spaCy/website/docs/api/textcategorizer.md
Paul O'Leary McCann ba6a37d358
Document Assigned Attributes of Pipeline Components (#9041)
* Add textcat docs

* Add NER docs

* Add Entity Linker docs

* Add assigned fields docs for the tagger

This also adds a preamble, since there wasn't one.

* Add morphologizer docs

* Add dependency parser docs

* Update entityrecognizer docs

This is a little weird because `Doc.ents` is the only thing assigned to,
but it's actually a bidirectional property.

* Add token fields for entityrecognizer

* Fix section name

* Add entity ruler docs

* Add lemmatizer docs

* Add sentencizer/recognizer docs

* Update website/docs/api/entityrecognizer.md

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Update website/docs/api/entityruler.md

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Update website/docs/api/tagger.md

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Update website/docs/api/entityruler.md

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* Update type for Doc.ents

This was `Tuple[Span, ...]` everywhere but `Tuple[Span]` seems to be
correct.

* Run prettier

* Apply suggestions from code review

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Run prettier

* Add transformers section

This basically just moves and renames the "custom attributes" section
from the bottom of the page to be consistent with "assigned attributes"
on other pages.

I looked at moving the paragraph just above the section into the
section, but it includes the unrelated registry additions, so it seemed
better to leave it unchanged.

* Make table header consistent

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
2021-09-01 12:09:39 +02:00

24 KiB

title tag source new teaser api_base_class api_string_name api_trainable
TextCategorizer class spacy/pipeline/textcat.py 2 Pipeline component for text classification /api/pipe textcat true

The text categorizer predicts categories over a whole document. and comes in two flavors: textcat and textcat_multilabel. When you need to predict exactly one true label per document, use the textcat which has mutually exclusive labels. If you want to perform multi-label classification and predict zero, one or more true labels per document, use the textcat_multilabel component instead. For a binary classification task, you can use textcat with two labels or textcat_multilabel with one label.

Both components are documented on this page.

In spaCy v2, the textcat component could also perform multi-label classification, and even used this setting by default. Since v3.0, the component textcat_multilabel should be used for multi-label classification instead. The textcat component is now used for mutually exclusive classes only.

Assigned Attributes

Predictions will be saved to doc.cats as a dictionary, where the key is the name of the category and the value is a score between 0 and 1 (inclusive). For textcat (exclusive categories), the scores will sum to 1, while for textcat_multilabel there is no particular guarantee about their sum.

Note that when assigning values to create training data, the score of each category must be 0 or 1. Using other values, for example to create a document that is a little bit in category A and a little bit in category B, is not supported.

Location Value
Doc.cats Category scores. Dict[str, float]

Config and implementation

The default config is defined by the pipeline component factory and describes how the component should be configured. You can override its settings via the config argument on nlp.add_pipe or in your config.cfg for training. See the model architectures documentation for details on the architectures and their arguments and hyperparameters.

Example (textcat)

from spacy.pipeline.textcat import DEFAULT_SINGLE_TEXTCAT_MODEL
config = {
   "threshold": 0.5,
   "model": DEFAULT_SINGLE_TEXTCAT_MODEL,
}
nlp.add_pipe("textcat", config=config)

Example (textcat_multilabel)

from spacy.pipeline.textcat_multilabel import DEFAULT_MULTI_TEXTCAT_MODEL
config = {
   "threshold": 0.5,
   "model": DEFAULT_MULTI_TEXTCAT_MODEL,
}
nlp.add_pipe("textcat_multilabel", config=config)
Setting Description
threshold Cutoff to consider a prediction "positive", relevant when printing accuracy results. float
model A model instance that predicts scores for each category. Defaults to TextCatEnsemble. Model[List[Doc], List[Floats2d]]
%%GITHUB_SPACY/spacy/pipeline/textcat.py
%%GITHUB_SPACY/spacy/pipeline/textcat_multilabel.py

TextCategorizer.__init__

Example

# Construction via add_pipe with default model
# Use 'textcat_multilabel' for multi-label classification
textcat = nlp.add_pipe("textcat")

# Construction via add_pipe with custom model
config = {"model": {"@architectures": "my_textcat"}}
parser = nlp.add_pipe("textcat", config=config)

# Construction from class
# Use 'MultiLabel_TextCategorizer' for multi-label classification
from spacy.pipeline import TextCategorizer
textcat = TextCategorizer(nlp.vocab, model, threshold=0.5)

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.

Name Description
vocab The shared vocabulary. Vocab
model The Thinc Model powering the pipeline component. Model[List[Doc], List[Floats2d]]
name String name of the component instance. Used to add entries to the losses during training. str
keyword-only
threshold Cutoff to consider a prediction "positive", relevant when printing accuracy results. float

TextCategorizer.__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.")
textcat = nlp.add_pipe("textcat")
# This usually happens under the hood
processed = textcat(doc)
Name Description
doc The document to process. Doc
RETURNS The processed document. Doc

TextCategorizer.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

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

TextCategorizer.initialize

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 and lets you customize arguments it receives via the [initialize.components] block in the config.

This method was previously called begin_training.

Example

textcat = nlp.add_pipe("textcat")
textcat.initialize(lambda: [], nlp=nlp)
### config.cfg
[initialize.components.textcat]
positive_label = "POS"

[initialize.components.textcat.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/textcat.json
Name Description
get_examples Function that returns gold-standard annotations in the form of Example objects. Callable], Iterable[Example
keyword-only
nlp The current nlp object. Defaults to None. Optional[Language]
labels The label information to add to the component, as provided by the label_data property after initialization. To generate a reusable JSON file from your data, you should run the init labels command. If no labels are provided, the get_examples callback is used to extract the labels from the data, which may be a lot slower. Optional[Iterable[str]]
positive_label The positive label for a binary task with exclusive classes, None otherwise and by default. This parameter is only used during scoring. It is not available when using the textcat_multilabel component. Optional[str]

TextCategorizer.predict

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

Example

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

TextCategorizer.set_annotations

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

Example

textcat = nlp.add_pipe("textcat")
scores = textcat.predict(docs)
textcat.set_annotations(docs, scores)
Name Description
docs The documents to modify. Iterable[Doc]
scores The scores to set, produced by TextCategorizer.predict.

TextCategorizer.update

Learn from a batch of Example objects containing the predictions and gold-standard annotations, and update the component's model. Delegates to predict and get_loss.

Example

textcat = nlp.add_pipe("textcat")
optimizer = nlp.initialize()
losses = textcat.update(examples, sgd=optimizer)
Name Description
examples A batch of Example objects to learn from. Iterable[Example]
keyword-only
drop The dropout rate. float
sgd An optimizer. Will be created via create_optimizer if not set. Optional[Optimizer]
losses Optional record of the loss during training. Updated using the component name as the key. Optional[Dict[str, float]]
RETURNS The updated losses dictionary. Dict[str, float]

TextCategorizer.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

textcat = nlp.add_pipe("textcat")
optimizer = nlp.resume_training()
losses = textcat.rehearse(examples, sgd=optimizer)
Name Description
examples A batch of Example objects to learn from. Iterable[Example]
keyword-only
drop The dropout rate. float
sgd An optimizer. Will be created via create_optimizer if not set. Optional[Optimizer]
losses Optional record of the loss during training. Updated using the component name as the key. Optional[Dict[str, float]]
RETURNS The updated losses dictionary. Dict[str, float]

TextCategorizer.get_loss

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

Example

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

TextCategorizer.score

Score a batch of examples.

Example

scores = textcat.score(examples)
Name Description
examples The examples to score. Iterable[Example]
keyword-only
RETURNS The scores, produced by Scorer.score_cats. Dict[str, Union[float, Dict[str, float]]]

TextCategorizer.create_optimizer

Create an optimizer for the pipeline component.

Example

textcat = nlp.add_pipe("textcat")
optimizer = textcat.create_optimizer()
Name Description
RETURNS The optimizer. Optimizer

TextCategorizer.use_params

Modify the pipe's model to use the given parameter values.

Example

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

TextCategorizer.add_label

Add a new label to the pipe. Raises an error if the output dimension is already set, or if the model has already been fully initialized. Note that you don't have to call this method 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.

Example

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

TextCategorizer.to_disk

Serialize the pipe to disk.

Example

textcat = nlp.add_pipe("textcat")
textcat.to_disk("/path/to/textcat")
Name Description
path A 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
exclude String names of serialization fields to exclude. Iterable[str]

TextCategorizer.from_disk

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

Example

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

TextCategorizer.to_bytes

Example

textcat = nlp.add_pipe("textcat")
textcat_bytes = textcat.to_bytes()

Serialize the pipe to a bytestring.

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

TextCategorizer.from_bytes

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

Example

textcat_bytes = textcat.to_bytes()
textcat = nlp.add_pipe("textcat")
textcat.from_bytes(textcat_bytes)
Name Description
bytes_data The data to load from. bytes
keyword-only
exclude String names of serialization fields to exclude. Iterable[str]
RETURNS The TextCategorizer object. TextCategorizer

TextCategorizer.labels

The labels currently added to the component.

Example

textcat.add_label("MY_LABEL")
assert "MY_LABEL" in textcat.labels
Name Description
RETURNS The labels added to the component. Tuple[str, ...]

TextCategorizer.label_data

The labels currently added to the component and their internal meta information. This is the data generated by init labels and used by TextCategorizer.initialize to initialize the model with a pre-defined label set.

Example

labels = textcat.label_data
textcat.initialize(lambda: [], nlp=nlp, labels=labels)
Name Description
RETURNS The label data added to the component. Tuple[str, ...]

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 = textcat.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.