explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-05 12:50:20 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'explosion:master' into rapidfuzz

Browse Source
This commit is contained in:
Kevin Humphreys 2022-12-07 16:13:23 -08:00 committed by GitHub
commit b690c9120c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
34 changed files with 1007 additions and 805 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
.github/azure-steps.yml vendored
View File

@ -52,17 +52,17 @@ steps:
python -W error -c "import spacy"
displayName: "Test import"
- script: |
python -m spacy download ca_core_news_sm
python -m spacy download ca_core_news_md
python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
displayName: 'Test download CLI'
condition: eq(variables['python_version'], '3.8')
- script: |
python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
displayName: 'Test no warnings on load (#11713)'
condition: eq(variables['python_version'], '3.8')
# - script: |
# python -m spacy download ca_core_news_sm
# python -m spacy download ca_core_news_md
# python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
# displayName: 'Test download CLI'
# condition: eq(variables['python_version'], '3.8')
#
# - script: |
# python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
# displayName: 'Test no warnings on load (#11713)'
# condition: eq(variables['python_version'], '3.8')
- script: |
python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
@ -86,17 +86,17 @@ steps:
displayName: 'Test train CLI'
condition: eq(variables['python_version'], '3.8')
- script: |
python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
displayName: 'Test assemble CLI'
condition: eq(variables['python_version'], '3.8')
- script: |
python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
displayName: 'Test assemble CLI vectors warning'
condition: eq(variables['python_version'], '3.8')
# - script: |
# python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
# PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
# displayName: 'Test assemble CLI'
# condition: eq(variables['python_version'], '3.8')
#
# - script: |
# python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
# python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
# displayName: 'Test assemble CLI vectors warning'
# condition: eq(variables['python_version'], '3.8')
- script: |
python -m pip install -U -r requirements.txt

2
.github/workflows/lock.yml vendored
View File

@ -15,7 +15,7 @@ jobs:
action:
runs-on: ubuntu-latest
steps:
- uses: dessant/lock-threads@v3
- uses: dessant/lock-threads@v4
with:
process-only: 'issues'
issue-inactive-days: '30'

4
README.md
View File

@ -14,7 +14,7 @@ parsing, **named entity recognition**, **text classification** and more,
multi-task learning with pretrained **transformers** like BERT, as well as a
production-ready [**training system**](https://spacy.io/usage/training) and easy
model packaging, deployment and workflow management. spaCy is commercial
open-source software, released under the MIT license.
open-source software, released under the [MIT license](https://github.com/explosion/spaCy/blob/master/LICENSE).
💫 **Version 3.4 out now!**
[Check out the release notes here.](https://github.com/explosion/spaCy/releases)
@ -46,6 +46,7 @@ open-source software, released under the MIT license.
| 🛠 **[Changelog]** | Changes and version history. |
| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
| <a href="https://explosion.ai/spacy-tailored-pipelines"><img src="https://user-images.githubusercontent.com/13643239/152853098-1c761611-ccb0-4ec6-9066-b234552831fe.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Get a custom spaCy pipeline, tailor-made for your NLP problem by spaCy's core developers. Streamlined, production-ready, predictable and maintainable. Start by completing our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-pipelines)** |
| <a href="https://explosion.ai/spacy-tailored-analysis"><img src="https://user-images.githubusercontent.com/1019791/206151300-b00cd189-e503-4797-aa1e-1bb6344062c5.png" width="125" alt="spaCy Tailored Pipelines"/></a> | Bespoke advice for problem solving, strategy and analysis for applied NLP projects. Services include data strategy, code reviews, pipeline design and annotation coaching. Curious? Fill in our 5-minute questionnaire to tell us what you need and we'll be in touch! **[Learn more &rarr;](https://explosion.ai/spacy-tailored-analysis)** |
[spacy 101]: https://spacy.io/usage/spacy-101
[new in v3.0]: https://spacy.io/usage/v3
@ -59,6 +60,7 @@ open-source software, released under the MIT license.
[changelog]: https://spacy.io/usage#changelog
[contribute]: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
## 💬 Where to ask questions
The spaCy project is maintained by the [spaCy team](https://explosion.ai/about).

4
azure-pipelines.yml
View File

@ -41,7 +41,7 @@ jobs:
matrix:
# We're only running one platform per Python version to speed up builds
Python36Linux:
imageName: "ubuntu-latest"
imageName: "ubuntu-20.04"
python.version: "3.6"
# Python36Windows:
# imageName: "windows-latest"
@ -50,7 +50,7 @@ jobs:
# imageName: "macos-latest"
# python.version: "3.6"
# Python37Linux:
# imageName: "ubuntu-latest"
# imageName: "ubuntu-20.04"
# python.version: "3.7"
Python37Windows:
imageName: "windows-latest"

2
requirements.txt
View File

@ -10,7 +10,7 @@ wasabi>=0.9.1,<1.1.0
srsly>=2.4.3,<3.0.0
catalogue>=2.0.6,<2.1.0
typer>=0.3.0,<0.8.0
pathy>=0.3.5
pathy>=0.10.0
smart-open>=5.2.1,<7.0.0
# Third party dependencies
numpy>=1.15.0

2
setup.cfg
View File

@ -52,7 +52,7 @@ install_requires =
catalogue>=2.0.6,<2.1.0
# Third-party dependencies
typer>=0.3.0,<0.8.0
pathy>=0.3.5
pathy>=0.10.0
smart-open>=5.2.1,<7.0.0
tqdm>=4.38.0,<5.0.0
numpy>=1.15.0

2
spacy/about.py
View File

@ -1,6 +1,6 @@
# fmt: off
__title__ = "spacy"
__version__ = "3.4.2"
__version__ = "3.5.0"
__download_url__ = "https://github.com/explosion/spacy-models/releases/download"
__compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
__projects__ = "https://github.com/explosion/projects"

23
spacy/cli/_util.py
View File

@ -23,7 +23,7 @@ from ..util import is_compatible_version, SimpleFrozenDict, ENV_VARS
from .. import about
if TYPE_CHECKING:
from pathy import Pathy # noqa: F401
from pathy import FluidPath # noqa: F401
SDIST_SUFFIX = ".tar.gz"
@ -158,15 +158,15 @@ def load_project_config(
sys.exit(1)
validate_project_version(config)
validate_project_commands(config)
if interpolate:
err = f"{PROJECT_FILE} validation error"
with show_validation_error(title=err, hint_fill=False):
config = substitute_project_variables(config, overrides)
# Make sure directories defined in config exist
for subdir in config.get("directories", []):
dir_path = path / subdir
if not dir_path.exists():
dir_path.mkdir(parents=True)
if interpolate:
err = f"{PROJECT_FILE} validation error"
with show_validation_error(title=err, hint_fill=False):
config = substitute_project_variables(config, overrides)
return config
@ -331,7 +331,7 @@ def import_code(code_path: Optional[Union[Path, str]]) -> None:
msg.fail(f"Couldn't load Python code: {code_path}", e, exits=1)
def upload_file(src: Path, dest: Union[str, "Pathy"]) -> None:
def upload_file(src: Path, dest: Union[str, "FluidPath"]) -> None:
"""Upload a file.
src (Path): The source path.
@ -339,13 +339,20 @@ def upload_file(src: Path, dest: Union[str, "Pathy"]) -> None:
"""
import smart_open
# Create parent directories for local paths
if isinstance(dest, Path):
if not dest.parent.exists():
dest.parent.mkdir(parents=True)
dest = str(dest)
with smart_open.open(dest, mode="wb") as output_file:
with src.open(mode="rb") as input_file:
output_file.write(input_file.read())
def download_file(src: Union[str, "Pathy"], dest: Path, *, force: bool = False) -> None:
def download_file(
src: Union[str, "FluidPath"], dest: Path, *, force: bool = False
) -> None:
"""Download a file using smart_open.
url (str): The URL of the file.
@ -368,7 +375,7 @@ def ensure_pathy(path):
slow and annoying Google Cloud warning)."""
from pathy import Pathy # noqa: F811
return Pathy(path)
return Pathy.fluid(path)
def git_checkout(

2
spacy/cli/debug_data.py
View File

@ -13,6 +13,7 @@ from ._util import import_code, debug_cli, _format_number
from ..training import Example, remove_bilu_prefix
from ..training.initialize import get_sourced_components
from ..schemas import ConfigSchemaTraining
from ..pipeline import TrainablePipe
from ..pipeline._parser_internals import nonproj
from ..pipeline._parser_internals.nonproj import DELIMITER
from ..pipeline import Morphologizer, SpanCategorizer
@ -934,6 +935,7 @@ def _get_labels_from_model(nlp: Language, factory_name: str) -> Set[str]:
labels: Set[str] = set()
for pipe_name in pipe_names:
pipe = nlp.get_pipe(pipe_name)
assert isinstance(pipe, TrainablePipe)
labels.update(pipe.labels)
return labels

42
spacy/cli/project/remote_storage.py
View File

@ -5,15 +5,17 @@ import hashlib
import urllib.parse
import tarfile
from pathlib import Path
from wasabi import msg
from .._util import get_hash, get_checksum, download_file, ensure_pathy
from ...util import make_tempdir, get_minor_version, ENV_VARS, check_bool_env_var
from .._util import get_hash, get_checksum, upload_file, download_file
from .._util import ensure_pathy, make_tempdir
from ...util import get_minor_version, ENV_VARS, check_bool_env_var
from ...git_info import GIT_VERSION
from ... import about
from ...errors import Errors
if TYPE_CHECKING:
from pathy import Pathy # noqa: F401
from pathy import FluidPath # noqa: F401
class RemoteStorage:
@ -28,7 +30,7 @@ class RemoteStorage:
self.url = ensure_pathy(url)
self.compression = compression
def push(self, path: Path, command_hash: str, content_hash: str) -> "Pathy":
def push(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
"""Compress a file or directory within a project and upload it to a remote
storage. If an object exists at the full URL, nothing is done.
@ -49,9 +51,7 @@ class RemoteStorage:
mode_string = f"w:{self.compression}" if self.compression else "w"
with tarfile.open(tar_loc, mode=mode_string) as tar_file:
tar_file.add(str(loc), arcname=str(path))
with tar_loc.open(mode="rb") as input_file:
with url.open(mode="wb") as output_file:
output_file.write(input_file.read())
upload_file(tar_loc, url)
return url
def pull(
@ -60,7 +60,7 @@ class RemoteStorage:
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["Pathy"]:
) -> Optional["FluidPath"]:
"""Retrieve a file from the remote cache. If the file already exists,
nothing is done.
@ -110,25 +110,37 @@ class RemoteStorage:
*,
command_hash: Optional[str] = None,
content_hash: Optional[str] = None,
) -> Optional["Pathy"]:
) -> Optional["FluidPath"]:
"""Find the best matching version of a file within the storage,
or `None` if no match can be found. If both the creation and content hash
are specified, only exact matches will be returned. Otherwise, the most
recent matching file is preferred.
"""
name = self.encode_name(str(path))
urls = []
if command_hash is not None and content_hash is not None:
url = self.make_url(path, command_hash, content_hash)
url = self.url / name / command_hash / content_hash
urls = [url] if url.exists() else []
elif command_hash is not None:
urls = list((self.url / name / command_hash).iterdir())
if (self.url / name / command_hash).exists():
urls = list((self.url / name / command_hash).iterdir())
else:
urls = list((self.url / name).iterdir())
if content_hash is not None:
urls = [url for url in urls if url.parts[-1] == content_hash]
if (self.url / name).exists():
for sub_dir in (self.url / name).iterdir():
urls.extend(sub_dir.iterdir())
if content_hash is not None:
urls = [url for url in urls if url.parts[-1] == content_hash]
if len(urls) >= 2:
try:
urls.sort(key=lambda x: x.stat().last_modified) # type: ignore
except Exception:
msg.warn(
"Unable to sort remote files by last modified. The file(s) "
"pulled from the cache may not be the most recent."
)
return urls[-1] if urls else None
def make_url(self, path: Path, command_hash: str, content_hash: str) -> "Pathy":
def make_url(self, path: Path, command_hash: str, content_hash: str) -> "FluidPath":
"""Construct a URL from a subpath, a creation hash and a content hash."""
return self.url / self.encode_name(str(path)) / command_hash / content_hash

4
spacy/cli/project/run.py
View File

@ -101,8 +101,8 @@ def project_run(
if not (project_dir / dep).exists():
err = f"Missing dependency specified by command '{subcommand}': {dep}"
err_help = "Maybe you forgot to run the 'project assets' command or a previous step?"
err_kwargs = {"exits": 1} if not dry else {}
msg.fail(err, err_help, **err_kwargs)
err_exits = 1 if not dry else None
msg.fail(err, err_help, exits=err_exits)
check_spacy_commit = check_bool_env_var(ENV_VARS.PROJECT_USE_GIT_VERSION)
with working_dir(project_dir) as current_dir:
msg.divider(subcommand)

2
spacy/cli/templates/quickstart_training.jinja
View File

@ -1,7 +1,7 @@
{# This is a template for training configs used for the quickstart widget in
the docs and the init config command. It encodes various best practices and
can help generate the best possible configuration, given a user's requirements. #}
{%- set use_transformer = hardware != "cpu" -%}
{%- set use_transformer = hardware != "cpu" and transformer_data -%}
{%- set transformer = transformer_data[optimize] if use_transformer else {} -%}
{%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "spancat", "trainable_lemmatizer"] -%}
[paths]

5
spacy/errors.py
View File

@ -345,6 +345,11 @@ class Errors(metaclass=ErrorsWithCodes):
"clear the existing vectors and resize the table.")
E074 = ("Error interpreting compiled match pattern: patterns are expected "
"to end with the attribute {attr}. Got: {bad_attr}.")
E079 = ("Error computing states in beam: number of predicted beams "
"({pbeams}) does not equal number of gold beams ({gbeams}).")
E080 = ("Duplicate state found in beam: {key}.")
E081 = ("Error getting gradient in beam: number of histories ({n_hist}) "
"does not equal number of losses ({losses}).")
E082 = ("Error deprojectivizing parse: number of heads ({n_heads}), "
"projective heads ({n_proj_heads}) and labels ({n_labels}) do not "
"match.")

55
spacy/language.py
View File

@ -43,8 +43,7 @@ from .lookups import load_lookups
from .compat import Literal
if TYPE_CHECKING:
from .pipeline import Pipe # noqa: F401
PipeCallable = Callable[[Doc], Doc]
# This is the base config will all settings (training etc.)
@ -181,7 +180,7 @@ class Language:
self.vocab: Vocab = vocab
if self.lang is None:
self.lang = self.vocab.lang
self._components: List[Tuple[str, "Pipe"]] = []
self._components: List[Tuple[str, PipeCallable]] = []
self._disabled: Set[str] = set()
self.max_length = max_length
# Create the default tokenizer from the default config
@ -303,7 +302,7 @@ class Language:
return SimpleFrozenList(names)
@property
def components(self) -> List[Tuple[str, "Pipe"]]:
def components(self) -> List[Tuple[str, PipeCallable]]:
"""Get all (name, component) tuples in the pipeline, including the
currently disabled components.
"""
@ -322,12 +321,12 @@ class Language:
return SimpleFrozenList(names, error=Errors.E926.format(attr="component_names"))
@property
def pipeline(self) -> List[Tuple[str, "Pipe"]]:
def pipeline(self) -> List[Tuple[str, PipeCallable]]:
"""The processing pipeline consisting of (name, component) tuples. The
components are called on the Doc in order as it passes through the
pipeline.
RETURNS (List[Tuple[str, Pipe]]): The pipeline.
RETURNS (List[Tuple[str, Callable[[Doc], Doc]]]): The pipeline.
"""
pipes = [(n, p) for n, p in self._components if n not in self._disabled]
return SimpleFrozenList(pipes, error=Errors.E926.format(attr="pipeline"))
@ -527,7 +526,7 @@ class Language:
assigns: Iterable[str] = SimpleFrozenList(),
requires: Iterable[str] = SimpleFrozenList(),
retokenizes: bool = False,
func: Optional["Pipe"] = None,
func: Optional[PipeCallable] = None,
) -> Callable[..., Any]:
"""Register a new pipeline component. Can be used for stateless function
components that don't require a separate factory. Can be used as a
@ -542,7 +541,7 @@ class Language:
e.g. "token.ent_id". Used for pipeline analysis.
retokenizes (bool): Whether the component changes the tokenization.
Used for pipeline analysis.
func (Optional[Callable]): Factory function if not used as a decorator.
func (Optional[Callable[[Doc], Doc]): Factory function if not used as a decorator.
DOCS: https://spacy.io/api/language#component
"""
@ -553,11 +552,11 @@ class Language:
raise ValueError(Errors.E853.format(name=name))
component_name = name if name is not None else util.get_object_name(func)
def add_component(component_func: "Pipe") -> Callable:
def add_component(component_func: PipeCallable) -> Callable:
if isinstance(func, type): # function is a class
raise ValueError(Errors.E965.format(name=component_name))
def factory_func(nlp, name: str) -> "Pipe":
def factory_func(nlp, name: str) -> PipeCallable:
return component_func
internal_name = cls.get_factory_name(name)
@ -607,7 +606,7 @@ class Language:
print_pipe_analysis(analysis, keys=keys)
return analysis
def get_pipe(self, name: str) -> "Pipe":
def get_pipe(self, name: str) -> PipeCallable:
"""Get a pipeline component for a given component name.
name (str): Name of pipeline component to get.
@ -628,7 +627,7 @@ class Language:
config: Dict[str, Any] = SimpleFrozenDict(),
raw_config: Optional[Config] = None,
validate: bool = True,
) -> "Pipe":
) -> PipeCallable:
"""Create a pipeline component. Mostly used internally. To create and
add a component to the pipeline, you can use nlp.add_pipe.
@ -640,7 +639,7 @@ class Language:
raw_config (Optional[Config]): Internals: the non-interpolated config.
validate (bool): Whether to validate the component config against the
arguments and types expected by the factory.
RETURNS (Pipe): The pipeline component.
RETURNS (Callable[[Doc], Doc]): The pipeline component.
DOCS: https://spacy.io/api/language#create_pipe
"""
@ -695,13 +694,13 @@ class Language:
def create_pipe_from_source(
self, source_name: str, source: "Language", *, name: str
) -> Tuple["Pipe", str]:
) -> Tuple[PipeCallable, str]:
"""Create a pipeline component by copying it from an existing model.
source_name (str): Name of the component in the source pipeline.
source (Language): The source nlp object to copy from.
name (str): Optional alternative name to use in current pipeline.
RETURNS (Tuple[Callable, str]): The component and its factory name.
RETURNS (Tuple[Callable[[Doc], Doc], str]): The component and its factory name.
"""
# Check source type
if not isinstance(source, Language):
@ -740,7 +739,7 @@ class Language:
config: Dict[str, Any] = SimpleFrozenDict(),
raw_config: Optional[Config] = None,
validate: bool = True,
) -> "Pipe":
) -> PipeCallable:
"""Add a component to the processing pipeline. Valid components are
callables that take a `Doc` object, modify it and return it. Only one
of before/after/first/last can be set. Default behaviour is "last".
@ -763,7 +762,7 @@ class Language:
raw_config (Optional[Config]): Internals: the non-interpolated config.
validate (bool): Whether to validate the component config against the
arguments and types expected by the factory.
RETURNS (Pipe): The pipeline component.
RETURNS (Callable[[Doc], Doc]): The pipeline component.
DOCS: https://spacy.io/api/language#add_pipe
"""
@ -869,7 +868,7 @@ class Language:
*,
config: Dict[str, Any] = SimpleFrozenDict(),
validate: bool = True,
) -> "Pipe":
) -> PipeCallable:
"""Replace a component in the pipeline.
name (str): Name of the component to replace.
@ -878,7 +877,7 @@ class Language:
component. Will be merged with default config, if available.
validate (bool): Whether to validate the component config against the
arguments and types expected by the factory.
RETURNS (Pipe): The new pipeline component.
RETURNS (Callable[[Doc], Doc]): The new pipeline component.
DOCS: https://spacy.io/api/language#replace_pipe
"""
@ -930,11 +929,11 @@ class Language:
init_cfg = self._config["initialize"]["components"].pop(old_name)
self._config["initialize"]["components"][new_name] = init_cfg
def remove_pipe(self, name: str) -> Tuple[str, "Pipe"]:
def remove_pipe(self, name: str) -> Tuple[str, PipeCallable]:
"""Remove a component from the pipeline.
name (str): Name of the component to remove.
RETURNS (tuple): A `(name, component)` tuple of the removed component.
RETURNS (Tuple[str, Callable[[Doc], Doc]]): A `(name, component)` tuple of the removed component.
DOCS: https://spacy.io/api/language#remove_pipe
"""
@ -1349,15 +1348,15 @@ class Language:
def set_error_handler(
self,
error_handler: Callable[[str, "Pipe", List[Doc], Exception], NoReturn],
error_handler: Callable[[str, PipeCallable, List[Doc], Exception], NoReturn],
):
"""Set an error handler object for all the components in the pipeline that implement
a set_error_handler function.
"""Set an error handler object for all the components in the pipeline
that implement a set_error_handler function.
error_handler (Callable[[str, Pipe, List[Doc], Exception], NoReturn]):
Function that deals with a failing batch of documents. This callable function should take in
the component's name, the component itself, the offending batch of documents, and the exception
that was thrown.
error_handler (Callable[[str, Callable[[Doc], Doc], List[Doc], Exception], NoReturn]):
Function that deals with a failing batch of documents. This callable
function should take in the component's name, the component itself,
the offending batch of documents, and the exception that was thrown.
DOCS: https://spacy.io/api/language#set_error_handler
"""
self.default_error_handler = error_handler

4
spacy/pipeline/edit_tree_lemmatizer.py
View File

@ -328,9 +328,9 @@ class EditTreeLemmatizer(TrainablePipe):
tree = dict(tree)
if "orig" in tree:
tree["orig"] = self.vocab.strings[tree["orig"]]
tree["orig"] = self.vocab.strings.add(tree["orig"])
if "orig" in tree:
tree["subst"] = self.vocab.strings[tree["subst"]]
tree["subst"] = self.vocab.strings.add(tree["subst"])
trees.append(tree)

5
spacy/pipeline/spancat.py
View File

@ -272,7 +272,10 @@ class SpanCategorizer(TrainablePipe):
DOCS: https://spacy.io/api/spancategorizer#predict
"""
indices = self.suggester(docs, ops=self.model.ops)
scores = self.model.predict((docs, indices)) # type: ignore
if indices.lengths.sum() == 0:
scores = self.model.ops.alloc2f(0, 0)
else:
scores = self.model.predict((docs, indices)) # type: ignore
return indices, scores
def set_candidates(

1
spacy/pipeline/textcat.py
View File

@ -87,7 +87,6 @@ subword_features = true
"cats_macro_f": None,
"cats_macro_auc": None,
"cats_f_per_type": None,
"cats_macro_auc_per_type": None,
},
)
def make_textcat(

1
spacy/pipeline/textcat_multilabel.py
View File

@ -87,7 +87,6 @@ subword_features = true
"cats_macro_f": None,
"cats_macro_auc": None,
"cats_f_per_type": None,
"cats_macro_auc_per_type": None,
},
)
def make_multilabel_textcat(

37
spacy/tests/pipeline/test_edit_tree_lemmatizer.py
View File

@ -60,10 +60,45 @@ def test_initialize_from_labels():
nlp2 = Language()
lemmatizer2 = nlp2.add_pipe("trainable_lemmatizer")
lemmatizer2.initialize(
get_examples=lambda: train_examples,
# We want to check that the strings in replacement nodes are
# added to the string store. Avoid that they get added through
# the examples.
get_examples=lambda: train_examples[:1],
labels=lemmatizer.label_data,
)
assert lemmatizer2.tree2label == {1: 0, 3: 1, 4: 2, 6: 3}
assert lemmatizer2.label_data == {
"trees": [
{"orig": "S", "subst": "s"},
{
"prefix_len": 1,
"suffix_len": 0,
"prefix_tree": 0,
"suffix_tree": 4294967295,
},
{"orig": "s", "subst": ""},
{
"prefix_len": 0,
"suffix_len": 1,
"prefix_tree": 4294967295,
"suffix_tree": 2,
},
{
"prefix_len": 0,
"suffix_len": 0,
"prefix_tree": 4294967295,
"suffix_tree": 4294967295,
},
{"orig": "E", "subst": "e"},
{
"prefix_len": 1,
"suffix_len": 0,
"prefix_tree": 5,
"suffix_tree": 4294967295,
},
],
"labels": (1, 3, 4, 6),
}
def test_no_data():

43
spacy/tests/pipeline/test_spancat.py
View File

@ -372,24 +372,39 @@ def test_overfitting_IO_overlapping():
def test_zero_suggestions():
# Test with a suggester that returns 0 suggestions
# Test with a suggester that can return 0 suggestions
@registry.misc("test_zero_suggester")
def make_zero_suggester():
def zero_suggester(docs, *, ops=None):
@registry.misc("test_mixed_zero_suggester")
def make_mixed_zero_suggester():
def mixed_zero_suggester(docs, *, ops=None):
if ops is None:
ops = get_current_ops()
return Ragged(
ops.xp.zeros((0, 0), dtype="i"), ops.xp.zeros((len(docs),), dtype="i")
)
spans = []
lengths = []
for doc in docs:
if len(doc) > 0 and len(doc) % 2 == 0:
spans.append((0, 1))
lengths.append(1)
else:
lengths.append(0)
spans = ops.asarray2i(spans)
lengths_array = ops.asarray1i(lengths)
if len(spans) > 0:
output = Ragged(ops.xp.vstack(spans), lengths_array)
else:
output = Ragged(ops.xp.zeros((0, 0), dtype="i"), lengths_array)
return output
return zero_suggester
return mixed_zero_suggester
fix_random_seed(0)
nlp = English()
spancat = nlp.add_pipe(
"spancat",
config={"suggester": {"@misc": "test_zero_suggester"}, "spans_key": SPAN_KEY},
config={
"suggester": {"@misc": "test_mixed_zero_suggester"},
"spans_key": SPAN_KEY,
},
)
train_examples = make_examples(nlp)
optimizer = nlp.initialize(get_examples=lambda: train_examples)
@ -397,6 +412,16 @@ def test_zero_suggestions():
assert set(spancat.labels) == {"LOC", "PERSON"}
nlp.update(train_examples, sgd=optimizer)
# empty doc
nlp("")
# single doc with zero suggestions
nlp("one")
# single doc with one suggestion
nlp("two two")
# batch with mixed zero/one suggestions
list(nlp.pipe(["one", "two two", "three three three", "", "four four four four"]))
# batch with no suggestions
list(nlp.pipe(["", "one", "three three three"]))
def test_set_candidates():

2
spacy/tests/pipeline/test_textcat.py
View File

@ -838,8 +838,8 @@ def test_textcat_loss(multi_label: bool, expected_loss: float):
textcat = nlp.add_pipe("textcat_multilabel")
else:
textcat = nlp.add_pipe("textcat")
textcat.initialize(lambda: train_examples)
assert isinstance(textcat, TextCategorizer)
textcat.initialize(lambda: train_examples)
scores = textcat.model.ops.asarray(
[[0.0, 0.0, 0.0, 1.0], [0.0, 0.0, 1.0, 1.0]], dtype="f" # type: ignore
)

77
spacy/tests/test_cli.py
View File

@ -3,6 +3,7 @@ import math
from collections import Counter
from typing import Tuple, List, Dict, Any
import pkg_resources
import time
import numpy
import pytest
@ -28,6 +29,7 @@ from spacy.cli.download import get_compatibility, get_version
from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config
from spacy.cli.package import get_third_party_dependencies
from spacy.cli.package import _is_permitted_package_name
from spacy.cli.project.remote_storage import RemoteStorage
from spacy.cli.project.run import _check_requirements
from spacy.cli.validate import get_model_pkgs
from spacy.cli.find_threshold import find_threshold
@ -121,6 +123,25 @@ def test_issue7055():
assert "model" in filled_cfg["components"]["ner"]
@pytest.mark.issue(11235)
def test_issue11235():
"""
Test that the cli handles interpolation in the directory names correctly when loading project config.
"""
lang_var = "en"
variables = {"lang": lang_var}
commands = [{"name": "x", "script": ["hello ${vars.lang}"]}]
directories = ["cfg", "${vars.lang}_model"]
project = {"commands": commands, "vars": variables, "directories": directories}
with make_tempdir() as d:
srsly.write_yaml(d / "project.yml", project)
cfg = load_project_config(d)
# Check that the directories are interpolated and created correctly
assert os.path.exists(d / "cfg")
assert os.path.exists(d / f"{lang_var}_model")
assert cfg["commands"][0]["script"][0] == f"hello {lang_var}"
def test_cli_info():
nlp = Dutch()
nlp.add_pipe("textcat")
@ -594,6 +615,7 @@ def test_string_to_list_intify(value):
assert string_to_list(value, intify=True) == [1, 2, 3]
@pytest.mark.skip(reason="Temporarily skip for dev version")
def test_download_compatibility():
spec = SpecifierSet("==" + about.__version__)
spec.prereleases = False
@ -604,6 +626,7 @@ def test_download_compatibility():
assert get_minor_version(about.__version__) == get_minor_version(version)
@pytest.mark.skip(reason="Temporarily skip for dev version")
def test_validate_compatibility_table():
spec = SpecifierSet("==" + about.__version__)
spec.prereleases = False
@ -862,6 +885,60 @@ def test_span_length_freq_dist_output_must_be_correct():
assert list(span_freqs.keys()) == [3, 1, 4, 5, 2]
def test_local_remote_storage():
with make_tempdir() as d:
filename = "a.txt"
content_hashes = ("aaaa", "cccc", "bbbb")
for i, content_hash in enumerate(content_hashes):
# make sure that each subsequent file has a later timestamp
if i > 0:
time.sleep(1)
content = f"{content_hash} content"
loc_file = d / "root" / filename
if not loc_file.parent.exists():
loc_file.parent.mkdir(parents=True)
with loc_file.open(mode="w") as file_:
file_.write(content)
# push first version to remote storage
remote = RemoteStorage(d / "root", str(d / "remote"))
remote.push(filename, "aaaa", content_hash)
# retrieve with full hashes
loc_file.unlink()
remote.pull(filename, command_hash="aaaa", content_hash=content_hash)
with loc_file.open(mode="r") as file_:
assert file_.read() == content
# retrieve with command hash
loc_file.unlink()
remote.pull(filename, command_hash="aaaa")
with loc_file.open(mode="r") as file_:
assert file_.read() == content
# retrieve with content hash
loc_file.unlink()
remote.pull(filename, content_hash=content_hash)
with loc_file.open(mode="r") as file_:
assert file_.read() == content
# retrieve with no hashes
loc_file.unlink()
remote.pull(filename)
with loc_file.open(mode="r") as file_:
assert file_.read() == content
def test_local_remote_storage_pull_missing():
# pulling from a non-existent remote pulls nothing gracefully
with make_tempdir() as d:
filename = "a.txt"
remote = RemoteStorage(d / "root", str(d / "remote"))
assert remote.pull(filename, command_hash="aaaa") is None
assert remote.pull(filename) is None
def test_cli_find_threshold(capsys):
thresholds = numpy.linspace(0, 1, 10)

9
spacy/util.py
View File

@ -51,8 +51,7 @@ from . import about
if TYPE_CHECKING:
# This lets us add type hints for mypy etc. without causing circular imports
from .language import Language # noqa: F401
from .pipeline import Pipe # noqa: F401
from .language import Language, PipeCallable # noqa: F401
from .tokens import Doc, Span # noqa: F401
from .vocab import Vocab # noqa: F401
@ -1642,9 +1641,11 @@ def check_bool_env_var(env_var: str) -> bool:
def _pipe(
docs: Iterable["Doc"],
proc: "Pipe",
proc: "PipeCallable",
name: str,
default_error_handler: Callable[[str, "Pipe", List["Doc"], Exception], NoReturn],
default_error_handler: Callable[
[str, "PipeCallable", List["Doc"], Exception], NoReturn
],
kwargs: Mapping[str, Any],
) -> Iterator["Doc"]:
if hasattr(proc, "pipe"):

658
website/README.md
View File

@ -1,531 +1,11 @@
<Comment>
# spacy.io website and docs
![Netlify Status](https://api.netlify.com/api/v1/badges/d65fe97d-99ab-47f8-a339-1d8987251da0/deploy-status)
_This page contains the documentation and styleguide for the spaCy website. Its
rendered version is available at https://spacy.io/styleguide._
The styleguide for the spaCy website is available at
[spacy.io/styleguide](https://spacy.io/styleguide).
---
</Comment>
The [spacy.io](https://spacy.io) website is implemented using
[Gatsby](https://www.gatsbyjs.org) with
[Remark](https://github.com/remarkjs/remark) and [MDX](https://mdxjs.com/). This
allows authoring content in **straightforward Markdown** without the usual
limitations. Standard elements can be overwritten with powerful
[React](http://reactjs.org/) components and wherever Markdown syntax isn't
enough, JSX components can be used.
> #### Contributing to the site
>
> The docs can always use another example or more detail, and they should always
> be up to date and not misleading. We always appreciate a
> [pull request](https://github.com/explosion/spaCy/pulls). To quickly find the
> correct file to edit, simply click on the "Suggest edits" button at the bottom
> of a page.
>
> For more details on editing the site locally, see the installation
> instructions and markdown reference below.
## Logo {#logo source="website/src/images/logo.svg"}
import { Logos } from 'widgets/styleguide'
If you would like to use the spaCy logo on your site, please get in touch and
ask us first. However, if you want to show support and tell others that your
project is using spaCy, you can grab one of our
[spaCy badges](/usage/spacy-101#faq-project-with-spacy).
<Logos />
## Colors {#colors}
import { Colors, Patterns } from 'widgets/styleguide'
<Colors />
### Patterns
<Patterns />
## Typography {#typography}
import { H1, H2, H3, H4, H5, Label, InlineList, Comment } from
'components/typography'
> #### Markdown
>
> ```markdown_
> ## Headline 2
> ## Headline 2 {#some_id}
> ## Headline 2 {#some_id tag="method"}
> ```
>
> #### JSX
>
> ```jsx
> <H2>Headline 2</H2>
> <H2 id="some_id">Headline 2</H2>
> <H2 id="some_id" tag="method">Headline 2</H2>
> ```
Headlines are set in
[HK Grotesk](http://cargocollective.com/hanken/HK-Grotesk-Open-Source-Font) by
Hanken Design. All other body text and code uses the best-matching default
system font to provide a "native" reading experience. All code uses the
[JetBrains Mono](https://www.jetbrains.com/lp/mono/) typeface by JetBrains.
<Infobox title="Important note" variant="warning">
Level 2 headings are automatically wrapped in `<section>` elements at compile
time, using a custom
[Markdown transformer](https://github.com/explosion/spaCy/tree/master/website/plugins/remark-wrap-section.js).
This makes it easier to highlight the section that's currently in the viewpoint
in the sidebar menu.
</Infobox>
<div>
<H1>Headline 1</H1>
<H2>Headline 2</H2>
<H3>Headline 3</H3>
<H4>Headline 4</H4>
<H5>Headline 5</H5>
<Label>Label</Label>
</div>
---
The following optional attributes can be set on the headline to modify it. For
example, to add a tag for the documented type or mark features that have been
introduced in a specific version or require statistical models to be loaded.
Tags are also available as standalone `<Tag />` components.
| Argument | Example | Result |
| -------- | -------------------------- | ----------------------------------------- |
| `tag` | `{tag="method"}` | <Tag>method</Tag> |
| `new` | `{new="3"}` | <Tag variant="new">3</Tag> |
| `model` | `{model="tagger, parser"}` | <Tag variant="model">tagger, parser</Tag> |
| `hidden` | `{hidden="true"}` | |
## Elements {#elements}
### Links {#links}
> #### Markdown
>
> ```markdown
> [I am a link](https://spacy.io)
> ```
>
> #### JSX
>
> ```jsx
> <Link to="https://spacy.io">I am a link</Link>
> ```
Special link styles are used depending on the link URL.
- [I am a regular external link](https://explosion.ai)
- [I am a link to the documentation](/api/doc)
- [I am a link to an architecture](/api/architectures#HashEmbedCNN)
- [I am a link to a model](/models/en#en_core_web_sm)
- [I am a link to GitHub](https://github.com/explosion/spaCy)
### Abbreviations {#abbr}
import { Abbr } from 'components/typography'
> #### JSX
>
> ```jsx
> <Abbr title="Explanation">Abbreviation</Abbr>
> ```
Some text with <Abbr title="Explanation here">an abbreviation</Abbr>. On small
screens, I collapse and the explanation text is displayed next to the
abbreviation.
### Tags {#tags}
import Tag from 'components/tag'
> ```jsx
> <Tag>method</Tag>
> <Tag variant="new">4</Tag>
> <Tag variant="model">tagger, parser</Tag>
> ```
Tags can be used together with headlines, or next to properties across the
documentation, and combined with tooltips to provide additional information. An
optional `variant` argument can be used for special tags. `variant="new"` makes
the tag take a version number to mark new features. Using the component,
visibility of this tag can later be toggled once the feature isn't considered
new anymore. Setting `variant="model"` takes a description of model capabilities
and can be used to mark features that require a respective model to be
installed.
<InlineList>
<Tag>method</Tag> <Tag variant="new">4</Tag> <Tag variant="model">tagger,
parser</Tag>
</InlineList>
### Buttons {#buttons}
import Button from 'components/button'
> ```jsx
> <Button to="#" variant="primary">Primary small</Button>
> <Button to="#" variant="secondary">Secondary small</Button>
> ```
Link buttons come in two variants, `primary` and `secondary` and two sizes, with
an optional `large` size modifier. Since they're mostly used as enhanced links,
the buttons are implemented as styled links instead of native button elements.
<InlineList><Button to="#" variant="primary">Primary small</Button>
<Button to="#" variant="secondary">Secondary small</Button></InlineList>
<br />
<InlineList><Button to="#" variant="primary" large>Primary large</Button>
<Button to="#" variant="secondary" large>Secondary large</Button></InlineList>
## Components
### Table {#table}
> #### Markdown
>
> ```markdown_
> | Header 1 | Header 2 |
> | -------- | -------- |
> | Column 1 | Column 2 |
> ```
>
> #### JSX
>
> ```markup
> <Table>
> <Tr><Th>Header 1</Th><Th>Header 2</Th></Tr></thead>
> <Tr><Td>Column 1</Td><Td>Column 2</Td></Tr>
> </Table>
> ```
Tables are used to present data and API documentation. Certain keywords can be
used to mark a footer row with a distinct style, for example to visualize the
return values of a documented function.
| Header 1 | Header 2 | Header 3 | Header 4 |
| ----------- | -------- | :------: | -------: |
| Column 1 | Column 2 | Column 3 | Column 4 |
| Column 1 | Column 2 | Column 3 | Column 4 |
| Column 1 | Column 2 | Column 3 | Column 4 |
| Column 1 | Column 2 | Column 3 | Column 4 |
| **RETURNS** | Column 2 | Column 3 | Column 4 |
Tables also support optional "divider" rows that are typically used to denote
keyword-only arguments in API documentation. To turn a row into a dividing
headline, it should only include content in its first cell, and its value should
be italicized:
> #### Markdown
>
> ```markdown_
> | Header 1 | Header 2 | Header 3 |
> | -------- | -------- | -------- |
> | Column 1 | Column 2 | Column 3 |
> | _Hello_ | | |
> | Column 1 | Column 2 | Column 3 |
> ```
| Header 1 | Header 2 | Header 3 |
| -------- | -------- | -------- |
| Column 1 | Column 2 | Column 3 |
| _Hello_ | | |
| Column 1 | Column 2 | Column 3 |
### Type Annotations {#type-annotations}
> #### Markdown
>
> ```markdown_
> ~~Model[List[Doc], Floats2d]~~
> ```
>
> #### JSX
>
> ```markup
> <TypeAnnotation>Model[List[Doc], Floats2d]</Typeannotation>
> ```
Type annotations are special inline code blocks are used to describe Python
types in the [type hints](https://docs.python.org/3/library/typing.html) format.
The special component will split the type, apply syntax highlighting and link
all types that specify links in `meta/type-annotations.json`. Types can link to
internal or external documentation pages. To make it easy to represent the type
annotations in Markdown, the rendering "hijacks" the `~~` tags that would
typically be converted to a `<del>` element – but in this case, text surrounded
by `~~` becomes a type annotation.
- ~~Dict[str, List[Union[Doc, Span]]]~~
- ~~Model[List[Doc], List[numpy.ndarray]]~~
Type annotations support a special visual style in tables and will render as a
separate row, under the cell text. This allows the API docs to display complex
types without taking up too much space in the cell. The type annotation should
always be the **last element** in the row.
> #### Markdown
>
> ```markdown_
> | Header 1 | Header 2 |
> | -------- | ----------------------- |
> | Column 1 | Column 2 ~~List[Doc]~~ |
> ```
| Name | Description |
| ----------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `vocab` | The shared vocabulary. ~~Vocab~~ |
| `model` | The Thinc [`Model`](https://thinc.ai/docs/api-model) wrapping the transformer. ~~Model[List[Doc], FullTransformerBatch]~~ |
| `set_extra_annotations` | Function that takes a batch of `Doc` objects and transformer outputs and can set additional annotations on the `Doc`. ~~Callable[[List[Doc], FullTransformerBatch], None]~~ |
### List {#list}
> #### Markdown
>
> ```markdown_
> 1. One
> 2. Two
> ```
>
> #### JSX
>
> ```markup
> <Ol>
> <Li>One</Li>
> <Li>Two</Li>
> </Ol>
> ```
Lists are available as bulleted and numbered. Markdown lists are transformed
automatically.
- I am a bulleted list
- I have nice bullets
- Lorem ipsum dolor
- consectetur adipiscing elit
1. I am an ordered list
2. I have nice numbers
3. Lorem ipsum dolor
4. consectetur adipiscing elit
### Aside {#aside}
> #### Markdown
>
> ```markdown_
> > #### Aside title
> > This is aside text.
> ```
>
> #### JSX
>
> ```jsx
> <Aside title="Aside title">This is aside text.</Aside>
> ```
Asides can be used to display additional notes and content in the right-hand
column. Asides can contain text, code and other elements if needed. Visually,
asides are moved to the side on the X-axis, and displayed at the same level they
were inserted. On small screens, they collapse and are rendered in their
original position, in between the text.
To make them easier to use in Markdown, paragraphs formatted as blockquotes will
turn into asides by default. Level 4 headlines (with a leading `####`) will
become aside titles.
### Code Block {#code-block}
> #### Markdown
>
> ````markdown_
> ```python
> ### This is a title
> import spacy
> ```
> ````
>
> #### JSX
>
> ```jsx
> <CodeBlock title="This is a title" lang="python">
> import spacy
> </CodeBlock>
> ```
Code blocks use the [Prism](http://prismjs.com/) syntax highlighter with a
custom theme. The language can be set individually on each block, and defaults
to raw text with no highlighting. An optional label can be added as the first
line with the prefix `####` (Python-like) and `///` (JavaScript-like). the
indented block as plain text and preserve whitespace.
```python
### Using spaCy
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")
for token in doc:
print(token.text, token.pos_)
```
Code blocks and also specify an optional range of line numbers to highlight by
adding `{highlight="..."}` to the headline. Acceptable ranges are spans like
`5-7`, but also `5-7,10` or `5-7,10,13-14`.
> #### Markdown
>
> ````markdown_
> ```python
> ### This is a title {highlight="1-2"}
> import spacy
> nlp = spacy.load("en_core_web_sm")
> ```
> ````
```python
### Using the matcher {highlight="5-7"}
import spacy
from spacy.matcher import Matcher
nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
pattern = [{"LOWER": "hello"}, {"IS_PUNCT": True}, {"LOWER": "world"}]
matcher.add("HelloWorld", None, pattern)
doc = nlp("Hello, world! Hello world!")
matches = matcher(doc)
```
Adding `{executable="true"}` to the title turns the code into an executable
block, powered by [Binder](https://mybinder.org) and
[Juniper](https://github.com/ines/juniper). If JavaScript is disabled, the
interactive widget defaults to a regular code block.
> #### Markdown
>
> ````markdown_
> ```python
> ### {executable="true"}
> import spacy
> nlp = spacy.load("en_core_web_sm")
> ```
> ````
```python
### {executable="true"}
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")
for token in doc:
print(token.text, token.pos_)
```
If a code block only contains a URL to a GitHub file, the raw file contents are
embedded automatically and syntax highlighting is applied. The link to the
original file is shown at the top of the widget.
> #### Markdown
>
> ````markdown_
> ```python
> https://github.com/...
> ```
> ````
>
> #### JSX
>
> ```jsx
> <GitHubCode url="https://github.com/..." lang="python" />
> ```
```python
https://github.com/explosion/spaCy/tree/master/spacy/language.py
```
### Infobox {#infobox}
import Infobox from 'components/infobox'
> #### JSX
>
> ```jsx
> <Infobox title="Information">Regular infobox</Infobox>
> <Infobox title="Important note" variant="warning">This is a warning.</Infobox>
> <Infobox title="Be careful!" variant="danger">This is dangerous.</Infobox>
> ```
Infoboxes can be used to add notes, updates, warnings or additional information
to a page or section. Semantically, they're implemented and interpreted as an
`aside` element. Infoboxes can take an optional `title` argument, as well as an
optional `variant` (either `"warning"` or `"danger"`).
<Infobox title="This is an infobox">
If needed, an infobox can contain regular text, `inline code`, lists and other
blocks.
</Infobox>
<Infobox title="This is a warning" variant="warning">
If needed, an infobox can contain regular text, `inline code`, lists and other
blocks.
</Infobox>
<Infobox title="This is dangerous" variant="danger">
If needed, an infobox can contain regular text, `inline code`, lists and other
blocks.
</Infobox>
### Accordion {#accordion}
import Accordion from 'components/accordion'
> #### JSX
>
> ```jsx
> <Accordion title="This is an accordion">
> Accordion content goes here.
> </Accordion>
> ```
Accordions are collapsible sections that are mostly used for lengthy tables,
like the tag and label annotation schemes for different languages. They all need
to be presented – but chances are the user doesn't actually care about _all_ of
them, especially not at the same time. So it's fairly reasonable to hide them
begin a click. This particular implementation was inspired by the amazing
[Inclusive Components blog](https://inclusive-components.design/collapsible-sections/).
<Accordion title="This is an accordion">
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Quisque enim ante,
pretium a orci eget, varius dignissim augue. Nam eu dictum mauris, id tincidunt
nisi. Integer commodo pellentesque tincidunt. Nam at turpis finibus tortor
gravida sodales tincidunt sit amet est. Nullam euismod arcu in tortor auctor,
sit amet dignissim justo congue.
</Accordion>
## Setup and installation {#setup}
## Setup and installation
Before running the setup, make sure your versions of
[Node](https://nodejs.org/en/) and [npm](https://www.npmjs.com/) are up to date.
@ -554,14 +34,14 @@ extensions for your code editor. The
[`.prettierrc`](https://github.com/explosion/spaCy/tree/master/website/.prettierrc)
file in the root defines the settings used in this codebase.
## Building & developing the site with Docker {#docker}
Sometimes it's hard to get a local environment working due to rapid updates to node dependencies,
so it may be easier to use docker for building the docs.
## Building & developing the site with Docker
If you'd like to do this,
**be sure you do *not* include your local `node_modules` folder**,
since there are some dependencies that need to be built for the image system.
Rename it before using.
Sometimes it's hard to get a local environment working due to rapid updates to
node dependencies, so it may be easier to use docker for building the docs.
If you'd like to do this, **be sure you do _not_ include your local
`node_modules` folder**, since there are some dependencies that need to be built
for the image system. Rename it before using.
```bash
docker run -it \
@ -571,16 +51,16 @@ docker run -it \
gatsby develop -H 0.0.0.0
```
This will allow you to access the built website at http://0.0.0.0:8000/
in your browser, and still edit code in your editor while having the site
reflect those changes.
This will allow you to access the built website at http://0.0.0.0:8000/ in your
browser, and still edit code in your editor while having the site reflect those
changes.
**Note**: If you're working on a Mac with an M1 processor,
you might see segfault errors from `qemu` if you use the default image.
To fix this use the `arm64` tagged image in the `docker run` command
**Note**: If you're working on a Mac with an M1 processor, you might see
segfault errors from `qemu` if you use the default image. To fix this use the
`arm64` tagged image in the `docker run` command
(ghcr.io/explosion/spacy-io:arm64).
### Building the Docker image {#docker-build}
### Building the Docker image
If you'd like to build the image locally, you can do so like this:
@ -588,67 +68,21 @@ If you'd like to build the image locally, you can do so like this:
docker build -t spacy-io .
```
This will take some time, so if you want to use the prebuilt image you'll save a bit of time.
This will take some time, so if you want to use the prebuilt image you'll save a
bit of time.
## Markdown reference {#markdown}
All page content and page meta lives in the `.md` files in the `/docs`
directory. The frontmatter block at the top of each file defines the page title
and other settings like the sidebar menu.
````markdown
---
title: Page title
---
## Headline starting a section {#some_id}
This is a regular paragraph with a [link](https://spacy.io) and **bold text**.
> #### This is an aside title
>
> This is aside text.
### Subheadline
| Header 1 | Header 2 |
| -------- | -------- |
| Column 1 | Column 2 |
```python
### Code block title {highlight="2-3"}
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("Hello world")
```
<Infobox title="Important note" variant="warning">
This is content in the infobox.
</Infobox>
````
In addition to the native markdown elements, you can use the components
[`<Infobox />`][infobox], [`<Accordion />`][accordion], [`<Abbr />`][abbr] and
[`<Tag />`][tag] via their JSX syntax.
[infobox]: https://spacy.io/styleguide#infobox
[accordion]: https://spacy.io/styleguide#accordion
[abbr]: https://spacy.io/styleguide#abbr
[tag]: https://spacy.io/styleguide#tag
## Project structure {#structure}
## Project structure
```yaml
### Directory structure
├── docs # the actual markdown content
├── meta # JSON-formatted site metadata
| ├── languages.json # supported languages and statistical models
| ├── sidebars.json # sidebar navigations for different sections
| ├── site.json # general site metadata
| ├── type-annotations.json # Type annotations
| └── universe.json # data for the spaCy universe section
├── public # compiled site
├── setup # Jinja setup
├── src # source
| ├── components # React components
| ├── fonts # webfonts
@ -661,54 +95,10 @@ In addition to the native markdown elements, you can use the components
| | ├── models.js # layout template for model pages
| | └── universe.js # layout templates for universe
| └── widgets # non-reusable components with content, e.g. changelog
├── .eslintrc.json # ESLint config file
├── .prettierrc # Prettier config file
├── gatsby-browser.js # browser-specific hooks for Gatsby
├── gatsby-config.js # Gatsby configuration
├── gatsby-node.js # Node-specific hooks for Gatsby
└── package.json # package settings and dependencies
```
## Editorial {#editorial}
- "spaCy" should always be spelled with a lowercase "s" and a capital "C",
unless it specifically refers to the Python package or Python import `spacy`
(in which case it should be formatted as code).
- ✅ spaCy is a library for advanced NLP in Python.
- ❌ Spacy is a library for advanced NLP in Python.
- ✅ First, you need to install the `spacy` package from pip.
- Mentions of code, like function names, classes, variable names etc. in inline
text should be formatted as `code`.
- ✅ "Calling the `nlp` object on a text returns a `Doc`."
- Objects that have pages in the [API docs](/api) should be linked – for
example, [`Doc`](/api/doc) or [`Language.to_disk`](/api/language#to_disk). The
mentions should still be formatted as code within the link. Links pointing to
the API docs will automatically receive a little icon. However, if a paragraph
includes many references to the API, the links can easily get messy. In that
case, we typically only link the first mention of an object and not any
subsequent ones.
- ✅ The [`Span`](/api/span) and [`Token`](/api/token) objects are views of a
[`Doc`](/api/doc). [`Span.as_doc`](/api/span#as_doc) creates a `Doc` object
from a `Span`.
- ❌ The [`Span`](/api/span) and [`Token`](/api/token) objects are views of a
[`Doc`](/api/doc). [`Span.as_doc`](/api/span#as_doc) creates a
[`Doc`](/api/doc) object from a [`Span`](/api/span).
* Other things we format as code are: references to trained pipeline packages
like `en_core_web_sm` or file names like `code.py` or `meta.json`.
- ✅ After training, the `config.cfg` is saved to disk.
* [Type annotations](#type-annotations) are a special type of code formatting,
expressed by wrapping the text in `~~` instead of backticks. The result looks
like this: ~~List[Doc]~~. All references to known types will be linked
automatically.
- ✅ The model has the input type ~~List[Doc]~~ and it outputs a
~~List[Array2d]~~.
* We try to keep links meaningful but short.
- ✅ For details, see the usage guide on
[training with custom code](/usage/training#custom-code).
- ❌ For details, see
[the usage guide on training with custom code](/usage/training#custom-code).
- ❌ For details, see the usage guide on training with custom code
[here](/usage/training#custom-code).

26
website/docs/api/cli.md
View File

@ -1391,12 +1391,13 @@ If the contents are different, the new version of the file is uploaded. Deleting
obsolete files is left up to you.
Remotes can be defined in the `remotes` section of the
[`project.yml`](/usage/projects#project-yml). Under the hood, spaCy uses the
[`smart-open`](https://github.com/RaRe-Technologies/smart_open) library to
communicate with the remote storages, so you can use any protocol that
`smart-open` supports, including [S3](https://aws.amazon.com/s3/),
[Google Cloud Storage](https://cloud.google.com/storage), SSH and more, although
you may need to install extra dependencies to use certain protocols.
[`project.yml`](/usage/projects#project-yml). Under the hood, spaCy uses
[`Pathy`](https://github.com/justindujardin/pathy) to communicate with the
remote storages, so you can use any protocol that `Pathy` supports, including
[S3](https://aws.amazon.com/s3/),
[Google Cloud Storage](https://cloud.google.com/storage), and the local
filesystem, although you may need to install extra dependencies to use certain
protocols.
```cli
$ python -m spacy project push [remote] [project_dir]
@ -1435,12 +1436,13 @@ outputs, so if you change the config back, you'll be able to fetch back the
result.
Remotes can be defined in the `remotes` section of the
[`project.yml`](/usage/projects#project-yml). Under the hood, spaCy uses the
[`smart-open`](https://github.com/RaRe-Technologies/smart_open) library to
communicate with the remote storages, so you can use any protocol that
`smart-open` supports, including [S3](https://aws.amazon.com/s3/),
[Google Cloud Storage](https://cloud.google.com/storage), SSH and more, although
you may need to install extra dependencies to use certain protocols.
[`project.yml`](/usage/projects#project-yml). Under the hood, spaCy uses
[`Pathy`](https://github.com/justindujardin/pathy) to communicate with the
remote storages, so you can use any protocol that `Pathy` supports, including
[S3](https://aws.amazon.com/s3/),
[Google Cloud Storage](https://cloud.google.com/storage), and the local
filesystem, although you may need to install extra dependencies to use certain
protocols.
```cli
$ python -m spacy project pull [remote] [project_dir]

48
website/docs/api/top-level.md
View File

@ -1004,6 +1004,54 @@ This method was previously available as `spacy.gold.spans_from_biluo_tags`.
| `tags` | A sequence of [BILUO](/usage/linguistic-features#accessing-ner) tags with each tag describing one token. Each tag string will be of the form of either `""`, `"O"` or `"{action}-{label}"`, where action is one of `"B"`, `"I"`, `"L"`, `"U"`. ~~List[str]~~ |
| **RETURNS** | A sequence of `Span` objects with added entity labels. ~~List[Span]~~ |
### training.biluo_to_iob {#biluo_to_iob tag="function"}
Convert a sequence of [BILUO](/usage/linguistic-features#accessing-ner) tags to
[IOB](/usage/linguistic-features#accessing-ner) tags. This is useful if you want
use the BILUO tags with a model that only supports IOB tags.
> #### Example
>
> ```python
> from spacy.training import biluo_to_iob
>
> tags = ["O", "O", "B-LOC", "I-LOC", "L-LOC", "O"]
> iob_tags = biluo_to_iob(tags)
> assert iob_tags == ["O", "O", "B-LOC", "I-LOC", "I-LOC", "O"]
> ```
| Name | Description |
| ----------- | --------------------------------------------------------------------------------------- |
| `tags` | A sequence of [BILUO](/usage/linguistic-features#accessing-ner) tags. ~~Iterable[str]~~ |
| **RETURNS** | A list of [IOB](/usage/linguistic-features#accessing-ner) tags. ~~List[str]~~ |
### training.iob_to_biluo {#iob_to_biluo tag="function"}
Convert a sequence of [IOB](/usage/linguistic-features#accessing-ner) tags to
[BILUO](/usage/linguistic-features#accessing-ner) tags. This is useful if you
want use the IOB tags with a model that only supports BILUO tags.
<Infobox title="Changed in v3.0" variant="warning" id="iob_to_biluo">
This method was previously available as `spacy.gold.iob_to_biluo`.
</Infobox>
> #### Example
>
> ```python
> from spacy.training import iob_to_biluo
>
> tags = ["O", "O", "B-LOC", "I-LOC", "O"]
> biluo_tags = iob_to_biluo(tags)
> assert biluo_tags == ["O", "O", "B-LOC", "L-LOC", "O"]
> ```
| Name | Description |
| ----------- | ------------------------------------------------------------------------------------- |
| `tags` | A sequence of [IOB](/usage/linguistic-features#accessing-ner) tags. ~~Iterable[str]~~ |
| **RETURNS** | A list of [BILUO](/usage/linguistic-features#accessing-ner) tags. ~~List[str]~~ |
## Utility functions {#util source="spacy/util.py"}
spaCy comes with a small collection of utility functions located in

16
website/docs/api/vocab.md
View File

@ -308,14 +308,14 @@ Load state from a binary string.
> assert type(PERSON) == int
> ```
| Name | Description |
| ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `strings` | A table managing the string-to-int mapping. ~~StringStore~~ |
| `vectors` | A table associating word IDs to word vectors. ~~Vectors~~ |
| `vectors_length` | Number of dimensions for each word vector. ~~int~~ |
| `lookups` | The available lookup tables in this vocab. ~~Lookups~~ |
| `writing_system` | A dict with information about the language's writing system. ~~Dict[str, Any]~~ |
| `get_noun_chunks` <Tag variant="new">3.0</Tag> | A function that yields base noun phrases used for [`Doc.noun_chunks`](/ap/doc#noun_chunks). ~~Optional[Callable[[Union[Doc, Span], Iterator[Tuple[int, int, int]]]]]~~ |
| Name | Description |
| ---------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `strings` | A table managing the string-to-int mapping. ~~StringStore~~ |
| `vectors` | A table associating word IDs to word vectors. ~~Vectors~~ |
| `vectors_length` | Number of dimensions for each word vector. ~~int~~ |
| `lookups` | The available lookup tables in this vocab. ~~Lookups~~ |
| `writing_system` | A dict with information about the language's writing system. ~~Dict[str, Any]~~ |
| `get_noun_chunks` <Tag variant="new">3.0</Tag> | A function that yields base noun phrases used for [`Doc.noun_chunks`](/api/doc#noun_chunks). ~~Optional[Callable[[Union[Doc, Span], Iterator[Tuple[int, int, int]]]]]~~ |
## Serialization fields {#serialization-fields}

610
website/docs/styleguide.md
View File

@ -8,9 +8,7 @@ menu:
- ['Typography', 'typography']
- ['Elements', 'elements']
- ['Components', 'components']
- ['Setup & Installation', 'setup']
- ['Markdown Reference', 'markdown']
- ['Project Structure', 'structure']
- ['Editorial', 'editorial']
sidebar:
- label: Styleguide
@ -25,6 +23,610 @@ sidebar:
url: https://github.com/explosion/spaCy/blob/master/CONTRIBUTING.md
---
import Readme from 'README.md'
The [spacy.io](https://spacy.io) website is implemented using
[Gatsby](https://www.gatsbyjs.org) with
[Remark](https://github.com/remarkjs/remark) and [MDX](https://mdxjs.com/). This
allows authoring content in **straightforward Markdown** without the usual
limitations. Standard elements can be overwritten with powerful
[React](http://reactjs.org/) components and wherever Markdown syntax isn't
enough, JSX components can be used.
<Readme />
> #### Contributing to the site
>
> The docs can always use another example or more detail, and they should always
> be up to date and not misleading. We always appreciate a
> [pull request](https://github.com/explosion/spaCy/pulls). To quickly find the
> correct file to edit, simply click on the "Suggest edits" button at the bottom
> of a page.
>
> For more details on editing the site locally, see the installation
> instructions and markdown reference below.
## Logo {#logo source="website/src/images/logo.svg"}
import { Logos } from 'widgets/styleguide'
If you would like to use the spaCy logo on your site, please get in touch and
ask us first. However, if you want to show support and tell others that your
project is using spaCy, you can grab one of our
[spaCy badges](/usage/spacy-101#faq-project-with-spacy).
<Logos />
## Colors {#colors}
import { Colors, Patterns } from 'widgets/styleguide'
<Colors />
### Patterns
<Patterns />
## Typography {#typography}
import { H1, H2, H3, H4, H5, Label, InlineList, Comment } from
'components/typography'
> #### Markdown
>
> ```markdown_
> ## Headline 2
> ## Headline 2 {#some_id}
> ## Headline 2 {#some_id tag="method"}
> ```
>
> #### JSX
>
> ```jsx
> <H2>Headline 2</H2>
> <H2 id="some_id">Headline 2</H2>
> <H2 id="some_id" tag="method">Headline 2</H2>
> ```
Headlines are set in
[HK Grotesk](http://cargocollective.com/hanken/HK-Grotesk-Open-Source-Font) by
Hanken Design. All other body text and code uses the best-matching default
system font to provide a "native" reading experience. All code uses the
[JetBrains Mono](https://www.jetbrains.com/lp/mono/) typeface by JetBrains.
<Infobox title="Important note" variant="warning">
Level 2 headings are automatically wrapped in `<section>` elements at compile
time, using a custom
[Markdown transformer](https://github.com/explosion/spaCy/tree/master/website/plugins/remark-wrap-section.js).
This makes it easier to highlight the section that's currently in the viewpoint
in the sidebar menu.
</Infobox>
<div>
<H1>Headline 1</H1>
<H2>Headline 2</H2>
<H3>Headline 3</H3>
<H4>Headline 4</H4>
<H5>Headline 5</H5>
<Label>Label</Label>
</div>
---
The following optional attributes can be set on the headline to modify it. For
example, to add a tag for the documented type or mark features that have been
introduced in a specific version or require statistical models to be loaded.
Tags are also available as standalone `<Tag />` components.
| Argument | Example | Result |
| -------- | -------------------------- | ----------------------------------------- |
| `tag` | `{tag="method"}` | <Tag>method</Tag> |
| `new` | `{new="3"}` | <Tag variant="new">3</Tag> |
| `model` | `{model="tagger, parser"}` | <Tag variant="model">tagger, parser</Tag> |
| `hidden` | `{hidden="true"}` | |
## Elements {#elements}
### Links {#links}
> #### Markdown
>
> ```markdown
> [I am a link](https://spacy.io)
> ```
>
> #### JSX
>
> ```jsx
> <Link to="https://spacy.io">I am a link</Link>
> ```
Special link styles are used depending on the link URL.
- [I am a regular external link](https://explosion.ai)
- [I am a link to the documentation](/api/doc)
- [I am a link to an architecture](/api/architectures#HashEmbedCNN)
- [I am a link to a model](/models/en#en_core_web_sm)
- [I am a link to GitHub](https://github.com/explosion/spaCy)
### Abbreviations {#abbr}
import { Abbr } from 'components/typography'
> #### JSX
>
> ```jsx
> <Abbr title="Explanation">Abbreviation</Abbr>
> ```
Some text with <Abbr title="Explanation here">an abbreviation</Abbr>. On small
screens, I collapse and the explanation text is displayed next to the
abbreviation.
### Tags {#tags}
import Tag from 'components/tag'
> ```jsx
> <Tag>method</Tag>
> <Tag variant="new">4</Tag>
> <Tag variant="model">tagger, parser</Tag>
> ```
Tags can be used together with headlines, or next to properties across the
documentation, and combined with tooltips to provide additional information. An
optional `variant` argument can be used for special tags. `variant="new"` makes
the tag take a version number to mark new features. Using the component,
visibility of this tag can later be toggled once the feature isn't considered
new anymore. Setting `variant="model"` takes a description of model capabilities
and can be used to mark features that require a respective model to be
installed.
<InlineList>
<Tag>method</Tag> <Tag variant="new">4</Tag> <Tag variant="model">tagger,
parser</Tag>
</InlineList>
### Buttons {#buttons}
import Button from 'components/button'
> ```jsx
> <Button to="#" variant="primary">Primary small</Button>
> <Button to="#" variant="secondary">Secondary small</Button>
> ```
Link buttons come in two variants, `primary` and `secondary` and two sizes, with
an optional `large` size modifier. Since they're mostly used as enhanced links,
the buttons are implemented as styled links instead of native button elements.
<InlineList><Button to="#" variant="primary">Primary small</Button>
<Button to="#" variant="secondary">Secondary small</Button></InlineList>
<br />
<InlineList><Button to="#" variant="primary" large>Primary large</Button>
<Button to="#" variant="secondary" large>Secondary large</Button></InlineList>
## Components
### Table {#table}
> #### Markdown
>
> ```markdown_
> | Header 1 | Header 2 |
> | -------- | -------- |
> | Column 1 | Column 2 |
> ```
>
> #### JSX
>
> ```markup
> <Table>
> <Tr><Th>Header 1</Th><Th>Header 2</Th></Tr></thead>
> <Tr><Td>Column 1</Td><Td>Column 2</Td></Tr>
> </Table>
> ```
Tables are used to present data and API documentation. Certain keywords can be
used to mark a footer row with a distinct style, for example to visualize the
return values of a documented function.
| Header 1 | Header 2 | Header 3 | Header 4 |
| ----------- | -------- | :------: | -------: |
| Column 1 | Column 2 | Column 3 | Column 4 |
| Column 1 | Column 2 | Column 3 | Column 4 |
| Column 1 | Column 2 | Column 3 | Column 4 |
| Column 1 | Column 2 | Column 3 | Column 4 |
| **RETURNS** | Column 2 | Column 3 | Column 4 |
Tables also support optional "divider" rows that are typically used to denote
keyword-only arguments in API documentation. To turn a row into a dividing
headline, it should only include content in its first cell, and its value should
be italicized:
> #### Markdown
>
> ```markdown_
> | Header 1 | Header 2 | Header 3 |
> | -------- | -------- | -------- |
> | Column 1 | Column 2 | Column 3 |
> | _Hello_ | | |
> | Column 1 | Column 2 | Column 3 |
> ```
| Header 1 | Header 2 | Header 3 |
| -------- | -------- | -------- |
| Column 1 | Column 2 | Column 3 |
| _Hello_ | | |
| Column 1 | Column 2 | Column 3 |
### Type Annotations {#type-annotations}
> #### Markdown
>
> ```markdown_
> ~~Model[List[Doc], Floats2d]~~
> ```
>
> #### JSX
>
> ```markup
> <TypeAnnotation>Model[List[Doc], Floats2d]</Typeannotation>
> ```
Type annotations are special inline code blocks are used to describe Python
types in the [type hints](https://docs.python.org/3/library/typing.html) format.
The special component will split the type, apply syntax highlighting and link
all types that specify links in `meta/type-annotations.json`. Types can link to
internal or external documentation pages. To make it easy to represent the type
annotations in Markdown, the rendering "hijacks" the `~~` tags that would
typically be converted to a `<del>` element – but in this case, text surrounded
by `~~` becomes a type annotation.
- ~~Dict[str, List[Union[Doc, Span]]]~~
- ~~Model[List[Doc], List[numpy.ndarray]]~~
Type annotations support a special visual style in tables and will render as a
separate row, under the cell text. This allows the API docs to display complex
types without taking up too much space in the cell. The type annotation should
always be the **last element** in the row.
> #### Markdown
>
> ```markdown_
> | Header 1 | Header 2 |
> | -------- | ----------------------- |
> | Column 1 | Column 2 ~~List[Doc]~~ |
> ```
| Name | Description |
| ----------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `vocab` | The shared vocabulary. ~~Vocab~~ |
| `model` | The Thinc [`Model`](https://thinc.ai/docs/api-model) wrapping the transformer. ~~Model[List[Doc], FullTransformerBatch]~~ |
| `set_extra_annotations` | Function that takes a batch of `Doc` objects and transformer outputs and can set additional annotations on the `Doc`. ~~Callable[[List[Doc], FullTransformerBatch], None]~~ |
### List {#list}
> #### Markdown
>
> ```markdown_
> 1. One
> 2. Two
> ```
>
> #### JSX
>
> ```markup
> <Ol>
> <Li>One</Li>
> <Li>Two</Li>
> </Ol>
> ```
Lists are available as bulleted and numbered. Markdown lists are transformed
automatically.
- I am a bulleted list
- I have nice bullets
- Lorem ipsum dolor
- consectetur adipiscing elit
1. I am an ordered list
2. I have nice numbers
3. Lorem ipsum dolor
4. consectetur adipiscing elit
### Aside {#aside}
> #### Markdown
>
> ```markdown_
> > #### Aside title
> > This is aside text.
> ```
>
> #### JSX
>
> ```jsx
> <Aside title="Aside title">This is aside text.</Aside>
> ```
Asides can be used to display additional notes and content in the right-hand
column. Asides can contain text, code and other elements if needed. Visually,
asides are moved to the side on the X-axis, and displayed at the same level they
were inserted. On small screens, they collapse and are rendered in their
original position, in between the text.
To make them easier to use in Markdown, paragraphs formatted as blockquotes will
turn into asides by default. Level 4 headlines (with a leading `####`) will
become aside titles.
### Code Block {#code-block}
> #### Markdown
>
> ````markdown_
> ```python
> ### This is a title
> import spacy
> ```
> ````
>
> #### JSX
>
> ```jsx
> <CodeBlock title="This is a title" lang="python">
> import spacy
> </CodeBlock>
> ```
Code blocks use the [Prism](http://prismjs.com/) syntax highlighter with a
custom theme. The language can be set individually on each block, and defaults
to raw text with no highlighting. An optional label can be added as the first
line with the prefix `####` (Python-like) and `///` (JavaScript-like). the
indented block as plain text and preserve whitespace.
```python
### Using spaCy
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")
for token in doc:
print(token.text, token.pos_)
```
Code blocks and also specify an optional range of line numbers to highlight by
adding `{highlight="..."}` to the headline. Acceptable ranges are spans like
`5-7`, but also `5-7,10` or `5-7,10,13-14`.
> #### Markdown
>
> ````markdown_
> ```python
> ### This is a title {highlight="1-2"}
> import spacy
> nlp = spacy.load("en_core_web_sm")
> ```
> ````
```python
### Using the matcher {highlight="5-7"}
import spacy
from spacy.matcher import Matcher
nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
pattern = [{"LOWER": "hello"}, {"IS_PUNCT": True}, {"LOWER": "world"}]
matcher.add("HelloWorld", None, pattern)
doc = nlp("Hello, world! Hello world!")
matches = matcher(doc)
```
Adding `{executable="true"}` to the title turns the code into an executable
block, powered by [Binder](https://mybinder.org) and
[Juniper](https://github.com/ines/juniper). If JavaScript is disabled, the
interactive widget defaults to a regular code block.
> #### Markdown
>
> ````markdown_
> ```python
> ### {executable="true"}
> import spacy
> nlp = spacy.load("en_core_web_sm")
> ```
> ````
```python
### {executable="true"}
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("This is a sentence.")
for token in doc:
print(token.text, token.pos_)
```
If a code block only contains a URL to a GitHub file, the raw file contents are
embedded automatically and syntax highlighting is applied. The link to the
original file is shown at the top of the widget.
> #### Markdown
>
> ````markdown_
> ```python
> https://github.com/...
> ```
> ````
>
> #### JSX
>
> ```jsx
> <GitHubCode url="https://github.com/..." lang="python" />
> ```
```python
https://github.com/explosion/spaCy/tree/master/spacy/language.py
```
### Infobox {#infobox}
import Infobox from 'components/infobox'
> #### JSX
>
> ```jsx
> <Infobox title="Information">Regular infobox</Infobox>
> <Infobox title="Important note" variant="warning">This is a warning.</Infobox>
> <Infobox title="Be careful!" variant="danger">This is dangerous.</Infobox>
> ```
Infoboxes can be used to add notes, updates, warnings or additional information
to a page or section. Semantically, they're implemented and interpreted as an
`aside` element. Infoboxes can take an optional `title` argument, as well as an
optional `variant` (either `"warning"` or `"danger"`).
<Infobox title="This is an infobox">
If needed, an infobox can contain regular text, `inline code`, lists and other
blocks.
</Infobox>
<Infobox title="This is a warning" variant="warning">
If needed, an infobox can contain regular text, `inline code`, lists and other
blocks.
</Infobox>
<Infobox title="This is dangerous" variant="danger">
If needed, an infobox can contain regular text, `inline code`, lists and other
blocks.
</Infobox>
### Accordion {#accordion}
import Accordion from 'components/accordion'
> #### JSX
>
> ```jsx
> <Accordion title="This is an accordion">
> Accordion content goes here.
> </Accordion>
> ```
Accordions are collapsible sections that are mostly used for lengthy tables,
like the tag and label annotation schemes for different languages. They all need
to be presented – but chances are the user doesn't actually care about _all_ of
them, especially not at the same time. So it's fairly reasonable to hide them
begin a click. This particular implementation was inspired by the amazing
[Inclusive Components blog](https://inclusive-components.design/collapsible-sections/).
<Accordion title="This is an accordion">
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Quisque enim ante,
pretium a orci eget, varius dignissim augue. Nam eu dictum mauris, id tincidunt
nisi. Integer commodo pellentesque tincidunt. Nam at turpis finibus tortor
gravida sodales tincidunt sit amet est. Nullam euismod arcu in tortor auctor,
sit amet dignissim justo congue.
</Accordion>
## Markdown reference {#markdown}
All page content and page meta lives in the `.md` files in the `/docs`
directory. The frontmatter block at the top of each file defines the page title
and other settings like the sidebar menu.
````markdown
---
title: Page title
---
## Headline starting a section {#some_id}
This is a regular paragraph with a [link](https://spacy.io) and **bold text**.
> #### This is an aside title
>
> This is aside text.
### Subheadline
| Header 1 | Header 2 |
| -------- | -------- |
| Column 1 | Column 2 |
```python
### Code block title {highlight="2-3"}
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp("Hello world")
```
<Infobox title="Important note" variant="warning">
This is content in the infobox.
</Infobox>
````
In addition to the native markdown elements, you can use the components
[`<Infobox />`][infobox], [`<Accordion />`][accordion], [`<Abbr />`][abbr] and
[`<Tag />`][tag] via their JSX syntax.
[infobox]: https://spacy.io/styleguide#infobox
[accordion]: https://spacy.io/styleguide#accordion
[abbr]: https://spacy.io/styleguide#abbr
[tag]: https://spacy.io/styleguide#tag
## Editorial {#editorial}
- "spaCy" should always be spelled with a lowercase "s" and a capital "C",
unless it specifically refers to the Python package or Python import `spacy`
(in which case it should be formatted as code).
- ✅ spaCy is a library for advanced NLP in Python.
- ❌ Spacy is a library for advanced NLP in Python.
- ✅ First, you need to install the `spacy` package from pip.
- Mentions of code, like function names, classes, variable names etc. in inline
text should be formatted as `code`.
- ✅ "Calling the `nlp` object on a text returns a `Doc`."
- Objects that have pages in the [API docs](/api) should be linked – for
example, [`Doc`](/api/doc) or [`Language.to_disk`](/api/language#to_disk). The
mentions should still be formatted as code within the link. Links pointing to
the API docs will automatically receive a little icon. However, if a paragraph
includes many references to the API, the links can easily get messy. In that
case, we typically only link the first mention of an object and not any
subsequent ones.
- ✅ The [`Span`](/api/span) and [`Token`](/api/token) objects are views of a
[`Doc`](/api/doc). [`Span.as_doc`](/api/span#as_doc) creates a `Doc` object
from a `Span`.
- ❌ The [`Span`](/api/span) and [`Token`](/api/token) objects are views of a
[`Doc`](/api/doc). [`Span.as_doc`](/api/span#as_doc) creates a
[`Doc`](/api/doc) object from a [`Span`](/api/span).
* Other things we format as code are: references to trained pipeline packages
like `en_core_web_sm` or file names like `code.py` or `meta.json`.
- ✅ After training, the `config.cfg` is saved to disk.
* [Type annotations](#type-annotations) are a special type of code formatting,
expressed by wrapping the text in `~~` instead of backticks. The result looks
like this: ~~List[Doc]~~. All references to known types will be linked
automatically.
- ✅ The model has the input type ~~List[Doc]~~ and it outputs a
~~List[Array2d]~~.
* We try to keep links meaningful but short.
- ✅ For details, see the usage guide on
[training with custom code](/usage/training#custom-code).
- ❌ For details, see
[the usage guide on training with custom code](/usage/training#custom-code).
- ❌ For details, see the usage guide on training with custom code
[here](/usage/training#custom-code).

20
website/docs/usage/projects.md
View File

@ -259,9 +259,9 @@ pipelines.
> This can be used in a project command like so:
>
> ```yaml
> - name: "echo-path"
> script:
> - "echo ${env.ENV_PATH}"
> - name: 'echo-path'
> script:
> - 'echo ${env.ENV_PATH}'
> ```
| Section | Description |
@ -643,12 +643,13 @@ locally.
You can list one or more remotes in the `remotes` section of your
[`project.yml`](#project-yml) by mapping a string name to the URL of the
storage. Under the hood, spaCy uses the
[`smart-open`](https://github.com/RaRe-Technologies/smart_open) library to
communicate with the remote storages, so you can use any protocol that
`smart-open` supports, including [S3](https://aws.amazon.com/s3/),
[Google Cloud Storage](https://cloud.google.com/storage), SSH and more, although
you may need to install extra dependencies to use certain protocols.
storage. Under the hood, spaCy uses
[`Pathy`](https://github.com/justindujardin/pathy) to communicate with the
remote storages, so you can use any protocol that `Pathy` supports, including
[S3](https://aws.amazon.com/s3/),
[Google Cloud Storage](https://cloud.google.com/storage), and the local
filesystem, although you may need to install extra dependencies to use certain
protocols.
> #### Example
>
@ -661,7 +662,6 @@ you may need to install extra dependencies to use certain protocols.
remotes:
default: 's3://my-spacy-bucket'
local: '/mnt/scratch/cache'
stuff: 'ssh://myserver.example.com/whatever'
```
<Infobox title="How it works" emoji="💡">

4
website/docs/usage/v3-4.md
View File

@ -66,8 +66,8 @@ The English CNN pipelines have new word vectors:
| Package | Model Version | TAG | Parser LAS | NER F |
| ----------------------------------------------- | ------------- | ---: | ---------: | ----: |
| [`en_core_web_md`](/models/en#en_core_web_md) | v3.3.0 | 97.3 | 90.1 | 84.6 |
| [`en_core_web_md`](/models/en#en_core_web_lg) | v3.4.0 | 97.2 | 90.3 | 85.5 |
| [`en_core_web_lg`](/models/en#en_core_web_md) | v3.3.0 | 97.4 | 90.1 | 85.3 |
| [`en_core_web_md`](/models/en#en_core_web_md) | v3.4.0 | 97.2 | 90.3 | 85.5 |
| [`en_core_web_lg`](/models/en#en_core_web_lg) | v3.3.0 | 97.4 | 90.1 | 85.3 |
| [`en_core_web_lg`](/models/en#en_core_web_lg) | v3.4.0 | 97.3 | 90.2 | 85.6 |
## Notes about upgrading from v3.3 {#upgrading}

2
website/meta/sidebars.json
View File

@ -45,7 +45,7 @@
{ "text": "v2.x Documentation", "url": "https://v2.spacy.io" },
{
"text": "Custom Solutions",
"url": "https://explosion.ai/spacy-tailored-pipelines"
"url": "https://explosion.ai/custom-solutions"
}
]
}

2
website/meta/site.json
View File

@ -51,7 +51,7 @@
{ "text": "Online Course", "url": "https://course.spacy.io" },
{
"text": "Custom Solutions",
"url": "https://explosion.ai/spacy-tailored-pipelines"
"url": "https://explosion.ai/custom-solutions"
}
]
},

44
website/meta/universe.json
View File

@ -1023,25 +1023,6 @@
},
"category": ["pipeline"]
},
{
"id": "spacy-sentence-segmenter",
"title": "Sentence Segmenter",
"slogan": "Custom sentence segmentation for spaCy",
"code_example": [
"from seg.newline.segmenter import NewLineSegmenter",
"import spacy",
"",
"nlseg = NewLineSegmenter()",
"nlp = spacy.load('en')",
"nlp.add_pipe(nlseg.set_sent_starts, name='sentence_segmenter', before='parser')",
"doc = nlp(my_doc_text)"
],
"author": "tc64",
"author_links": {
"github": "tc64"
},
"category": ["pipeline"]
},
{
"id": "spacy_cld",
"title": "spaCy-CLD",
@ -1468,13 +1449,26 @@
"image": "https://jasonkessler.github.io/2012conventions0.0.2.2.png",
"code_example": [
"import spacy",
"import scattertext as st",
"",
"nlp = spacy.load('en')",
"corpus = st.CorpusFromPandas(convention_df,",
" category_col='party',",
" text_col='text',",
" nlp=nlp).build()"
"from scattertext import SampleCorpora, produce_scattertext_explorer",
"from scattertext import produce_scattertext_html",
"from scattertext.CorpusFromPandas import CorpusFromPandas",
"",
"nlp = spacy.load('en_core_web_sm')",
"convention_df = SampleCorpora.ConventionData2012.get_data()",
"corpus = CorpusFromPandas(convention_df,",
" category_col='party',",
" text_col='text',",
" nlp=nlp).build()",
"",
"html = produce_scattertext_html(corpus,",
" category='democrat',",
" category_name='Democratic',",
" not_category_name='Republican',",
" minimum_term_frequency=5,",
" width_in_pixels=1000)",
"open('./simple.html', 'wb').write(html.encode('utf-8'))",
"print('Open ./simple.html in Chrome or Firefox.')"
],
"author": "Jason Kessler",
"author_links": {

4
website/src/widgets/landing.js
View File

@ -105,13 +105,13 @@ const Landing = ({ data }) => {
<LandingBannerGrid>
<LandingBanner
to="https://explosion.ai/spacy-tailored-pipelines"
to="https://explosion.ai/custom-solutions"
button="Learn more"
background="#E4F4F9"
color="#1e1935"
small
>
<Link to="https://explosion.ai/spacy-tailored-pipelines" hidden>
<Link to="https://explosion.ai/custom-solutions" hidden>
<img src={tailoredPipelinesImage} alt="spaCy Tailored Pipelines" />
</Link>
<strong>