mirror of
https://github.com/explosion/spaCy.git
synced 2025-07-05 04:13:05 +03:00
Merge pull request #5933 from svlandeg/feature/more-v3-docs [ci skip]
This commit is contained in:
commit
2285e59765
|
@ -216,7 +216,7 @@ list of available editor integrations.
|
|||
#### Disabling formatting
|
||||
|
||||
There are a few cases where auto-formatting doesn't improve readability – for
|
||||
example, in some of the the language data files like the `tag_map.py`, or in
|
||||
example, in some of the language data files like the `tag_map.py`, or in
|
||||
the tests that construct `Doc` objects from lists of words and other labels.
|
||||
Wrapping a block in `# fmt: off` and `# fmt: on` lets you disable formatting
|
||||
for that particular code. Here's an example:
|
||||
|
|
|
@ -235,7 +235,7 @@ def train_while_improving(
|
|||
with each iteration yielding a tuple `(batch, info, is_best_checkpoint)`,
|
||||
where info is a dict, and is_best_checkpoint is in [True, False, None] --
|
||||
None indicating that the iteration was not evaluated as a checkpoint.
|
||||
The evaluation is conducted by calling the evaluate callback, which should
|
||||
The evaluation is conducted by calling the evaluate callback.
|
||||
|
||||
Positional arguments:
|
||||
nlp: The spaCy pipeline to evaluate.
|
||||
|
|
|
@ -546,7 +546,7 @@ network has an internal CNN Tok2Vec layer and uses attention.
|
|||
<!-- TODO: model return type -->
|
||||
|
||||
| Name | Description |
|
||||
| -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
|
||||
| `pretrained_vectors` | Whether or not pretrained vectors will be used in addition to the feature vectors. ~~bool~~ |
|
||||
| `width` | Output dimension of the feature encoding step. ~~int~~ |
|
||||
|
@ -555,7 +555,7 @@ network has an internal CNN Tok2Vec layer and uses attention.
|
|||
| `window_size` | The number of contextual vectors to [concatenate](https://thinc.ai/docs/api-layers#expand_window) from the left and from the right. ~~int~~ |
|
||||
| `ngram_size` | Determines the maximum length of the n-grams in the BOW model. For instance, `ngram_size=3`would give unigram, trigram and bigram features. ~~int~~ |
|
||||
| `dropout` | The dropout rate. ~~float~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the the [`TextCategorizer`](/api/textcategorizer) component will set it when `begin_training` is called. ~~Optional[int]~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `begin_training` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model~~ |
|
||||
|
||||
### spacy.TextCatCNN.v1 {#TextCatCNN}
|
||||
|
@ -586,10 +586,10 @@ architecture is usually less accurate than the ensemble, but runs faster.
|
|||
<!-- TODO: model return type -->
|
||||
|
||||
| Name | Description |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
|
||||
| `tok2vec` | The [`tok2vec`](#tok2vec) layer of the model. ~~Model~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the the [`TextCategorizer`](/api/textcategorizer) component will set it when `begin_training` is called. ~~Optional[int]~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `begin_training` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model~~ |
|
||||
|
||||
### spacy.TextCatBOW.v1 {#TextCatBOW}
|
||||
|
@ -611,11 +611,11 @@ others, but may not be as accurate, especially if texts are short.
|
|||
<!-- TODO: model return type -->
|
||||
|
||||
| Name | Description |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
|
||||
| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| `exclusive_classes` | Whether or not categories are mutually exclusive. ~~bool~~ |
|
||||
| `ngram_size` | Determines the maximum length of the n-grams in the BOW model. For instance, `ngram_size=3`would give unigram, trigram and bigram features. ~~int~~ |
|
||||
| `no_output_layer` | Whether or not to add an output layer to the model (`Softmax` activation if `exclusive_classes` is `True`, else `Logistic`. ~~bool~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the the [`TextCategorizer`](/api/textcategorizer) component will set it when `begin_training` is called. ~~Optional[int]~~ |
|
||||
| `nO` | Output dimension, determined by the number of different labels. If not set, the [`TextCategorizer`](/api/textcategorizer) component will set it when `begin_training` is called. ~~Optional[int]~~ |
|
||||
| **CREATES** | The model using the architecture. ~~Model~~ |
|
||||
|
||||
## Entity linking architectures {#entitylinker source="spacy/ml/models/entity_linker.py"}
|
||||
|
|
|
@ -17,7 +17,7 @@ customize the data loading during training, you can register your own
|
|||
or evaluation data. It takes the same arguments as the `Corpus` class and
|
||||
returns a callable that yields [`Example`](/api/example) objects. You can
|
||||
replace it with your own registered function in the
|
||||
[`@readers` registry](/api/top-level#regsitry) to customize the data loading and
|
||||
[`@readers` registry](/api/top-level#registry) to customize the data loading and
|
||||
streaming.
|
||||
|
||||
> #### Example config
|
||||
|
|
|
@ -162,7 +162,7 @@ run [`spacy pretrain`](/api/cli#pretrain).
|
|||
| `dropout` | The dropout rate. Defaults to `0.2`. ~~float~~ |
|
||||
| `n_save_every` | Saving frequency. Defaults to `null`. ~~Optional[int]~~ |
|
||||
| `batch_size` | The batch size or batch size [schedule](https://thinc.ai/docs/api-schedules). Defaults to `3000`. ~~Union[int, Sequence[int]]~~ |
|
||||
| `seed` | The random seed. Defaults to variable `${system.seed}`. ~~int~~ |
|
||||
| `seed` | The random seed. Defaults to variable `${system:seed}`. ~~int~~ |
|
||||
| `use_pytorch_for_gpu_memory` | Allocate memory via PyTorch. Defaults to variable `${system:use_pytorch_for_gpu_memory}`. ~~bool~~ |
|
||||
| `tok2vec_model` | The model section of the embedding component in the config. Defaults to `"components.tok2vec.model"`. ~~str~~ |
|
||||
| `objective` | The pretraining objective. Defaults to `{"type": "characters", "n_characters": 4}`. ~~Dict[str, Any]~~ |
|
||||
|
|
|
@ -169,7 +169,7 @@ $ python setup.py build_ext --inplace # compile spaCy
|
|||
|
||||
Compared to regular install via pip, the
|
||||
[`requirements.txt`](https://github.com/explosion/spaCy/tree/master/requirements.txt)
|
||||
additionally installs developer dependencies such as Cython. See the the
|
||||
additionally installs developer dependencies such as Cython. See the
|
||||
[quickstart widget](#quickstart) to get the right commands for your platform and
|
||||
Python version.
|
||||
|
||||
|
|
|
@ -551,9 +551,9 @@ setup(
|
|||
)
|
||||
```
|
||||
|
||||
After installing the package, the the custom colors will be used when
|
||||
visualizing text with `displacy`. Whenever the label `SNEK` is assigned, it will
|
||||
be displayed in `#3dff74`.
|
||||
After installing the package, the custom colors will be used when visualizing
|
||||
text with `displacy`. Whenever the label `SNEK` is assigned, it will be
|
||||
displayed in `#3dff74`.
|
||||
|
||||
import DisplaCyEntSnekHtml from 'images/displacy-ent-snek.html'
|
||||
|
||||
|
|
|
@ -144,7 +144,7 @@ https://github.com/explosion/spaCy/blob/develop/spacy/default_config.cfg
|
|||
|
||||
Under the hood, the config is parsed into a dictionary. It's divided into
|
||||
sections and subsections, indicated by the square brackets and dot notation. For
|
||||
example, `[training]` is a section and `[training.batch_size]` a subsections.
|
||||
example, `[training]` is a section and `[training.batch_size]` a subsection.
|
||||
Subsections can define values, just like a dictionary, or use the `@` syntax to
|
||||
refer to [registered functions](#config-functions). This allows the config to
|
||||
not just define static settings, but also construct objects like architectures,
|
||||
|
@ -156,7 +156,7 @@ sections of a config file are:
|
|||
| `nlp` | Definition of the `nlp` object, its tokenizer and [processing pipeline](/usage/processing-pipelines) component names. |
|
||||
| `components` | Definitions of the [pipeline components](/usage/processing-pipelines) and their models. |
|
||||
| `paths` | Paths to data and other assets. Re-used across the config as variables, e.g. `${paths:train}`, and can be [overwritten](#config-overrides) on the CLI. |
|
||||
| `system` | Settings related to system and hardware. Re-used across the config as variables, e.g. `${system.seed}`, and can be [overwritten](#config-overrides) on the CLI. |
|
||||
| `system` | Settings related to system and hardware. Re-used across the config as variables, e.g. `${system:seed}`, and can be [overwritten](#config-overrides) on the CLI. |
|
||||
| `training` | Settings and controls for the training and evaluation process. |
|
||||
| `pretraining` | Optional settings and controls for the [language model pretraining](#pretraining). |
|
||||
|
||||
|
@ -514,11 +514,11 @@ language class and `nlp` object at different points of the lifecycle:
|
|||
| `after_creation` | Called right after the `nlp` object is created, but before the pipeline components are added to the pipeline and receives the `nlp` object. Useful for modifying the tokenizer. |
|
||||
| `after_pipeline_creation` | Called right after the pipeline components are created and added and receives the `nlp` object. Useful for modifying pipeline components. |
|
||||
|
||||
The `@spacy.registry.callbacks` decorator lets you register that function in the
|
||||
`callbacks` [registry](/api/top-level#registry) under a given name. You can then
|
||||
reference the function in a config block using the `@callbacks` key. If a block
|
||||
contains a key starting with an `@`, it's interpreted as a reference to a
|
||||
function. Because you've registered the function, spaCy knows how to create it
|
||||
The `@spacy.registry.callbacks` decorator lets you register your custom function
|
||||
in the `callbacks` [registry](/api/top-level#registry) under a given name. You
|
||||
can then reference the function in a config block using the `@callbacks` key. If
|
||||
a block contains a key starting with an `@`, it's interpreted as a reference to
|
||||
a function. Because you've registered the function, spaCy knows how to create it
|
||||
when you reference `"customize_language_data"` in your config. Here's an example
|
||||
of a callback that runs before the `nlp` object is created and adds a few custom
|
||||
tokenization rules to the defaults:
|
||||
|
@ -593,9 +593,9 @@ spaCy's configs are powered by our machine learning library Thinc's
|
|||
using [`pydantic`](https://github.com/samuelcolvin/pydantic). If your registered
|
||||
function provides type hints, the values that are passed in will be checked
|
||||
against the expected types. For example, `debug: bool` in the example above will
|
||||
ensure that the value received as the argument `debug` is an boolean. If the
|
||||
ensure that the value received as the argument `debug` is a boolean. If the
|
||||
value can't be coerced into a boolean, spaCy will raise an error.
|
||||
`start: pydantic.StrictBool` will force the value to be an boolean and raise an
|
||||
`debug: pydantic.StrictBool` will force the value to be a boolean and raise an
|
||||
error if it's not – for instance, if your config defines `1` instead of `true`.
|
||||
|
||||
</Infobox>
|
||||
|
@ -642,7 +642,9 @@ settings in the block will be passed to the function as keyword arguments. Keep
|
|||
in mind that the config shouldn't have any hidden defaults and all arguments on
|
||||
the functions need to be represented in the config. If your function defines
|
||||
**default argument values**, spaCy is able to auto-fill your config when you run
|
||||
[`init fill-config`](/api/cli#init-fill-config).
|
||||
[`init fill-config`](/api/cli#init-fill-config). If you want to make sure that a
|
||||
given parameter is always explicitely set in the config, avoid setting a default
|
||||
value for it.
|
||||
|
||||
```ini
|
||||
### config.cfg (excerpt)
|
||||
|
@ -654,7 +656,68 @@ factor = 1.005
|
|||
|
||||
#### Example: Custom data reading and batching {#custom-code-readers-batchers}
|
||||
|
||||
<!-- TODO: -->
|
||||
Some use-cases require streaming in data or manipulating datasets on the fly,
|
||||
rather than generating all data beforehand and storing it to file. Instead of
|
||||
using the built-in reader `"spacy.Corpus.v1"`, which uses static file paths, you
|
||||
can create and register a custom function that generates
|
||||
[`Example`](/api/example) objects. The resulting generator can be infinite. When
|
||||
using this dataset for training, stopping criteria such as maximum number of
|
||||
steps, or stopping when the loss does not decrease further, can be used.
|
||||
|
||||
In this example we assume a custom function `read_custom_data()` which loads or
|
||||
generates texts with relevant textcat annotations. Then, small lexical
|
||||
variations of the input text are created before generating the final `Example`
|
||||
objects.
|
||||
|
||||
We can also customize the batching strategy by registering a new "batcher" which
|
||||
turns a stream of items into a stream of batches. spaCy has several useful
|
||||
built-in batching strategies with customizable sizes<!-- TODO: link -->, but
|
||||
it's also easy to implement your own. For instance, the following function takes
|
||||
the stream of generated `Example` objects, and removes those which have the
|
||||
exact same underlying raw text, to avoid duplicates within each batch. Note that
|
||||
in a more realistic implementation, you'd also want to check whether the
|
||||
annotations are exactly the same.
|
||||
|
||||
> ```ini
|
||||
> [training.train_corpus]
|
||||
> @readers = "corpus_variants.v1"
|
||||
>
|
||||
> [training.batcher]
|
||||
> @batchers = "filtering_batch.v1"
|
||||
> size = 150
|
||||
> ```
|
||||
|
||||
```python
|
||||
### functions.py
|
||||
from typing import Callable, Iterable, List
|
||||
import spacy
|
||||
from spacy.gold import Example
|
||||
import random
|
||||
|
||||
@spacy.registry.readers("corpus_variants.v1")
|
||||
def stream_data() -> Callable[["Language"], Iterable[Example]]:
|
||||
def generate_stream(nlp):
|
||||
for text, cats in read_custom_data():
|
||||
random_index = random.randint(0, len(text) - 1)
|
||||
variant = text[:random_index] + text[random_index].upper() + text[random_index + 1:]
|
||||
doc = nlp.make_doc(variant)
|
||||
example = Example.from_dict(doc, {"cats": cats})
|
||||
yield example
|
||||
return generate_stream
|
||||
|
||||
|
||||
@spacy.registry.batchers("filtering_batch.v1")
|
||||
def filter_batch(size: int) -> Callable[[Iterable[Example]], Iterable[List[Example]]]:
|
||||
def create_filtered_batches(examples: Iterable[Example]) -> Iterable[List[Example]]:
|
||||
batch = []
|
||||
for eg in examples:
|
||||
if eg.text not in [x.text for x in batch]:
|
||||
batch.append(eg)
|
||||
if len(batch) == size:
|
||||
yield batch
|
||||
batch = []
|
||||
return create_filtered_batches
|
||||
```
|
||||
|
||||
### Wrapping PyTorch and TensorFlow {#custom-frameworks}
|
||||
|
||||
|
|
|
@ -60,7 +60,7 @@
|
|||
"clear": "rm -rf .cache",
|
||||
"test": "echo \"Write tests! -> https://gatsby.app/unit-testing\"",
|
||||
"python:install": "pip install setup/requirements.txt",
|
||||
"python:setup": "cd setup && ./setup.sh"
|
||||
"python:setup": "cd setup && sh setup.sh"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@sindresorhus/slugify": "^0.8.0",
|
||||
|
|
|
@ -2,7 +2,7 @@
|
|||
# With additional functionality: in/not in, replace, pprint, round, + for lists,
|
||||
# rendering empty dicts
|
||||
# This script is mostly used to generate the JavaScript function for the
|
||||
# training quicktart widget.
|
||||
# training quickstart widget.
|
||||
import contextlib
|
||||
import json
|
||||
import re
|
||||
|
|
Loading…
Reference in New Issue
Block a user