_size int The number of documents to buffer. Defaults to 128.
YIELDS Doc The processed documents in order.

Pipe.begin_training

Initialize the pipe for training, using data examples if available. Returns an Optimizer object.

Example

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = pipe.begin_training(pipeline=nlp.pipeline)
Name Type Description
get_examples Callable[[], Iterable[Example]] Optional function that returns gold-standard annotations in the form of Example objects.
keyword-only
pipeline List[Tuple[str, Callable]] Optional list of pipeline components that this component is part of.
sgd Optimizer An optional optimizer. Will be created via create_optimizer if not set.
RETURNS Optimizer The optimizer.

Pipe.predict

Apply the pipeline's model to a batch of docs, without modifying them.

This method needs to be overwritten with your own custom predict method.

Example

pipe = nlp.add_pipe("your_custom_pipe")
scores = pipe.predict([doc1, doc2])
Name Type Description
docs Iterable[Doc] The documents to predict.
RETURNS - The model's prediction for each document.

Pipe.set_annotations

Modify a batch of documents, using pre-computed scores.

This method needs to be overwritten with your own custom set_annotations method.

Example

pipe = nlp.add_pipe("your_custom_pipe")
scores = pipe.predict(docs)
pipe.set_annotations(docs, scores)
Name Type Description
docs Iterable[Doc] The documents to modify.
scores - The scores to set, produced by Pipe.predict.

Pipe.update

Learn from a batch of documents and gold-standard information, updating the pipe's model. Delegates to predict.

This method needs to be overwritten with your own custom update method.

Example

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = nlp.begin_training()
losses = pipe.update(examples, sgd=optimizer)
Name Type Description
examples Iterable[Example] A batch of Example objects to learn from.
keyword-only
drop float The dropout rate.
set_annotations bool Whether or not to update the Example objects with the predictions, delegating to set_annotations.
sgd Optimizer The optimizer.
losses Dict[str, float] Optional record of the loss during training. Updated using the component name as the key.
RETURNS Dict[str, float] The updated losses dictionary.

Pipe.rehearse

Perform a "rehearsal" update from a batch of data. Rehearsal updates teach the current model to make predictions similar to an initial model, to try to address the "catastrophic forgetting" problem. This feature is experimental.

Example

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = nlp.resume_training()
losses = pipe.rehearse(examples, sgd=optimizer)
Name Type Description
examples Iterable[Example] A batch of Example objects to learn from.
keyword-only
drop float The dropout rate.
sgd Optimizer The optimizer.
losses Dict[str, float] Optional record of the loss during training. Updated using the component name as the key.
RETURNS Dict[str, float] The updated losses dictionary.

Pipe.get_loss

Find the loss and gradient of loss for the batch of documents and their predicted scores.

Example

ner = nlp.add_pipe("ner")
scores = ner.predict([eg.predicted for eg in examples])
loss, d_loss = ner.get_loss(examples, scores)
Name Type Description
examples Iterable[Example] The batch of examples.
scores Scores representing the model's predictions.
RETURNS Tuple[float, float] The loss and the gradient, i.e. (loss, gradient).

Pipe.score

Score a batch of examples.

Example

scores = pipe.score(examples)
Name Type Description
examples Iterable[Example] The examples to score.
RETURNS Dict[str, Any] The scores, e.g. produced by the Scorer.

Pipe.create_optimizer

Create an optimizer for the pipeline component. Defaults to Adam with default settings.

Example

pipe = nlp.add_pipe("your_custom_pipe")
optimizer = pipe.create_optimizer()
Name Type Description
RETURNS Optimizer The optimizer.

Pipe.add_label

Add a new label to the pipe. It's possible to extend pretrained models with new labels, but care should be taken to avoid the "catastrophic forgetting" problem.

Example

pipe = nlp.add_pipe("your_custom_pipe")
pipe.add_label("MY_LABEL")
Name Type Description
label str The label to add.
RETURNS int 0 if the label is already present, otherwise 1.

Pipe.use_params

Modify the pipe's model, to use the given parameter values. At the end of the context, the original parameters are restored.

Example

pipe = nlp.add_pipe("your_custom_pipe")
with pipe.use_params(optimizer.averages):
    pipe.to_disk("/best_model")
Name Type Description
params dict The parameter values to use in the model.

Pipe.to_disk

Serialize the pipe to disk.

Example

pipe = nlp.add_pipe("your_custom_pipe")
pipe.to_disk("/path/to/pipe")
Name Type Description
path str / Path A path to a directory, which will be created if it doesn't exist. Paths may be either strings or Path-like objects.
keyword-only
exclude Iterable[str] String names of serialization fields to exclude.

Pipe.from_disk

Load the pipe from disk. Modifies the object in place and returns it.

Example

pipe = nlp.add_pipe("your_custom_pipe")
pipe.from_disk("/path/to/pipe")
Name Type Description
path str / Path A path to a directory. Paths may be either strings or Path-like objects.
keyword-only
exclude Iterable[str] String names of serialization fields to exclude.
RETURNS Pipe The modified pipe.

Pipe.to_bytes

Example

pipe = nlp.add_pipe("your_custom_pipe")
pipe_bytes = pipe.to_bytes()

Serialize the pipe to a bytestring.

Name Type Description
keyword-only
exclude Iterable[str] String names of serialization fields to exclude.
RETURNS bytes The serialized form of the pipe.

Pipe.from_bytes

Load the pipe from a bytestring. Modifies the object in place and returns it.

Example

pipe_bytes = pipe.to_bytes()
pipe = nlp.add_pipe("your_custom_pipe")
pipe.from_bytes(pipe_bytes)
Name Type Description
bytes_data bytes The data to load from.
keyword-only
exclude Iterable[str] String names of serialization fields to exclude.
RETURNS Pipe The pipe.

Serialization fields

During serialization, spaCy will export several data fields used to restore different aspects of the object. If needed, you can exclude them from serialization by passing in the string names via the exclude argument.

Example

data = pipe.to_disk("/path", exclude=["vocab"])
Name Description
vocab The shared Vocab.
cfg The config file. You usually don't want to exclude this.
model The binary model data. You usually don't want to exclude this.