Pipeline

TrainablePipe

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. See the docs on writing trainable components for how to use the TrainablePipe base class to implement custom components.

explosion/spaCy/master/spacy/pipeline/trainable_pipe.pyx
Can't fetch code example from GitHub :( Please use the link below to view the example. If you've come across a broken link, we always appreciate a pull request to the repository, or a report on the issue tracker. Thanks!

TrainablePipe.__init__ method

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.

NameDescription
vocabThe shared vocabulary. Vocab
modelThe Thinc Model powering the pipeline component. Model[List[Doc], Any]
nameString name of the component instance. Used to add entries to the losses during training. str
**cfgAdditional config parameters and settings. Will be available as the dictionary cfg and is serialized with the component.

TrainablePipe.__call__ method

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.

NameDescription
docThe document to process. Doc

TrainablePipe.pipe method

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.

NameDescription
streamA stream of documents. Iterable[Doc]
keyword-only
batch_sizeThe number of documents to buffer. Defaults to 128. int

TrainablePipe.set_error_handler methodv3.0

Define a callback that will be invoked when an error is thrown during processing of one or more documents with either __call__ or pipe. The error handler will be invoked with the original component’s name, the component itself, the list of documents that was being processed, and the original error.

NameDescription
error_handlerA function that performs custom error handling. Callable[[str, Callable[[Doc], Doc], List[Doc], Exception]

TrainablePipe.get_error_handler methodv3.0

Retrieve the callback that performs error handling for this component’s __call__ and pipe methods. If no custom function was previously defined with set_error_handler, a default function is returned that simply reraises the exception.

NameDescription

TrainablePipe.initialize methodv3.0

Initialize the component for training. get_examples should be a function that returns an iterable of Example objects. The data examples are used to initialize the model of the component and can either be the full training data or a representative sample. Initialization includes validating the network, inferring missing shapes and setting up the label scheme based on the data. This method is typically called by Language.initialize.

NameDescription
get_examplesFunction that returns gold-standard annotations in the form of Example objects. Callable[[], Iterable[Example]]
keyword-only
nlpThe current nlp object. Defaults to None. Optional[Language]

TrainablePipe.predict method

Apply the component’s model to a batch of Doc objects, without modifying them.

NameDescription
docsThe documents to predict. Iterable[Doc]

TrainablePipe.set_annotations method

Modify a batch of Doc objects, using pre-computed scores.

NameDescription
docsThe documents to modify. Iterable[Doc]
scoresThe scores to set, produced by Tagger.predict.

TrainablePipe.update method

Learn from a batch of Example objects containing the predictions and gold-standard annotations, and update the component’s model.

NameDescription
examplesA batch of Example objects to learn from. Iterable[Example]
keyword-only
dropThe dropout rate. float
sgdAn optimizer. Will be created via create_optimizer if not set. Optional[Optimizer]
lossesOptional record of the loss during training. Updated using the component name as the key. Optional[Dict[str, float]]

TrainablePipe.rehearse methodexperimentalv3.0

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.

NameDescription
examplesA batch of Example objects to learn from. Iterable[Example]
keyword-only
sgdAn optimizer. Will be created via create_optimizer if not set. Optional[Optimizer]
lossesOptional record of the loss during training. Updated using the component name as the key. Optional[Dict[str, float]]

TrainablePipe.get_loss method

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

NameDescription
examplesThe batch of examples. Iterable[Example]
scoresScores representing the model’s predictions.

TrainablePipe.score methodv3.0

Score a batch of examples.

NameDescription
examplesThe examples to score. Iterable[Example]

TrainablePipe.create_optimizer method

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

NameDescription

TrainablePipe.use_params methodcontextmanager

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

NameDescription
paramsThe parameter values to use in the model. dict

TrainablePipe.finish_update method

Update parameters using the current parameter gradients. Defaults to calling self.model.finish_update.

NameDescription
sgdAn optimizer. Optional[Optimizer]

TrainablePipe.add_label method

Add a new label to the pipe, to be predicted by the model. The actual implementation depends on the specific component, but in general add_label shouldn’t be called if the output dimension is already set, or if the model has already been fully initialized. If these conditions are violated, the function will raise an Error. The exception to this rule is when the component is resizable, in which case set_output should be called to ensure that the model is properly resized.

NameDescription
labelThe label to add. str

Note that in general, you don’t have to call pipe.add_label if you provide a representative data sample to the initialize method. In this case, all labels found in the sample will be automatically added to the model, and the output dimension will be inferred automatically.

TrainablePipe.is_resizable property

Check whether or not the output dimension of the component’s model can be resized. If this method returns True, set_output can be called to change the model’s output dimension.

For built-in components that are not resizable, you have to create and train a new model from scratch with the appropriate architecture and output dimension. For custom components, you can implement a resize_output function and add it as an attribute to the component’s model.

NameDescription

TrainablePipe.set_output method

Change the output dimension of the component’s model. If the component is not resizable, this method will raise a NotImplementedError. If a component is resizable, the model’s attribute resize_output will be called. This is a function that takes the original model and the new output dimension nO, and changes the model in place. When resizing an already trained model, care should be taken to avoid the “catastrophic forgetting” problem.

NameDescription
nOThe new output dimension. int

TrainablePipe.to_disk method

Serialize the pipe to disk.

NameDescription
pathA path to a directory, which will be created if it doesn’t exist. Paths may be either strings or Path-like objects. Union[str, Path]
keyword-only
excludeString names of serialization fields to exclude. Iterable[str]

TrainablePipe.from_disk method

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

NameDescription
pathA path to a directory. Paths may be either strings or Path-like objects. Union[str, Path]
keyword-only
excludeString names of serialization fields to exclude. Iterable[str]

TrainablePipe.to_bytes method

Serialize the pipe to a bytestring.

NameDescription
keyword-only
excludeString names of serialization fields to exclude. Iterable[str]

TrainablePipe.from_bytes method

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

NameDescription
bytes_dataThe data to load from. bytes
keyword-only
excludeString names of serialization fields to exclude. Iterable[str]

Attributes

NameDescription
vocabThe shared vocabulary that’s passed in on initialization. Vocab
modelThe model powering the component. Model[List[Doc], Any]
nameThe name of the component instance in the pipeline. Can be used in the losses. str
cfgKeyword arguments passed to TrainablePipe.__init__. Will be serialized with the component. Dict[str, Any]

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.

NameDescription
cfgThe config file. You usually don’t want to exclude this.
modelThe binary model data. You usually don’t want to exclude this.