explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-25 09:26:27 +03:00
Code Issues Packages Projects Releases Wiki Activity

textcat scoring fix and multi_label docs (#6974)

Browse Source 
* add multi-label textcat to menu

* add infobox on textcat API

* add info to v3 migration guide

* small edits

* further fixes in doc strings

* add infobox to textcat architectures

* add textcat_multilabel to overview of built-in components

* spelling

* fix unrelated warn msg

* Add textcat_multilabel to quickstart [ci skip]

* remove separate documentation page for multilabel_textcategorizer

* small edits

* positive label clarification

* avoid duplicating information in self.cfg and fix textcat.score

* fix multilabel textcat too

* revert threshold to storage in cfg

* revert threshold stuff for multi-textcat

Co-authored-by: Ines Montani <ines@ines.io>
This commit is contained in:
Sofie Van Landeghem 2021-03-09 13:04:22 +01:00 committed by GitHub
parent 39de3602e0
commit 932887b950
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
10 changed files with 191 additions and 520 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/cli/download.py
View File

@ -60,7 +60,7 @@ def download(model: str, direct: bool = False, sdist: bool = False, *pip_args) -
model_name = model
if model in OLD_MODEL_SHORTCUTS:
msg.warn(
f"As of spaCy v3.0, shortcuts like '{model}' are deprecated. Please"
f"As of spaCy v3.0, shortcuts like '{model}' are deprecated. Please "
f"use the full pipeline package name '{OLD_MODEL_SHORTCUTS[model]}' instead."
)
model_name = OLD_MODEL_SHORTCUTS[model]

16
spacy/pipeline/textcat.py
View File

@ -88,11 +88,9 @@ subword_features = true
def make_textcat(
nlp: Language, name: str, model: Model[List[Doc], List[Floats2d]], threshold: float
) -> "TextCategorizer":
"""Create a TextCategorizer compoment. The text categorizer predicts categories
over a whole document. It can learn one or more labels, and the labels can
be mutually exclusive (i.e. one true label per doc) or non-mutually exclusive
(i.e. zero or more labels may be true per doc). The multi-label setting is
controlled by the model instance that's provided.
"""Create a TextCategorizer component. The text categorizer predicts categories
over a whole document. It can learn one or more labels, and the labels are considered
to be mutually exclusive (i.e. one true label per doc).
model (Model[List[Doc], List[Floats2d]]): A model instance that predicts
scores for each category.
@ -317,9 +315,11 @@ class TextCategorizer(TrainablePipe):
get_examples (Callable[[], Iterable[Example]]): Function that
returns a representative sample of gold-standard Example objects.
nlp (Language): The current nlp object the component is part of.
labels: The labels to add to the component, typically generated by the
labels (Optional[Iterable[str]]): The labels to add to the component, typically generated by the
`init labels` command. If no labels are provided, the get_examples
callback is used to extract the labels from the data.
positive_label (Optional[str]): The positive label for a binary task with exclusive classes,
`None` otherwise and by default.
DOCS: https://spacy.io/api/textcategorizer#initialize
"""
@ -358,13 +358,13 @@ class TextCategorizer(TrainablePipe):
"""
validate_examples(examples, "TextCategorizer.score")
self._validate_categories(examples)
kwargs.setdefault("threshold", self.cfg["threshold"])
kwargs.setdefault("positive_label", self.cfg["positive_label"])
return Scorer.score_cats(
examples,
"cats",
labels=self.labels,
multi_label=False,
positive_label=self.cfg["positive_label"],
threshold=self.cfg["threshold"],
**kwargs,
)

19
spacy/pipeline/textcat_multilabel.py
View File

@ -88,11 +88,10 @@ subword_features = true
def make_multilabel_textcat(
nlp: Language, name: str, model: Model[List[Doc], List[Floats2d]], threshold: float
) -> "TextCategorizer":
"""Create a TextCategorizer compoment. The text categorizer predicts categories
over a whole document. It can learn one or more labels, and the labels can
be mutually exclusive (i.e. one true label per doc) or non-mutually exclusive
(i.e. zero or more labels may be true per doc). The multi-label setting is
controlled by the model instance that's provided.
"""Create a TextCategorizer component. The text categorizer predicts categories
over a whole document. It can learn one or more labels, and the labels are considered
to be non-mutually exclusive, which means that there can be zero or more labels
per doc).
model (Model[List[Doc], List[Floats2d]]): A model instance that predicts
scores for each category.
@ -104,7 +103,7 @@ def make_multilabel_textcat(
class MultiLabel_TextCategorizer(TextCategorizer):
"""Pipeline component for multi-label text classification.
DOCS: https://spacy.io/api/multilabel_textcategorizer
DOCS: https://spacy.io/api/textcategorizer
"""
def __init__(
@ -123,7 +122,7 @@ class MultiLabel_TextCategorizer(TextCategorizer):
losses during training.
threshold (float): Cutoff to consider a prediction "positive".
DOCS: https://spacy.io/api/multilabel_textcategorizer#init
DOCS: https://spacy.io/api/textcategorizer#init
"""
self.vocab = vocab
self.model = model
@ -149,7 +148,7 @@ class MultiLabel_TextCategorizer(TextCategorizer):
`init labels` command. If no labels are provided, the get_examples
callback is used to extract the labels from the data.
DOCS: https://spacy.io/api/multilabel_textcategorizer#initialize
DOCS: https://spacy.io/api/textcategorizer#initialize
"""
validate_get_examples(get_examples, "MultiLabel_TextCategorizer.initialize")
if labels is None:
@ -173,15 +172,15 @@ class MultiLabel_TextCategorizer(TextCategorizer):
examples (Iterable[Example]): The examples to score.
RETURNS (Dict[str, Any]): The scores, produced by Scorer.score_cats.
DOCS: https://spacy.io/api/multilabel_textcategorizer#score
DOCS: https://spacy.io/api/textcategorizer#score
"""
validate_examples(examples, "MultiLabel_TextCategorizer.score")
kwargs.setdefault("threshold", self.cfg["threshold"])
return Scorer.score_cats(
examples,
"cats",
labels=self.labels,
multi_label=True,
threshold=self.cfg["threshold"],
**kwargs,
)

48
spacy/tests/pipeline/test_textcat.py
View File

@ -370,3 +370,51 @@ def test_textcat_evaluation():
assert scores["cats_micro_p"] == 4 / 5
assert scores["cats_micro_r"] == 4 / 6
def test_textcat_threshold():
# Ensure the scorer can be called with a different threshold
nlp = English()
nlp.add_pipe("textcat")
train_examples = []
for text, annotations in TRAIN_DATA_SINGLE_LABEL:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
nlp.initialize(get_examples=lambda: train_examples)
# score the model (it's not actually trained but that doesn't matter)
scores = nlp.evaluate(train_examples)
assert 0 <= scores["cats_score"] <= 1
scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 1.0})
assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 0
scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0})
macro_f = scores["cats_score"]
assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0
scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0, "positive_label": "POSITIVE"})
pos_f = scores["cats_score"]
assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0
assert pos_f > macro_f
def test_textcat_multi_threshold():
# Ensure the scorer can be called with a different threshold
nlp = English()
nlp.add_pipe("textcat_multilabel")
train_examples = []
for text, annotations in TRAIN_DATA_SINGLE_LABEL:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
nlp.initialize(get_examples=lambda: train_examples)
# score the model (it's not actually trained but that doesn't matter)
scores = nlp.evaluate(train_examples)
assert 0 <= scores["cats_score"] <= 1
scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 1.0})
assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 0
scores = nlp.evaluate(train_examples, scorer_cfg={"threshold": 0})
assert scores["cats_f_per_type"]["POSITIVE"]["r"] == 1.0

11
website/docs/api/architectures.md
View File

@ -589,6 +589,17 @@ several different built-in architectures. It is recommended to experiment with
different architectures and settings to determine what works best on your
specific data and challenge.
<Infobox title="Single-label vs. multi-label classification" variant="warning">
When the architecture for a text classification challenge contains a setting for
`exclusive_classes`, it is important to use the correct value for the correct
pipeline component. The `textcat` component should always be used for
single-label use-cases where `exclusive_classes = true`, while the
`textcat_multilabel` should be used for multi-label settings with
`exclusive_classes = false`.
</Infobox>
### spacy.TextCatEnsemble.v2 {#TextCatEnsemble}
> #### Example Config

453
website/docs/api/multilabel_textcategorizer.md
View File

@ -1,453 +0,0 @@
---
title: Multi-label TextCategorizer
tag: class
source: spacy/pipeline/textcat_multilabel.py
new: 3
teaser: 'Pipeline component for multi-label text classification'
api_base_class: /api/pipe
api_string_name: textcat_multilabel
api_trainable: true
---
The text categorizer predicts **categories over a whole document**. It
learns non-mutually exclusive labels, which means that zero or more labels
may be true per document.
## Config and implementation {#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`](/api/language#add_pipe) or in your
[`config.cfg` for training](/usage/training#config). See the
[model architectures](/api/architectures) documentation for details on the
architectures and their arguments and hyperparameters.
> #### Example
>
> ```python
> 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](/api/architectures#TextCatEnsemble). ~~Model[List[Doc], List[Floats2d]]~~ |
```python
%%GITHUB_SPACY/spacy/pipeline/textcat_multilabel.py
```
## MultiLabel_TextCategorizer.\_\_init\_\_ {#init tag="method"}
> #### Example
>
> ```python
> # Construction via add_pipe with default model
> textcat = nlp.add_pipe("textcat_multilabel")
>
> # Construction via add_pipe with custom model
> config = {"model": {"@architectures": "my_textcat"}}
> parser = nlp.add_pipe("textcat_multilabel", config=config)
>
> # Construction from class
> from spacy.pipeline import MultiLabel_TextCategorizer
> textcat = MultiLabel_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`](/api/language#create_pipe).
| Name | Description |
| -------------- | -------------------------------------------------------------------------------------------------------------------------- |
| `vocab` | The shared vocabulary. ~~Vocab~~ |
| `model` | The Thinc [`Model`](https://thinc.ai/docs/api-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~~ |
## MultiLabel_TextCategorizer.\_\_call\_\_ {#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__`](/api/multilabel_textcategorizer#call) and [`pipe`](/api/multilabel_textcategorizer#pipe)
delegate to the [`predict`](/api/multilabel_textcategorizer#predict) and
[`set_annotations`](/api/multilabel_textcategorizer#set_annotations) methods.
> #### Example
>
> ```python
> doc = nlp("This is a sentence.")
> textcat = nlp.add_pipe("textcat_multilabel")
> # This usually happens under the hood
> processed = textcat(doc)
> ```
| Name | Description |
| ----------- | -------------------------------- |
| `doc` | The document to process. ~~Doc~~ |
| **RETURNS** | The processed document. ~~Doc~~ |
## MultiLabel_TextCategorizer.pipe {#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__`](/api/multilabel_textcategorizer#call) and
[`pipe`](/api/multilabel_textcategorizer#pipe) delegate to the
[`predict`](/api/multilabel_textcategorizer#predict) and
[`set_annotations`](/api/multilabel_textcategorizer#set_annotations) methods.
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> 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~~ |
## MultiLabel_TextCategorizer.initialize {#initialize tag="method" new="3"}
Initialize the component for training. `get_examples` should be a function that
returns an iterable of [`Example`](/api/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](https://thinc.ai/docs/usage-models#validation) and
setting up the label scheme based on the data. This method is typically called
by [`Language.initialize`](/api/language#initialize) and lets you customize
arguments it receives via the
[`[initialize.components]`](/api/data-formats#config-initialize) block in the
config.
<Infobox variant="warning" title="Changed in v3.0" id="begin_training">
This method was previously called `begin_training`.
</Infobox>
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> textcat.initialize(lambda: [], nlp=nlp)
> ```
>
> ```ini
> ### config.cfg
> [initialize.components.textcat_multilabel]
>
> [initialize.components.textcat_multilabel.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`](/api/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`](#label_data) property after initialization. To generate a reusable JSON file from your data, you should run the [`init labels`](/api/cli#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]]~~ |
## MultiLabel_TextCategorizer.predict {#predict tag="method"}
Apply the component's model to a batch of [`Doc`](/api/doc) objects without
modifying them.
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> scores = textcat.predict([doc1, doc2])
> ```
| Name | Description |
| ----------- | ------------------------------------------- |
| `docs` | The documents to predict. ~~Iterable[Doc]~~ |
| **RETURNS** | The model's prediction for each document. |
## MultiLabel_TextCategorizer.set_annotations {#set_annotations tag="method"}
Modify a batch of [`Doc`](/api/doc) objects using pre-computed scores.
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> 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 `MultiLabel_TextCategorizer.predict`. |
## MultiLabel_TextCategorizer.update {#update tag="method"}
Learn from a batch of [`Example`](/api/example) objects containing the
predictions and gold-standard annotations, and update the component's model.
Delegates to [`predict`](/api/multilabel_textcategorizer#predict) and
[`get_loss`](/api/multilabel_textcategorizer#get_loss).
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> optimizer = nlp.initialize()
> losses = textcat.update(examples, sgd=optimizer)
> ```
| Name | Description |
| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| `drop` | The dropout rate. ~~float~~ |
| `sgd` | An optimizer. Will be created via [`create_optimizer`](#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]~~ |
## MultiLabel_TextCategorizer.rehearse {#rehearse tag="method,experimental" new="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
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> optimizer = nlp.resume_training()
> losses = textcat.rehearse(examples, sgd=optimizer)
> ```
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------------------------------------ |
| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| `drop` | The dropout rate. ~~float~~ |
| `sgd` | An optimizer. Will be created via [`create_optimizer`](#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]~~ |
## MultiLabel_TextCategorizer.get_loss {#get_loss tag="method"}
Find the loss and gradient of loss for the batch of documents and their
predicted scores.
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat_multilabel")
> 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]~~ |
## MultiLabel_TextCategorizer.score {#score tag="method" new="3"}
Score a batch of examples.
> #### Example
>
> ```python
> scores = textcat.score(examples)
> ```
| Name | Description |
| ---------------- | -------------------------------------------------------------------------------------------------------------------- |
| `examples` | The examples to score. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| **RETURNS** | The scores, produced by [`Scorer.score_cats`](/api/scorer#score_cats). ~~Dict[str, Union[float, Dict[str, float]]]~~ |
## MultiLabel_TextCategorizer.create_optimizer {#create_optimizer tag="method"}
Create an optimizer for the pipeline component.
> #### Example
>
> ```python
> textcat = nlp.add_pipe("textcat")
> optimizer = textcat.create_optimizer()
> ```
| Name | Description |
| ----------- | ---------------------------- |
| **RETURNS** | The optimizer. ~~Optimizer~~ |
## MultiLabel_TextCategorizer.use_params {#use_params tag="method, contextmanager"}
Modify the pipe's model to use the given parameter values.
> #### Example
>
> ```python
> 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~~ |
## MultiLabel_TextCategorizer.add_label {#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](#initialize). Note
that you don't have to call this method if you provide a **representative data
sample** to the [`initialize`](#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](/usage/layers-architectures#thinc-shape-inference)
automatically.
> #### Example
>
> ```python
> 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~~ |
## MultiLabel_TextCategorizer.to_disk {#to_disk tag="method"}
Serialize the pipe to disk.
> #### Example
>
> ```python
> 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](#serialization-fields) to exclude. ~~Iterable[str]~~ |
## MultiLabel_TextCategorizer.from_disk {#from_disk tag="method"}
Load the pipe from disk. Modifies the object in place and returns it.
> #### Example
>
> ```python
> 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](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The modified `MultiLabel_TextCategorizer` object. ~~MultiLabel_TextCategorizer~~ |
## MultiLabel_TextCategorizer.to_bytes {#to_bytes tag="method"}
> #### Example
>
> ```python
> 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](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The serialized form of the `MultiLabel_TextCategorizer` object. ~~bytes~~ |
## MultiLabel_TextCategorizer.from_bytes {#from_bytes tag="method"}
Load the pipe from a bytestring. Modifies the object in place and returns it.
> #### Example
>
> ```python
> 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](#serialization-fields) to exclude. ~~Iterable[str]~~ |
| **RETURNS** | The `MultiLabel_TextCategorizer` object. ~~MultiLabel_TextCategorizer~~ |
## MultiLabel_TextCategorizer.labels {#labels tag="property"}
The labels currently added to the component.
> #### Example
>
> ```python
> textcat.add_label("MY_LABEL")
> assert "MY_LABEL" in textcat.labels
> ```
| Name | Description |
| ----------- | ------------------------------------------------------ |
| **RETURNS** | The labels added to the component. ~~Tuple[str, ...]~~ |
## MultiLabel_TextCategorizer.label_data {#label_data tag="property" new="3"}
The labels currently added to the component and their internal meta information.
This is the data generated by [`init labels`](/api/cli#init-labels) and used by
[`MultiLabel_TextCategorizer.initialize`](/api/multilabel_textcategorizer#initialize) to initialize
the model with a pre-defined label set.
> #### Example
>
> ```python
> 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 {#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
>
> ```python
> data = textcat.to_disk("/path", exclude=["vocab"])
> ```
| Name | Description |
| ------- | -------------------------------------------------------------- |
| `vocab` | The shared [`Vocab`](/api/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. |

66
website/docs/api/textcategorizer.md
View File

@ -3,15 +3,30 @@ title: TextCategorizer
tag: class
source: spacy/pipeline/textcat.py
new: 2
teaser: 'Pipeline component for single-label text classification'
teaser: 'Pipeline component for text classification'
api_base_class: /api/pipe
api_string_name: textcat
api_trainable: true
---
The text categorizer predicts **categories over a whole document**. It can learn
one or more labels, and the labels are mutually exclusive - there is exactly one
true label per document.
The text categorizer predicts **categories over a whole document**. and comes in
two flavours: `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 labels per document, use the `textcat_multilabel` component
instead.
Both components are documented on this page.
<Infobox title="Migration from v2" variant="warning">
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.
</Infobox>
## Config and implementation {#config}
@ -22,7 +37,7 @@ how the component should be configured. You can override its settings via the
[model architectures](/api/architectures) documentation for details on the
architectures and their arguments and hyperparameters.
> #### Example
> #### Example (textcat)
>
> ```python
> from spacy.pipeline.textcat import DEFAULT_SINGLE_TEXTCAT_MODEL
@ -33,6 +48,17 @@ architectures and their arguments and hyperparameters.
> nlp.add_pipe("textcat", config=config)
> ```
> #### Example (textcat_multilabel)
>
> ```python
> 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~~ |
@ -48,6 +74,7 @@ architectures and their arguments and hyperparameters.
>
> ```python
> # 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
@ -55,6 +82,7 @@ architectures and their arguments and hyperparameters.
> 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)
> ```
@ -161,7 +189,7 @@ This method was previously called `begin_training`.
| _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`](#label_data) property after initialization. To generate a reusable JSON file from your data, you should run the [`init labels`](/api/cli#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. ~~Optional[str]~~ |
| `positive_label` | The positive label for a binary task with exclusive classes, `None` otherwise and by default. This parameter is not available when using the `textcat_multilabel` component. ~~Optional[str]~~ |
## TextCategorizer.predict {#predict tag="method"}
@ -212,14 +240,14 @@ Delegates to [`predict`](/api/textcategorizer#predict) and
> losses = textcat.update(examples, sgd=optimizer)
> ```
| Name | Description |
| ----------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| `drop` | The dropout rate. ~~float~~ |
| `sgd` | An optimizer. Will be created via [`create_optimizer`](#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]~~ |
| Name | Description |
| -------------- | ------------------------------------------------------------------------------------------------------------------------ |
| `examples` | A batch of [`Example`](/api/example) objects to learn from. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| `drop` | The dropout rate. ~~float~~ |
| `sgd` | An optimizer. Will be created via [`create_optimizer`](#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 {#rehearse tag="method,experimental" new="3"}
@ -273,11 +301,11 @@ Score a batch of examples.
> scores = textcat.score(examples)
> ```
| Name | Description |
| ---------------- | -------------------------------------------------------------------------------------------------------------------- |
| `examples` | The examples to score. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| **RETURNS** | The scores, produced by [`Scorer.score_cats`](/api/scorer#score_cats). ~~Dict[str, Union[float, Dict[str, float]]]~~ |
| Name | Description |
| -------------- | -------------------------------------------------------------------------------------------------------------------- |
| `examples` | The examples to score. ~~Iterable[Example]~~ |
| _keyword-only_ | |
| **RETURNS** | The scores, produced by [`Scorer.score_cats`](/api/scorer#score_cats). ~~Dict[str, Union[float, Dict[str, float]]]~~ |
## TextCategorizer.create_optimizer {#create_optimizer tag="method"}

37
website/docs/usage/processing-pipelines.md
View File

@ -223,21 +223,22 @@ available pipeline components and component functions.
> ruler = nlp.add_pipe("entity_ruler")
> ```
| String name | Component | Description |
| ----------------- | ----------------------------------------------- | ----------------------------------------------------------------------------------------- |
| `tagger` | [`Tagger`](/api/tagger) | Assign part-of-speech-tags. |
| `parser` | [`DependencyParser`](/api/dependencyparser) | Assign dependency labels. |
| `ner` | [`EntityRecognizer`](/api/entityrecognizer) | Assign named entities. |
| `entity_linker` | [`EntityLinker`](/api/entitylinker) | Assign knowledge base IDs to named entities. Should be added after the entity recognizer. |
| `entity_ruler` | [`EntityRuler`](/api/entityruler) | Assign named entities based on pattern rules and dictionaries. |
| `textcat` | [`TextCategorizer`](/api/textcategorizer) | Assign text categories. |
| `lemmatizer` | [`Lemmatizer`](/api/lemmatizer) | Assign base forms to words. |
| `morphologizer` | [`Morphologizer`](/api/morphologizer) | Assign morphological features and coarse-grained POS tags. |
| `attribute_ruler` | [`AttributeRuler`](/api/attributeruler) | Assign token attribute mappings and rule-based exceptions. |
| `senter` | [`SentenceRecognizer`](/api/sentencerecognizer) | Assign sentence boundaries. |
| `sentencizer` | [`Sentencizer`](/api/sentencizer) | Add rule-based sentence segmentation without the dependency parse. |
| `tok2vec` | [`Tok2Vec`](/api/tok2vec) | Assign token-to-vector embeddings. |
| `transformer` | [`Transformer`](/api/transformer) | Assign the tokens and outputs of a transformer model. |
| String name | Component | Description |
| -------------------- | ---------------------------------------------------- | ----------------------------------------------------------------------------------------- |
| `tagger` | [`Tagger`](/api/tagger) | Assign part-of-speech-tags. |
| `parser` | [`DependencyParser`](/api/dependencyparser) | Assign dependency labels. |
| `ner` | [`EntityRecognizer`](/api/entityrecognizer) | Assign named entities. |
| `entity_linker` | [`EntityLinker`](/api/entitylinker) | Assign knowledge base IDs to named entities. Should be added after the entity recognizer. |
| `entity_ruler` | [`EntityRuler`](/api/entityruler) | Assign named entities based on pattern rules and dictionaries. |
| `textcat` | [`TextCategorizer`](/api/textcategorizer) | Assign text categories: exactly one category is predicted per document. |
| `textcat_multilabel` | [`MultiLabel_TextCategorizer`](/api/textcategorizer) | Assign text categories in a multi-label setting: zero, one or more labels per document. |
| `lemmatizer` | [`Lemmatizer`](/api/lemmatizer) | Assign base forms to words. |
| `morphologizer` | [`Morphologizer`](/api/morphologizer) | Assign morphological features and coarse-grained POS tags. |
| `attribute_ruler` | [`AttributeRuler`](/api/attributeruler) | Assign token attribute mappings and rule-based exceptions. |
| `senter` | [`SentenceRecognizer`](/api/sentencerecognizer) | Assign sentence boundaries. |
| `sentencizer` | [`Sentencizer`](/api/sentencizer) | Add rule-based sentence segmentation without the dependency parse. |
| `tok2vec` | [`Tok2Vec`](/api/tok2vec) | Assign token-to-vector embeddings. |
| `transformer` | [`Transformer`](/api/transformer) | Assign the tokens and outputs of a transformer model. |
### Disabling, excluding and modifying components {#disabling}
@ -400,8 +401,8 @@ vectors available – otherwise, it won't be able to make the same predictions.
> ```
>
> By default, sourced components will be updated with your data during training.
> If you want to preserve the component as-is, you can "freeze" it if the pipeline
> is not using a shared `Tok2Vec` layer:
> If you want to preserve the component as-is, you can "freeze" it if the
> pipeline is not using a shared `Tok2Vec` layer:
>
> ```ini
> [training]
@ -1244,7 +1245,7 @@ labels = []
# the argument "model"
[components.textcat.model]
@architectures = "spacy.TextCatBOW.v1"
exclusive_classes = false
exclusive_classes = true
ngram_size = 1
no_output_layer = false

21
website/docs/usage/v3.md
View File

@ -320,14 +320,15 @@ add to your pipeline and customize for your use case:
> nlp.add_pipe("lemmatizer")
> ```
| Name | Description |
| ----------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`SentenceRecognizer`](/api/sentencerecognizer) | Trainable component for sentence segmentation. |
| [`Morphologizer`](/api/morphologizer) | Trainable component to predict morphological features. |
| [`Lemmatizer`](/api/lemmatizer) | Standalone component for rule-based and lookup lemmatization. |
| [`AttributeRuler`](/api/attributeruler) | Component for setting token attributes using match patterns. |
| [`Transformer`](/api/transformer) | Component for using [transformer models](/usage/embeddings-transformers) in your pipeline, accessing outputs and aligning tokens. Provided via [`spacy-transformers`](https://github.com/explosion/spacy-transformers). |
| [`TrainablePipe`](/api/pipe) | Base class for trainable pipeline components. |
| Name | Description |
| ----------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| [`SentenceRecognizer`](/api/sentencerecognizer) | Trainable component for sentence segmentation. |
| [`Morphologizer`](/api/morphologizer) | Trainable component to predict morphological features. |
| [`Lemmatizer`](/api/lemmatizer) | Standalone component for rule-based and lookup lemmatization. |
| [`AttributeRuler`](/api/attributeruler) | Component for setting token attributes using match patterns. |
| [`Transformer`](/api/transformer) | Component for using [transformer models](/usage/embeddings-transformers) in your pipeline, accessing outputs and aligning tokens. Provided via [`spacy-transformers`](https://github.com/explosion/spacy-transformers). |
| [`TrainablePipe`](/api/pipe) | Base class for trainable pipeline components. |
| [`Multi-label TextCategorizer`](/api/textcategorizer) | Trainable component for multi-label text classification. |
<Infobox title="Details & Documentation" emoji="📖" list>
@ -592,6 +593,10 @@ Note that spaCy v3.0 now requires **Python 3.6+**.
- Various keyword arguments across functions and methods are now explicitly
declared as **keyword-only** arguments. Those arguments are documented
accordingly across the API reference using the <Tag>keyword-only</Tag> tag.
- The `textcat` pipeline component is now only applicable for classification of
mutually exclusives classes - i.e. one predicted class per input sentence or
document. To perform multi-label classification, use the new
`textcat_multilabel` component instead.
### Removed or renamed API {#incompat-removed}

38
website/src/widgets/quickstart-training.js
View File

@ -9,6 +9,7 @@ import { htmlToReact } from '../components/util'
const DEFAULT_LANG = 'en'
const DEFAULT_HARDWARE = 'cpu'
const DEFAULT_OPT = 'efficiency'
const DEFAULT_TEXTCAT_EXCLUSIVE = true
const COMPONENTS = ['tagger', 'parser', 'ner', 'textcat']
const COMMENT = `# This is an auto-generated partial config. To use it with 'spacy train'
# you can run spacy init fill-config to auto-fill all default settings:
@ -27,6 +28,19 @@ const DATA = [
options: COMPONENTS.map(id => ({ id, title: id })),
multiple: true,
},
{
id: 'textcat',
title: 'Text Classification',
multiple: true,
options: [
{
id: 'exclusive',
title: 'exclusive categories',
checked: DEFAULT_TEXTCAT_EXCLUSIVE,
help: 'only one label can apply',
},
],
},
{
id: 'hardware',
title: 'Hardware',
@ -49,14 +63,28 @@ const DATA = [
export default function QuickstartTraining({ id, title, download = 'base_config.cfg' }) {
const [lang, setLang] = useState(DEFAULT_LANG)
const [_components, _setComponents] = useState([])
const [components, setComponents] = useState([])
const [[hardware], setHardware] = useState([DEFAULT_HARDWARE])
const [[optimize], setOptimize] = useState([DEFAULT_OPT])
const [textcatExclusive, setTextcatExclusive] = useState(DEFAULT_TEXTCAT_EXCLUSIVE)
function updateComponents(value, isExclusive) {
_setComponents(value)
const updated = value.map(c => (c === 'textcat' && !isExclusive ? 'textcat_multilabel' : c))
setComponents(updated)
}
const setters = {
lang: setLang,
components: setComponents,
components: v => updateComponents(v, textcatExclusive),
hardware: setHardware,
optimize: setOptimize,
textcat: v => {
const isExclusive = v.includes('exclusive')
setTextcatExclusive(isExclusive)
updateComponents(_components, isExclusive)
},
}
const reco = GENERATOR_DATA[lang] || GENERATOR_DATA.__default__
const content = generator({
@ -78,20 +106,24 @@ export default function QuickstartTraining({ id, title, download = 'base_config.
<StaticQuery
query={query}
render={({ site }) => {
let data = DATA
const langs = site.siteMetadata.languages
DATA[0].dropdown = langs
data[0].dropdown = langs
.map(({ name, code }) => ({
id: code,
title: name,
}))
.sort((a, b) => a.title.localeCompare(b.title))
if (!_components.includes('textcat')) {
data = data.filter(({ id }) => id !== 'textcat')
}
return (
<Quickstart
id="quickstart-widget"
Container="div"
download={download}
rawContent={rawContent}
data={DATA}
data={data}
title={title}
id={id}
setters={setters}