TextCategorizer

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 {id="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. This also means that for textcat, missing values are equated to a value of 0 (i.e. False) and are counted as such towards the loss and scoring metrics. This is not the case for textcat_multilabel, where missing values in the gold standard data do not influence the loss or accuracy calculations.

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.

Config and implementation {id="config"}

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)

pythonCopy

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

Example (textcat_multilabel)

pythonCopy

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)

%%GITHUB_SPACY/spacy/pipeline/textcat.py

%%GITHUB_SPACY/spacy/pipeline/textcat_multilabel.py

TextCategorizer.__init__ {id="init",tag="method"}

Example

pythonCopy

# 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.

TextCategorizer.__call__ {id="call",tag="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.

Example

pythonCopy

doc = nlp("This is a sentence.")
textcat = nlp.add_pipe("textcat")
# This usually happens under the hood
processed = textcat(doc)

TextCategorizer.pipe {id="pipe",tag="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.

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
for doc in textcat.pipe(docs, batch_size=50):
    pass

TextCategorizer.initialize {id="initialize",tag="method",version="3"}

Initialize the component for training. get_examples should be a function that returns an iterable of Example objects. At least one example should be supplied. 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

pythonCopy

textcat = nlp.add_pipe("textcat")
textcat.initialize(lambda: examples, nlp=nlp)

iniCopy

### config.cfg
[initialize.components.textcat]
positive_label = "POS"

[initialize.components.textcat.labels]
@readers = "spacy.read_labels.v1"
path = "corpus/labels/textcat.json

TextCategorizer.predict {id="predict",tag="method"}

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

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
scores = textcat.predict([doc1, doc2])

TextCategorizer.set_annotations {id="set_annotations",tag="method"}

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

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
scores = textcat.predict(docs)
textcat.set_annotations(docs, scores)

TextCategorizer.update {id="update",tag="method"}

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

pythonCopy

textcat = nlp.add_pipe("textcat")
optimizer = nlp.initialize()
losses = textcat.update(examples, sgd=optimizer)

TextCategorizer.rehearse {id="rehearse",tag="method,experimental",version="3"}

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

pythonCopy

textcat = nlp.add_pipe("textcat")
optimizer = nlp.resume_training()
losses = textcat.rehearse(examples, sgd=optimizer)

TextCategorizer.get_loss {id="get_loss",tag="method"}

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

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
scores = textcat.predict([eg.predicted for eg in examples])
loss, d_loss = textcat.get_loss(examples, scores)

TextCategorizer.score {id="score",tag="method",version="3"}

Score a batch of examples.

Example

pythonCopy

scores = textcat.score(examples)

TextCategorizer.create_optimizer {id="create_optimizer",tag="method"}

Create an optimizer for the pipeline component.

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
optimizer = textcat.create_optimizer()

TextCategorizer.use_params {id="use_params",tag="method, contextmanager"}

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

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
with textcat.use_params(optimizer.averages):
    textcat.to_disk("/best_model")

TextCategorizer.add_label {id="add_label",tag="method"}

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

pythonCopy

textcat = nlp.add_pipe("textcat")
textcat.add_label("MY_LABEL")

TextCategorizer.to_disk {id="to_disk",tag="method"}

Serialize the pipe to disk.

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
textcat.to_disk("/path/to/textcat")

TextCategorizer.from_disk {id="from_disk",tag="method"}

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

Example

pythonCopy

textcat = nlp.add_pipe("textcat")
textcat.from_disk("/path/to/textcat")

TextCategorizer.to_bytes {id="to_bytes",tag="method"}

Example

pythonCopy

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

Serialize the pipe to a bytestring.

TextCategorizer.from_bytes {id="from_bytes",tag="method"}

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

Example

pythonCopy

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

TextCategorizer.labels {id="labels",tag="property"}

The labels currently added to the component.

Example

pythonCopy

textcat.add_label("MY_LABEL")
assert "MY_LABEL" in textcat.labels

TextCategorizer.label_data {id="label_data",tag="property",version="3"}

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

pythonCopy

labels = textcat.label_data
textcat.initialize(lambda: [], nlp=nlp, labels=labels)

Serialization fields {id="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

pythonCopy

data = textcat.to_disk("/path", exclude=["vocab"])