Method initialize

spacy/language.py:1293–1367

Initialize the pipe for training, using data examples if available. get_examples (Callable[[], Iterable[Example]]): Optional function that returns gold-standard Example objects. sgd (Optional[Optimizer]): An optimizer to use for updates. If not provided, will

(
        self,
        get_examples: Optional[Callable[[], Iterable[Example]]] = None,
        *,
        sgd: Optional[Optimizer] = None,
    )

        return self.initialize(get_examples, sgd=sgd)

    def initialize(
        self,
        get_examples: Optional[Callable[[], Iterable[Example]]] = None,
        *,
        sgd: Optional[Optimizer] = None,
    ) -> Optimizer:
        """Initialize the pipe for training, using data examples if available.

        get_examples (Callable[[], Iterable[Example]]): Optional function that
            returns gold-standard Example objects.
        sgd (Optional[Optimizer]): An optimizer to use for updates. If not
            provided, will be created using the .create_optimizer() method.
        RETURNS (thinc.api.Optimizer): The optimizer.

        DOCS: https://spacy.io/api/language#initialize
        """
        if get_examples is None:
            util.logger.debug(
                "No 'get_examples' callback provided to 'Language.initialize', creating dummy examples"
            )
            doc = Doc(self.vocab, words=["x", "y", "z"])

            def get_examples():
                return [Example.from_dict(doc, {})]

        if not hasattr(get_examples, "__call__"):
            err = Errors.E930.format(
                method="Language.initialize", obj=type(get_examples)
            )
            raise TypeError(err)
        # Make sure the config is interpolated so we can resolve subsections
        config = self.config.interpolate()
        # These are the settings provided in the [initialize] block in the config
        I = registry.resolve(config["initialize"], schema=ConfigSchemaInit)  # type: ignore[arg-type]
        before_init = I["before_init"]
        if before_init is not None:
            before_init(self)
        try:
            init_vocab(
                self, data=I["vocab_data"], lookups=I["lookups"], vectors=I["vectors"]
            )
        except IOError:
            raise IOError(Errors.E884.format(vectors=I["vectors"]))
        if self.vocab.vectors.shape[1] >= 1:
            ops = get_current_ops()
            self.vocab.vectors.to_ops(ops)
        if hasattr(self.tokenizer, "initialize"):
            tok_settings = validate_init_settings(
                self.tokenizer.initialize,  # type: ignore[union-attr]
                I["tokenizer"],
                section="tokenizer",
                name="tokenizer",
            )
            self.tokenizer.initialize(get_examples, nlp=self, **tok_settings)  # type: ignore[union-attr]
        for name, proc in self.pipeline:
            if isinstance(proc, ty.InitializableComponent):
                p_settings = I["components"].get(name, {})
                p_settings = validate_init_settings(