explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #12626 from adrianeboyd/backport/v3.5.3-1

Browse Source 
Backports for v3.5.3
This commit is contained in:
Adriane Boyd 2023-05-12 11:18:12 +02:00 committed by GitHub
commit 424e917c6c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
20 changed files with 298 additions and 311 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

118
.github/azure-steps.yml vendored
View File

@ -1,118 +0,0 @@
parameters:
python_version: ''
architecture: 'x64'
num_build_jobs: 2
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: ${{ parameters.python_version }}
architecture: ${{ parameters.architecture }}
allowUnstable: true
- bash: |
echo "##vso[task.setvariable variable=python_version]${{ parameters.python_version }}"
displayName: 'Set variables'
- script: |
python -m pip install -U build pip setuptools
python -m pip install -U -r requirements.txt
displayName: "Install dependencies"
- script: |
python -m build --sdist
displayName: "Build sdist"
- script: |
python -m mypy spacy
displayName: 'Run mypy'
condition: ne(variables['python_version'], '3.6')
- task: DeleteFiles@1
inputs:
contents: "spacy"
displayName: "Delete source directory"
- task: DeleteFiles@1
inputs:
contents: "*.egg-info"
displayName: "Delete egg-info directory"
- script: |
python -m pip freeze > installed.txt
python -m pip uninstall -y -r installed.txt
displayName: "Uninstall all packages"
- bash: |
SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
SPACY_NUM_BUILD_JOBS=${{ parameters.num_build_jobs }} python -m pip install dist/$SDIST
displayName: "Install from sdist"
- script: |
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'], '3.9')
- script: |
python -W error -m spacy info ca_core_news_sm | grep -q download_url
displayName: 'Test download_url in info CLI'
condition: eq(variables['python_version'], '3.9')
- 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'], '3.9')
- script: |
python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
displayName: 'Test convert CLI'
condition: eq(variables['python_version'], '3.9')
- script: |
python -m spacy init config -p ner -l ca ner.cfg
python -m spacy debug config ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy
displayName: 'Test debug config CLI'
condition: eq(variables['python_version'], '3.9')
- script: |
# will have errors due to sparse data, check for summary in output
python -m spacy debug data ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy | grep -q Summary
displayName: 'Test debug data CLI'
condition: eq(variables['python_version'], '3.9')
- script: |
python -m spacy train ner.cfg --paths.train ner-token-per-line-conll2003.spacy --paths.dev ner-token-per-line-conll2003.spacy --training.max_steps 10 --gpu-id -1
displayName: 'Test train CLI'
condition: eq(variables['python_version'], '3.9')
- 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'], '3.9')
- 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'], '3.9')
- script: |
python -m pip install -U -r requirements.txt
displayName: "Install test requirements"
- script: |
python -m pytest --pyargs spacy -W error
displayName: "Run CPU tests"
- script: |
python -m pip install 'spacy[apple]'
python -m pytest --pyargs spacy
displayName: "Run CPU tests with thinc-apple-ops"
condition: and(startsWith(variables['imageName'], 'macos'), eq(variables['python.version'], '3.11'))

1
.github/workflows/tests.yml vendored
View File

@ -165,6 +165,7 @@ jobs:
- name: "Run CPU tests"
run: |
python -m pytest --pyargs spacy -W error
if: "!(startsWith(matrix.os, 'macos') && matrix.python_version == '3.11')"
- name: "Run CPU tests with thinc-apple-ops"
run: |

120
azure-pipelines.yml
View File

@ -1,120 +0,0 @@
trigger:
batch: true
branches:
include:
- "*"
exclude:
- "spacy.io"
- "nightly.spacy.io"
- "v2.spacy.io"
paths:
exclude:
- "website/*"
- "*.md"
- "*.mdx"
- ".github/workflows/*"
pr:
paths:
exclude:
- "*.md"
- "*.mdx"
- "website/docs/*"
- "website/src/*"
- "website/meta/*.tsx"
- "website/meta/*.mjs"
- "website/meta/languages.json"
- "website/meta/site.json"
- "website/meta/sidebars.json"
- "website/meta/type-annotations.json"
- "website/pages/*"
- ".github/workflows/*"
jobs:
# Check formatting and linting. Perform basic checks for most important errors
# (syntax etc.) Uses the config defined in setup.cfg and overwrites the
# selected codes.
- job: "Validate"
pool:
vmImage: "ubuntu-latest"
steps:
- task: UsePythonVersion@0
inputs:
versionSpec: "3.7"
- script: |
pip install black -c requirements.txt
python -m black spacy --check
displayName: "black"
- script: |
pip install flake8==5.0.4
python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics
displayName: "flake8"
- script: |
python .github/validate_universe_json.py website/meta/universe.json
displayName: 'Validate website/meta/universe.json'
- job: "Test"
dependsOn: "Validate"
strategy:
matrix:
# We're only running one platform per Python version to speed up builds
Python36Linux:
imageName: "ubuntu-20.04"
python.version: "3.6"
# Python36Windows:
# imageName: "windows-latest"
# python.version: "3.6"
# Python36Mac:
# imageName: "macos-latest"
# python.version: "3.6"
# Python37Linux:
# imageName: "ubuntu-20.04"
# python.version: "3.7"
Python37Windows:
imageName: "windows-latest"
python.version: "3.7"
# Python37Mac:
# imageName: "macos-latest"
# python.version: "3.7"
# Python38Linux:
# imageName: "ubuntu-latest"
# python.version: "3.8"
# Python38Windows:
# imageName: "windows-latest"
# python.version: "3.8"
Python38Mac:
imageName: "macos-latest"
python.version: "3.8"
Python39Linux:
imageName: "ubuntu-latest"
python.version: "3.9"
# Python39Windows:
# imageName: "windows-latest"
# python.version: "3.9"
# Python39Mac:
# imageName: "macos-latest"
# python.version: "3.9"
# Python310Linux:
# imageName: "ubuntu-latest"
# python.version: "3.10"
Python310Windows:
imageName: "windows-latest"
python.version: "3.10"
# Python310Mac:
# imageName: "macos-latest"
# python.version: "3.10"
Python311Linux:
imageName: 'ubuntu-latest'
python.version: '3.11'
Python311Windows:
imageName: 'windows-latest'
python.version: '3.11'
Python311Mac:
imageName: 'macos-latest'
python.version: '3.11'
maxParallel: 4
pool:
vmImage: $(imageName)
steps:
- template: .github/azure-steps.yml
parameters:
python_version: '$(python.version)'

2
spacy/cli/debug_data.py
View File

@ -336,7 +336,7 @@ def debug_data(
show=verbose,
)
else:
msg.good("Examples without ocurrences available for all labels")
msg.good("Examples without occurrences available for all labels")
if "ner" in factory_names:
# Get all unique NER labels present in the data

3
spacy/cli/download.py
View File

@ -81,11 +81,8 @@ def download(
def get_model_filename(model_name: str, version: str, sdist: bool = False) -> str:
dl_tpl = "{m}-{v}/{m}-{v}{s}"
egg_tpl = "#egg={m}=={v}"
suffix = SDIST_SUFFIX if sdist else WHEEL_SUFFIX
filename = dl_tpl.format(m=model_name, v=version, s=suffix)
if sdist:
filename += egg_tpl.format(m=model_name, v=version)
return filename

9
spacy/cli/evaluate.py
View File

@ -122,6 +122,8 @@ def evaluate(
docs = list(nlp.pipe(ex.reference.text for ex in dev_dataset[:displacy_limit]))
render_deps = "parser" in factory_names
render_ents = "ner" in factory_names
render_spans = "spancat" in factory_names
render_parses(
docs,
displacy_path,
@ -129,6 +131,7 @@ def evaluate(
limit=displacy_limit,
deps=render_deps,
ents=render_ents,
spans=render_spans,
)
msg.good(f"Generated {displacy_limit} parses as HTML", displacy_path)
@ -182,6 +185,7 @@ def render_parses(
limit: int = 250,
deps: bool = True,
ents: bool = True,
spans: bool = True,
):
docs[0].user_data["title"] = model_name
if ents:
@ -195,6 +199,11 @@ def render_parses(
with (output_path / "parses.html").open("w", encoding="utf8") as file_:
file_.write(html)
if spans:
html = displacy.render(docs[:limit], style="span", page=True)
with (output_path / "spans.html").open("w", encoding="utf8") as file_:
file_.write(html)
def print_prf_per_type(
msg: Printer, scores: Dict[str, Dict[str, float]], name: str, type: str

8
spacy/matcher/dependencymatcher.pyx
View File

@ -432,22 +432,22 @@ cdef class DependencyMatcher:
return [doc[child.i] for child in doc[node].head.children if child.i < node]
def _imm_right_child(self, doc, node):
for child in doc[node].children:
for child in doc[node].rights:
if child.i == node + 1:
return [doc[child.i]]
return []
def _imm_left_child(self, doc, node):
for child in doc[node].children:
for child in doc[node].lefts:
if child.i == node - 1:
return [doc[child.i]]
return []
def _right_child(self, doc, node):
return [doc[child.i] for child in doc[node].children if child.i > node]
return [child for child in doc[node].rights]
def _left_child(self, doc, node):
return [doc[child.i] for child in doc[node].children if child.i < node]
return [child for child in doc[node].lefts]
def _imm_right_parent(self, doc, node):
if doc[node].head.i == node + 1:

8
spacy/ml/extract_spans.py
View File

@ -1,4 +1,4 @@
from typing import Tuple, Callable
from typing import List, Tuple, Callable
from thinc.api import Model, to_numpy
from thinc.types import Ragged, Ints1d
@ -52,14 +52,14 @@ def _get_span_indices(ops, spans: Ragged, lengths: Ints1d) -> Ints1d:
indices will be [5, 6, 7, 8, 8, 9].
"""
spans, lengths = _ensure_cpu(spans, lengths)
indices = []
indices: List[int] = []
offset = 0
for i, length in enumerate(lengths):
spans_i = spans[i].dataXd + offset
for j in range(spans_i.shape[0]):
indices.append(ops.xp.arange(spans_i[j, 0], spans_i[j, 1])) # type: ignore[call-overload, index]
indices.extend(range(spans_i[j, 0], spans_i[j, 1])) # type: ignore[arg-type, call-overload]
offset += length
return ops.flatten(indices, dtype="i", ndim_if_empty=1)
return ops.asarray1i(indices)
def _ensure_cpu(spans: Ragged, lengths: Ints1d) -> Tuple[Ragged, Ints1d]:

2
spacy/tests/doc/test_morphanalysis.py
View File

@ -33,6 +33,8 @@ def test_token_morph_key(i_has):
def test_morph_props(i_has):
assert i_has[0].morph.get("PronType") == ["prs"]
assert i_has[1].morph.get("PronType") == []
assert i_has[1].morph.get("AsdfType", ["asdf"]) == ["asdf"]
assert i_has[1].morph.get("AsdfType", default=["asdf", "qwer"]) == ["asdf", "qwer"]
def test_morph_iter(i_has):

66
spacy/tests/test_cli.py
View File

@ -12,6 +12,7 @@ import srsly
from click import NoSuchOption
from packaging.specifiers import SpecifierSet
from thinc.api import Config, ConfigValidationError
from spacy.tokens import DocBin
from spacy import about
from spacy.cli import info
@ -27,6 +28,7 @@ from spacy.cli.debug_data import _get_span_characteristics
from spacy.cli.debug_data import _print_span_characteristics
from spacy.cli.debug_data import _get_spans_length_freq_dist
from spacy.cli.download import get_compatibility, get_version
from spacy.cli.evaluate import render_parses
from spacy.cli.init_config import RECOMMENDATIONS, init_config, fill_config
from spacy.cli.init_pipeline import _init_labels
from spacy.cli.package import get_third_party_dependencies
@ -144,6 +146,70 @@ def test_issue11235():
assert cfg["commands"][0]["script"][0] == f"hello {lang_var}"
@pytest.mark.issue(12566)
@pytest.mark.parametrize(
"factory,output_file",
[("deps", "parses.html"), ("ents", "entities.html"), ("spans", "spans.html")],
)
def test_issue12566(factory: str, output_file: str):
"""
Test if all displaCy types (ents, dep, spans) produce an HTML file
"""
with make_tempdir() as tmp_dir:
# Create sample spaCy file
doc_json = {
"ents": [
{"end": 54, "label": "nam_adj_country", "start": 44},
{"end": 83, "label": "nam_liv_person", "start": 69},
{"end": 100, "label": "nam_pro_title_book", "start": 86},
],
"spans": {
"sc": [
{"end": 54, "kb_id": "", "label": "nam_adj_country", "start": 44},
{"end": 83, "kb_id": "", "label": "nam_liv_person", "start": 69},
{
"end": 100,
"kb_id": "",
"label": "nam_pro_title_book",
"start": 86,
},
]
},
"text": "Niedawno czytał em nową książkę znakomitego szkockiego medioznawcy , "
"Briana McNaira - Cultural Chaos .",
"tokens": [
# fmt: off
{"id": 0, "start": 0, "end": 8, "tag": "ADV", "pos": "ADV", "morph": "Degree=Pos", "lemma": "niedawno", "dep": "advmod", "head": 1, },
{"id": 1, "start": 9, "end": 15, "tag": "PRAET", "pos": "VERB", "morph": "Animacy=Hum|Aspect=Imp|Gender=Masc|Mood=Ind|Number=Sing|Tense=Past|VerbForm=Fin|Voice=Act", "lemma": "czytać", "dep": "ROOT", "head": 1, },
{"id": 2, "start": 16, "end": 18, "tag": "AGLT", "pos": "NOUN", "morph": "Animacy=Inan|Case=Ins|Gender=Masc|Number=Sing", "lemma": "em", "dep": "iobj", "head": 1, },
{"id": 3, "start": 19, "end": 23, "tag": "ADJ", "pos": "ADJ", "morph": "Case=Acc|Degree=Pos|Gender=Fem|Number=Sing", "lemma": "nowy", "dep": "amod", "head": 4, },
{"id": 4, "start": 24, "end": 31, "tag": "SUBST", "pos": "NOUN", "morph": "Case=Acc|Gender=Fem|Number=Sing", "lemma": "książka", "dep": "obj", "head": 1, },
{"id": 5, "start": 32, "end": 43, "tag": "ADJ", "pos": "ADJ", "morph": "Animacy=Nhum|Case=Gen|Degree=Pos|Gender=Masc|Number=Sing", "lemma": "znakomit", "dep": "acl", "head": 4, },
{"id": 6, "start": 44, "end": 54, "tag": "ADJ", "pos": "ADJ", "morph": "Animacy=Hum|Case=Gen|Degree=Pos|Gender=Masc|Number=Sing", "lemma": "szkockiy", "dep": "amod", "head": 7, },
{"id": 7, "start": 55, "end": 66, "tag": "SUBST", "pos": "NOUN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "medioznawca", "dep": "iobj", "head": 5, },
{"id": 8, "start": 67, "end": 68, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Comm", "lemma": ",", "dep": "punct", "head": 9, },
{"id": 9, "start": 69, "end": 75, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "Brian", "dep": "nmod", "head": 4, },
{"id": 10, "start": 76, "end": 83, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Hum|Case=Gen|Gender=Masc|Number=Sing", "lemma": "McNair", "dep": "flat", "head": 9, },
{"id": 11, "start": 84, "end": 85, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Dash", "lemma": "-", "dep": "punct", "head": 12, },
{"id": 12, "start": 86, "end": 94, "tag": "SUBST", "pos": "PROPN", "morph": "Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing", "lemma": "Cultural", "dep": "conj", "head": 4, },
{"id": 13, "start": 95, "end": 100, "tag": "SUBST", "pos": "NOUN", "morph": "Animacy=Inan|Case=Nom|Gender=Masc|Number=Sing", "lemma": "Chaos", "dep": "flat", "head": 12, },
{"id": 14, "start": 101, "end": 102, "tag": "INTERP", "pos": "PUNCT", "morph": "PunctType=Peri", "lemma": ".", "dep": "punct", "head": 1, },
# fmt: on
],
}
# Create a .spacy file
nlp = spacy.blank("pl")
doc = Doc(nlp.vocab).from_json(doc_json)
# Run the evaluate command and check if the html files exist
render_parses(
docs=[doc], output_path=tmp_dir, model_name="", limit=1, **{factory: True}
)
assert (tmp_dir / output_file).is_file()
def test_cli_info():
nlp = Dutch()
nlp.add_pipe("textcat")

6
spacy/tokenizer.pyx
View File

@ -834,10 +834,12 @@ cdef class Tokenizer:
self.token_match = re.compile(data["token_match"]).match
if "url_match" in data and isinstance(data["url_match"], str):
self.url_match = re.compile(data["url_match"]).match
if "rules" in data and isinstance(data["rules"], dict):
self.rules = data["rules"]
if "faster_heuristics" in data:
self.faster_heuristics = data["faster_heuristics"]
# always load rules last so that all other settings are set before the
# internal tokenization for the phrase matcher
if "rules" in data and isinstance(data["rules"], dict):
self.rules = data["rules"]
return self

4
spacy/tokens/morphanalysis.pyi
View File

@ -1,4 +1,4 @@
from typing import Any, Dict, Iterator, List, Union
from typing import Any, Dict, Iterator, List, Optional, Union
from ..vocab import Vocab
class MorphAnalysis:
@ -13,7 +13,7 @@ class MorphAnalysis:
def __hash__(self) -> int: ...
def __eq__(self, other: MorphAnalysis) -> bool: ... # type: ignore[override]
def __ne__(self, other: MorphAnalysis) -> bool: ... # type: ignore[override]
def get(self, field: Any) -> List[str]: ...
def get(self, field: Any, default: Optional[List[str]]) -> List[str]: ...
def to_json(self) -> str: ...
def to_dict(self) -> Dict[str, str]: ...
def __str__(self) -> str: ...

6
spacy/tokens/morphanalysis.pyx
View File

@ -58,10 +58,14 @@ cdef class MorphAnalysis:
def __ne__(self, other):
return self.key != other.key
def get(self, field):
def get(self, field, default=None):
"""Retrieve feature values by field."""
cdef attr_t field_id = self.vocab.strings.as_int(field)
cdef np.ndarray results = get_by_field(&self.c, field_id)
if len(results) == 0:
if default is None:
default = []
return default
features = [self.vocab.strings[result] for result in results]
return [f.split(Morphology.FIELD_SEP)[1] for f in features]

9
spacy/training/initialize.py
View File

@ -133,10 +133,11 @@ def init_vocab(
logger.info("Added vectors: %s", vectors)
# warn if source model vectors are not identical
sourced_vectors_hashes = nlp.meta.pop("_sourced_vectors_hashes", {})
vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"]))
for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items():
if vectors_hash != sourced_vectors_hash:
warnings.warn(Warnings.W113.format(name=sourced_component))
if len(sourced_vectors_hashes) > 0:
vectors_hash = hash(nlp.vocab.vectors.to_bytes(exclude=["strings"]))
for sourced_component, sourced_vectors_hash in sourced_vectors_hashes.items():
if vectors_hash != sourced_vectors_hash:
warnings.warn(Warnings.W113.format(name=sourced_component))
logger.info("Finished initializing nlp object")

3
website/docs/api/cli.mdx
View File

@ -1640,7 +1640,7 @@ with [`spacy package`](/api/cli#package) and `--build wheel`. For more details,
see the spaCy project [integration](/usage/projects#huggingface_hub).
```bash
$ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--local-repo] [--verbose]
$ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--verbose]
```
> #### Example
@ -1654,6 +1654,5 @@ $ python -m spacy huggingface-hub push [whl_path] [--org] [--msg] [--local-repo]
| `whl_path` | The path to the `.whl` file packaged with [`spacy package`](https://spacy.io/api/cli#package). ~~Path(positional)~~ |
| `--org`, `-o` | Optional name of organization to which the pipeline should be uploaded. ~~str (option)~~ |
| `--msg`, `-m` | Commit message to use for update. Defaults to `"Update spaCy pipeline"`. ~~str (option)~~ |
| `--local-repo`, `-l` | Local path to the model repository (will be created if it doesn't exist). Defaults to `hub` in the current working directory. ~~Path (option)~~ |
| `--verbose`, `-V` | Output additional info for debugging, e.g. the full generated hub metadata. ~~bool (flag)~~ |
| **UPLOADS** | The pipeline to the hub. |

44
website/docs/api/dependencymatcher.mdx
View File

@ -68,28 +68,28 @@ The following operators are supported by the `DependencyMatcher`, most of which
come directly from
[Semgrex](https://nlp.stanford.edu/nlp/javadoc/javanlp/edu/stanford/nlp/semgraph/semgrex/SemgrexPattern.html):
| Symbol | Description |
| --------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
| `A < B` | `A` is the immediate dependent of `B`. |
| `A > B` | `A` is the immediate head of `B`. |
| `A << B` | `A` is the dependent in a chain to `B` following dep &rarr; head paths. |
| `A >> B` | `A` is the head in a chain to `B` following head &rarr; dep paths. |
| `A . B` | `A` immediately precedes `B`, i.e. `A.i == B.i - 1`, and both are within the same dependency tree. |
| `A .* B` | `A` precedes `B`, i.e. `A.i < B.i`, and both are within the same dependency tree _(not in Semgrex)_. |
| `A ; B` | `A` immediately follows `B`, i.e. `A.i == B.i + 1`, and both are within the same dependency tree _(not in Semgrex)_. |
| `A ;* B` | `A` follows `B`, i.e. `A.i > B.i`, and both are within the same dependency tree _(not in Semgrex)_. |
| `A $+ B` | `B` is a right immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i - 1`. |
| `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. |
| `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. |
| `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
| `A >+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A >- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i` _(not in Semgrex)_. |
| `A <+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A <- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i` _(not in Semgrex)_. |
| Symbol | Description |
| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `A < B` | `A` is the immediate dependent of `B`. |
| `A > B` | `A` is the immediate head of `B`. |
| `A << B` | `A` is the dependent in a chain to `B` following dep &rarr; head paths. |
| `A >> B` | `A` is the head in a chain to `B` following head &rarr; dep paths. |
| `A . B` | `A` immediately precedes `B`, i.e. `A.i == B.i - 1`, and both are within the same dependency tree. |
| `A .* B` | `A` precedes `B`, i.e. `A.i < B.i`, and both are within the same dependency tree _(Semgrex counterpart: `..`)_. |
| `A ; B` | `A` immediately follows `B`, i.e. `A.i == B.i + 1`, and both are within the same dependency tree _(Semgrex counterpart: `-`)_. |
| `A ;* B` | `A` follows `B`, i.e. `A.i > B.i`, and both are within the same dependency tree _(Semgrex counterpart: `--`)_. |
| `A $+ B` | `B` is a right immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i - 1`. |
| `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. |
| `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. |
| `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
| `A >+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A >- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i`. |
| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i`. |
| `A <+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A <- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i`. |
| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i`. |
## DependencyMatcher.\_\_init\_\_ {id="init",tag="method"}

2
website/docs/api/inmemorylookupkb.mdx
View File

@ -292,7 +292,7 @@ Restore the state of the knowledge base from a given directory. Note that the
> ```python
> from spacy.vocab import Vocab
> vocab = Vocab().from_disk("/path/to/vocab")
> kb = FullyImplementedKB(vocab=vocab, entity_vector_length=64)
> kb = InMemoryLookupKB(vocab=vocab, entity_vector_length=64)
> kb.from_disk("/path/to/kb")
> ```

9
website/docs/api/morphology.mdx
View File

@ -213,10 +213,11 @@ Retrieve values for a feature by field.
> assert morph.get("Feat1") == ["Val1", "Val2"]
> ```
| Name | Description |
| ----------- | ------------------------------------------------ |
| `field` | The field to retrieve. ~~str~~ |
| **RETURNS** | A list of the individual features. ~~List[str]~~ |
| Name | Description |
| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------ |
| `field` | The field to retrieve. ~~str~~ |
| `default` <Tag variant="new">3.6</Tag> | The value to return if the field is not present. If unset or `None`, the default return value is `[]`. ~~Optional[List[str]]~~ |
| **RETURNS** | A list of the individual features. ~~List[str]~~ |
### MorphAnalysis.to_dict {id="morphanalysis-to_dict",tag="method"}

44
website/docs/usage/rule-based-matching.mdx
View File

@ -1096,28 +1096,28 @@ The following operators are supported by the `DependencyMatcher`, most of which
come directly from
[Semgrex](https://nlp.stanford.edu/nlp/javadoc/javanlp/edu/stanford/nlp/semgraph/semgrex/SemgrexPattern.html):
| Symbol | Description |
| --------------------------------------- | -------------------------------------------------------------------------------------------------------------------- |
| `A < B` | `A` is the immediate dependent of `B`. |
| `A > B` | `A` is the immediate head of `B`. |
| `A << B` | `A` is the dependent in a chain to `B` following dep &rarr; head paths. |
| `A >> B` | `A` is the head in a chain to `B` following head &rarr; dep paths. |
| `A . B` | `A` immediately precedes `B`, i.e. `A.i == B.i - 1`, and both are within the same dependency tree. |
| `A .* B` | `A` precedes `B`, i.e. `A.i < B.i`, and both are within the same dependency tree _(not in Semgrex)_. |
| `A ; B` | `A` immediately follows `B`, i.e. `A.i == B.i + 1`, and both are within the same dependency tree _(not in Semgrex)_. |
| `A ;* B` | `A` follows `B`, i.e. `A.i > B.i`, and both are within the same dependency tree _(not in Semgrex)_. |
| `A $+ B` | `B` is a right immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i - 1`. |
| `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. |
| `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. |
| `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
| `A >+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A >- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i` _(not in Semgrex)_. |
| `A <+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A <- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i` _(not in Semgrex)_. |
| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i` _(not in Semgrex)_. |
| Symbol | Description |
| --------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------- |
| `A < B` | `A` is the immediate dependent of `B`. |
| `A > B` | `A` is the immediate head of `B`. |
| `A << B` | `A` is the dependent in a chain to `B` following dep &rarr; head paths. |
| `A >> B` | `A` is the head in a chain to `B` following head &rarr; dep paths. |
| `A . B` | `A` immediately precedes `B`, i.e. `A.i == B.i - 1`, and both are within the same dependency tree. |
| `A .* B` | `A` precedes `B`, i.e. `A.i < B.i`, and both are within the same dependency tree _(Semgrex counterpart: `..`)_. |
| `A ; B` | `A` immediately follows `B`, i.e. `A.i == B.i + 1`, and both are within the same dependency tree _(Semgrex counterpart: `-`)_. |
| `A ;* B` | `A` follows `B`, i.e. `A.i > B.i`, and both are within the same dependency tree _(Semgrex counterpart: `--`)_. |
| `A $+ B` | `B` is a right immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i - 1`. |
| `A $- B` | `B` is a left immediate sibling of `A`, i.e. `A` and `B` have the same parent and `A.i == B.i + 1`. |
| `A $++ B` | `B` is a right sibling of `A`, i.e. `A` and `B` have the same parent and `A.i < B.i`. |
| `A $-- B` | `B` is a left sibling of `A`, i.e. `A` and `B` have the same parent and `A.i > B.i`. |
| `A >+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A >- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate child of `A`, i.e. `A` is a parent of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A >++ B` | `B` is a right child of `A`, i.e. `A` is a parent of `B` and `A.i < B.i`. |
| `A >-- B` | `B` is a left child of `A`, i.e. `A` is a parent of `B` and `A.i > B.i`. |
| `A <+ B` <Tag variant="new">3.5.1</Tag> | `B` is a right immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i - 1` _(not in Semgrex)_. |
| `A <- B` <Tag variant="new">3.5.1</Tag> | `B` is a left immediate parent of `A`, i.e. `A` is a child of `B` and `A.i == B.i + 1` _(not in Semgrex)_. |
| `A <++ B` | `B` is a right parent of `A`, i.e. `A` is a child of `B` and `A.i < B.i`. |
| `A <-- B` | `B` is a left parent of `A`, i.e. `A` is a child of `B` and `A.i > B.i`. |
### Designing dependency matcher patterns {id="dependencymatcher-patterns"}

145
website/meta/universe.json
View File

@ -1,5 +1,98 @@
{
"resources": [
{
"id": "parsigs",
"title": "parsigs",
"slogan": "Structuring prescriptions text made simple using spaCy",
"description": "Parsigs is an open-source project that aims to extract the relevant dosage information from prescriptions text without compromising the patient's privacy.\n\nNotice you also need to install the model in order to use the package: `pip install https://huggingface.co/royashcenazi/en_parsigs/resolve/main/en_parsigs-any-py3-none-any.whl`",
"github": "royashcenazi/parsigs",
"pip": "parsigs",
"code_language": "python",
"author": "Roy Ashcenazi",
"code_example": [
"# You'll need to install the trained model, see instructions in the description section",
"from parsigs.parse_sig_api import StructuredSig, SigParser",
"sig_parser = SigParser()",
"",
"sig = 'Take 1 tablet of ibuprofen 200mg 3 times every day for 3 weeks'",
"parsed_sig = sig_parser.parse(sig)"
],
"author_links": {
"github": "royashcenazi"
},
"category": ["model", "research", "biomedical"],
"tags": ["sigs", "prescription","pharma"]
},
{
"id": "latincy",
"title": "LatinCy",
"thumb": "https://raw.githubusercontent.com/diyclassics/la_core_web_lg/main/latincy-logo.png",
"slogan": "Synthetic trained spaCy pipelines for Latin NLP",
"description": "Set of trained general purpose Latin-language 'core' pipelines for use with spaCy. The models are trained on a large amount of available Latin data, including all five of the Latin Universal Dependency treebanks, which have been preprocessed to be compatible with each other.",
"url": "https://huggingface.co/latincy",
"code_example": [
"# pip install https://huggingface.co/latincy/la_core_web_lg/resolve/main/la_core_web_lg-any-py3-none-any.whl",
"import spacy",
"nlp = spacy.load('la_core_web_lg')",
"doc = nlp('Haec narrantur a poetis de Perseo')",
"",
"print(f'{doc[0].text}, {doc[0].norm_}, {doc[0].lemma_}, {doc[0].pos_}')",
"",
"# > Haec, haec, hic, DET"
],
"code_language": "python",
"author": "Patrick J. Burns",
"author_links": {
"twitter": "@diyclassics",
"github": "diyclassics",
"website": "https://diyclassics.github.io/"
},
"category": ["pipeline", "research"],
"tags": ["latin"]
},
{
"id": "spacy-wasm",
"title": "spacy-wasm",
"slogan": "spaCy in the browser using WebAssembly",
"description": "Run spaCy directly in the browser with WebAssembly. Using Pyodide, the application loads the spaCy model and renders the text prompt with displaCy.",
"url": "https://spacy-wasm.vercel.app/",
"github": "SyedAhkam/spacy-wasm",
"code_language": "python",
"author": "Syed Ahkam",
"author_links": {
"twitter": "@SyedAhkam1",
"github": "SyedAhkam"
},
"category": ["visualizers"],
"tags": ["visualization", "deployment"]
},
{
"id": "spacysee",
"title": "spaCysee",
"slogan": "Visualize spaCy's Dependency Parsing, POS tagging, and morphological analysis",
"description": "A project that helps you visualize your spaCy docs in Jupyter notebooks. Each of the dependency tags, POS tags and morphological features are clickable. Clicking on a tag will bring up the relevant documentation for that tag.",
"github": "moxley01/spacysee",
"pip": "spacysee",
"code_example": [
"import spacy",
"from spacysee import render",
"",
"nlp = spacy.load('en_core_web_sm')",
"doc = nlp('This is a neat way to visualize your spaCy docs')",
"render(doc, width='500', height='500')"
],
"code_language": "python",
"thumb": "https://www.mattoxley.com/static/images/spacysee_logo.svg",
"image": "https://www.mattoxley.com/static/images/spacysee_logo.svg",
"author": "Matt Oxley",
"author_links": {
"twitter": "matt0xley",
"github": "moxley01",
"website": "https://mattoxley.com"
},
"category": ["visualizers"],
"tags": ["visualization"]
},
{
"id": "grecy",
"title": "greCy",
@ -1555,7 +1648,7 @@
"twitter": "allenai_org",
"website": "http://allenai.org"
},
"category": ["scientific", "models", "research"]
"category": ["scientific", "models", "research", "biomedical"]
},
{
"id": "textacy",
@ -2767,6 +2860,56 @@
"tags": ["coreference", "multi-lingual", "cross-lingual", "allennlp"],
"spacy_version": 3
},
{
"id": "adeptaugmentations",
"title": "Adept Augmentations",
"slogan": " A Python library aimed at dissecting and augmenting NER training data for a few-shot scenario.",
"description": "EntitySwapAugmenter takes either a `datasets.Dataset` or a `spacy.tokens.DocBin`. Additionally, it is optional to provide a set of labels. It initially creates a knowledge base of entities belonging to a certain label. When running `augmenter.augment()` for N runs, it then creates N new sentences with random swaps of the original entities with an entity of the same corresponding label from the knowledge base.\n\nFor example, assuming that we have knowledge base for `PERSONS`, `LOCATIONS` and `PRODUCTS`. We can then create additional data for the sentence \"Momofuko Ando created instant noodles in Osaka.\" using `augmenter.augment(N=2)`, resulting in \"David created instant noodles in Madrid.\" or \"Tom created Adept Augmentations in the Netherlands\".",
"github": "davidberenstein1957/adept-augmentations",
"pip": "adept-augmentations",
"thumb": "https://raw.githubusercontent.com/Pandora-Intelligence/crosslingual-coreference/master/img/logo.png",
"code_example": [
"import spacy",
"from spacy.tokens import DocBin",
"",
"from adept_augmentations import EntitySwapAugmenter",
"",
"nlp = spacy.load(\"en_core_web_sm\")",
"",
"TRAIN_DATA = [",
" \"Apple is looking at buying U.K. startup for $1 billion\",",
" \"Microsoft acquires GitHub for $7.5 billion\"",
"]",
"docs = nlp.pipe(TRAIN_DATA)",
"",
"# Create a new DocBin",
"doc_bin = DocBin(docs=docs)",
"",
"# Augment Data",
"doc_bin = EntitySwapAugmenter(doc_bin).augment(4)",
"for doc in doc_bin.get_docs(nlp.vocab):",
" print(doc.text)",
"",
"# Output",
"#",
"# GitHub is looking at buying U.K. startup for $ 7.5 billion",
"# Microsoft is looking at buying U.K. startup for $ 1 billion",
"# Microsoft is looking at buying U.K. startup for $ 7.5 billion",
"# GitHub is looking at buying U.K. startup for $ 1 billion",
"# Microsoft acquires Apple for $ 7.5 billion",
"# Apple acquires Microsoft for $ 1 billion",
"# Microsoft acquires Microsoft for $ 7.5 billion",
"# GitHub acquires GitHub for $ 1 billion"
],
"author": "David Berenstein",
"author_links": {
"github": "davidberenstein1957",
"website": "https://www.linkedin.com/in/david-berenstein-1bab11105/"
},
"category": ["standalone"],
"tags": ["ner", "few-shot", "augmentation", "datasets", "training"],
"spacy_version": 3
},
{
"id": "blackstone",
"title": "Blackstone",