explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-21 01:21:58 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'v4' into feature/docwise-generator-batching

Browse Source 
# Conflicts:
#	spacy/kb/kb.pyx
#	spacy/kb/kb_in_memory.pyx
#	spacy/ml/models/entity_linker.py
#	spacy/pipeline/entity_linker.py
#	spacy/tests/pipeline/test_entity_linker.py
#	website/docs/api/entitylinker.mdx
This commit is contained in:
Raphael Mitsch 2023-07-27 14:28:06 +02:00
commit 8aa59c4f65
606 changed files with 11468 additions and 3480 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

129
.github/azure-steps.yml vendored
View File

@ -1,129 +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'], '3.8')
#
# - 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 2>&1 | grep -q skipping
# displayName: 'Test skip re-download (#12188)'
# condition: eq(variables['python_version'], '3.8')
# - 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'] '3.8')
- 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'], '3.8')
- 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'], '3.8')
- 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'], '3.8')
- 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'], '3.8')
# - 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
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'))
- script: |
python .github/validate_universe_json.py website/meta/universe.json
displayName: 'Test website/meta/universe.json'
condition: eq(variables['python_version'], '3.8')

45
.github/workflows/autoblack.yml vendored
View File

@ -1,45 +0,0 @@
# GitHub Action that uses Black to reformat all Python code and submits a PR
# in regular intervals. Inspired by: https://github.com/cclauss/autoblack
name: autoblack
on:
workflow_dispatch: # allow manual trigger
schedule:
- cron: '0 8 * * 5' # every Friday at 8am UTC
jobs:
autoblack:
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
with:
ref: ${{ github.head_ref }}
- uses: actions/setup-python@v4
- run: pip install black -c requirements.txt
- name: Auto-format code if needed
run: black spacy
# We can't run black --check here because that returns a non-zero excit
# code and makes GitHub think the action failed
- name: Check for modified files
id: git-check
run: echo modified=$(if git diff-index --quiet HEAD --; then echo "false"; else echo "true"; fi) >> $GITHUB_OUTPUT
- name: Create Pull Request
if: steps.git-check.outputs.modified == 'true'
uses: peter-evans/create-pull-request@v4
with:
title: Auto-format code with black
labels: meta
commit-message: Auto-format code with black
committer: GitHub <noreply@github.com>
author: explosion-bot <explosion-bot@users.noreply.github.com>
body: _This PR is auto-generated._
branch: autoblack
delete-branch: true
draft: false
- name: Check outputs
if: steps.git-check.outputs.modified == 'true'
run: |
echo "Pull Request Number - ${{ steps.cpr.outputs.pull-request-number }}"
echo "Pull Request URL - ${{ steps.cpr.outputs.pull-request-url }}"

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

@ -8,6 +8,7 @@ on:
jobs:
explosion-bot:
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:
- name: Dump GitHub context

1
.github/workflows/issue-manager.yml vendored
View File

@ -13,6 +13,7 @@ on:
jobs:
issue-manager:
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:
- uses: tiangolo/issue-manager@0.4.0

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

@ -13,6 +13,7 @@ concurrency:
jobs:
action:
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:
- uses: dessant/lock-threads@v4

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

@ -7,6 +7,7 @@ on:
jobs:
build:
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:

179
.github/workflows/tests.yml vendored Normal file
View File

@ -0,0 +1,179 @@
name: tests
on:
push:
branches-ignore:
- "spacy.io"
- "nightly.spacy.io"
- "v2.spacy.io"
paths-ignore:
- "*.md"
- "*.mdx"
- "website/**"
- ".github/workflows/**"
pull_request:
types: [opened, synchronize, reopened, edited]
paths-ignore:
- "*.md"
- "*.mdx"
- "website/**"
jobs:
validate:
name: Validate
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:
- name: Check out repo
uses: actions/checkout@v3
- name: Configure Python version
uses: actions/setup-python@v4
with:
python-version: "3.8"
architecture: x64
- name: black
run: |
python -m pip install black -c requirements.txt
python -m black spacy --check
- name: isort
run: |
python -m pip install isort -c requirements.txt
python -m isort spacy --check
- name: flake8
run: |
python -m pip install flake8==5.0.4
python -m flake8 spacy --count --select=E901,E999,F821,F822,F823,W605 --show-source --statistics
- name: cython-lint
run: |
python -m pip install cython-lint -c requirements.txt
# E501: line too log, W291: trailing whitespace, E266: too many leading '#' for block comment
cython-lint spacy --ignore E501,W291,E266
tests:
name: Test
needs: Validate
strategy:
fail-fast: true
matrix:
os: [ubuntu-latest, windows-latest, macos-latest]
python_version: ["3.11"]
include:
- os: macos-latest
python_version: "3.8"
- os: ubuntu-20.04
python_version: "3.9"
- os: windows-latest
python_version: "3.10"
runs-on: ${{ matrix.os }}
steps:
- name: Check out repo
uses: actions/checkout@v3
- name: Configure Python version
uses: actions/setup-python@v4
with:
python-version: ${{ matrix.python_version }}
architecture: x64
- name: Install dependencies
run: |
python -m pip install -U build pip setuptools
python -m pip install -U -r requirements.txt
- name: Build sdist
run: |
python -m build --sdist
- name: Run mypy
run: |
python -m mypy spacy
- name: Delete source directory and .egg-info
run: |
rm -rf spacy *.egg-info
shell: bash
- name: Uninstall all packages
run: |
python -m pip freeze
python -m pip freeze --exclude pywin32 > installed.txt
python -m pip uninstall -y -r installed.txt
- name: Install from sdist
run: |
SDIST=$(python -c "import os;print(os.listdir('./dist')[-1])" 2>&1)
SPACY_NUM_BUILD_JOBS=2 python -m pip install dist/$SDIST
shell: bash
- name: Test import
run: python -W error -c "import spacy"
# - name: "Test download CLI"
# run: |
# 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')"
# if: matrix.python_version == '3.9'
#
# - name: "Test download_url in info CLI"
# run: |
# python -W error -m spacy info ca_core_news_sm | grep -q download_url
# if: matrix.python_version == '3.9'
#
# - name: "Test no warnings on load (#11713)"
# run: |
# python -W error -c "import ca_core_news_sm; nlp = ca_core_news_sm.load(); doc=nlp('test')"
# if: matrix.python_version == '3.9'
- name: "Test convert CLI"
run: |
python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
if: matrix.python_version == '3.9'
- name: "Test debug config CLI"
run: |
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
if: matrix.python_version == '3.9'
- name: "Test debug data CLI"
run: |
# 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
if: matrix.python_version == '3.9'
- name: "Test train CLI"
run: |
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
if: matrix.python_version == '3.9'
# - name: "Test assemble CLI"
# run: |
# 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
# if: matrix.python_version == '3.9'
#
# - name: "Test assemble CLI vectors warning"
# run: |
# 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
# if: matrix.python_version == '3.9'
- name: "Install test requirements"
run: |
python -m pip install -U -r requirements.txt
- 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: |
python -m pip install 'spacy[apple]'
python -m pytest --pyargs spacy
if: startsWith(matrix.os, 'macos') && matrix.python_version == '3.11'

33
.github/workflows/universe_validation.yml vendored Normal file
View File

@ -0,0 +1,33 @@
name: universe validation
on:
push:
branches-ignore:
- "spacy.io"
- "nightly.spacy.io"
- "v2.spacy.io"
paths:
- "website/meta/universe.json"
pull_request:
types: [opened, synchronize, reopened, edited]
paths:
- "website/meta/universe.json"
jobs:
validate:
name: Validate
if: github.repository_owner == 'explosion'
runs-on: ubuntu-latest
steps:
- name: Check out repo
uses: actions/checkout@v3
- name: Configure Python version
uses: actions/setup-python@v4
with:
python-version: "3.8"
architecture: x64
- name: Validate website/meta/universe.json
run: |
python .github/validate_universe_json.py website/meta/universe.json

2
Makefile
View File

@ -1,7 +1,7 @@
SHELL := /bin/bash
ifndef SPACY_EXTRAS
override SPACY_EXTRAS = spacy-lookups-data==1.0.2 jieba spacy-pkuseg==0.0.28 sudachipy sudachidict_core pymorphy2
override SPACY_EXTRAS = spacy-lookups-data==1.0.3
endif
ifndef PYVER

32
README.md
View File

@ -16,6 +16,9 @@ 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](https://github.com/explosion/spaCy/blob/master/LICENSE).
💥 **We'd love to hear more about your experience with spaCy!**
[Fill out our survey here.](https://form.typeform.com/to/aMel9q9f)
💫 **Version 3.5 out now!**
[Check out the release notes here.](https://github.com/explosion/spaCy/releases)
@ -32,19 +35,20 @@ open-source software, released under the [MIT license](https://github.com/explos
## 📖 Documentation
| Documentation | |
| ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ⭐️ **[spaCy 101]** | New to spaCy? Here's everything you need to know! |
| 📚 **[Usage Guides]** | How to use spaCy and its features. |
| 🚀 **[New in v3.0]** | New features, backwards incompatibilities and migration guide. |
| 🪐 **[Project Templates]** | End-to-end workflows you can clone, modify and run. |
| 🎛 **[API Reference]** | The detailed reference for spaCy's API. |
| 📦 **[Models]** | Download trained pipelines for spaCy. |
| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. |
| 👩‍🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
| 🛠 **[Changelog]** | Changes and version history. |
| 💝 **[Contribute]** | How to contribute to the spaCy project and code base. |
| Documentation | |
| ----------------------------- | ---------------------------------------------------------------------- |
| ⭐️ **[spaCy 101]** | New to spaCy? Here's everything you need to know! |
| 📚 **[Usage Guides]** | How to use spaCy and its features. |
| 🚀 **[New in v3.0]** | New features, backwards incompatibilities and migration guide. |
| 🪐 **[Project Templates]** | End-to-end workflows you can clone, modify and run. |
| 🎛 **[API Reference]** | The detailed reference for spaCy's API. |
| 📦 **[Models]** | Download trained pipelines for spaCy. |
| 🌌 **[Universe]** | Plugins, extensions, demos and books from the spaCy ecosystem. |
| ⚙️ **[spaCy VS Code Extension]** | Additional tooling and features for working with spaCy's config files. |
| 👩‍🏫 **[Online Course]** | Learn spaCy in this free and interactive online course. |
| 📺 **[Videos]** | Our YouTube channel with video tutorials, talks and more. |
| 🛠 **[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)** |
@ -54,13 +58,13 @@ open-source software, released under the [MIT license](https://github.com/explos
[api reference]: https://spacy.io/api/
[models]: https://spacy.io/models
[universe]: https://spacy.io/universe
[spaCy VS Code Extension]: https://github.com/explosion/spacy-vscode
[videos]: https://www.youtube.com/c/ExplosionAI
[online course]: https://course.spacy.io
[project templates]: https://github.com/explosion/projects
[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).

99
azure-pipelines.yml
View File

@ -1,99 +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: "3.8"
- 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"
- job: "Test"
dependsOn: "Validate"
strategy:
matrix:
# We're only running one platform per Python version to speed up builds
# 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
build-constraints.txt
View File

@ -1,6 +1,4 @@
# build version constraints for use with wheelwright + multibuild
numpy==1.15.0; python_version<='3.7' and platform_machine!='aarch64'
numpy==1.19.2; python_version<='3.7' and platform_machine=='aarch64'
numpy==1.17.3; python_version=='3.8' and platform_machine!='aarch64'
numpy==1.19.2; python_version=='3.8' and platform_machine=='aarch64'
numpy==1.19.3; python_version=='3.9'

3
pyproject.toml
View File

@ -9,3 +9,6 @@ requires = [
"numpy>=1.15.0",
]
build-backend = "setuptools.build_meta"
[tool.isort]
profile = "black"

7
requirements.txt
View File

@ -9,7 +9,7 @@ murmurhash>=0.28.0,<1.1.0
wasabi>=0.9.1,<1.2.0
srsly>=2.4.3,<3.0.0
catalogue>=2.0.6,<2.1.0
typer>=0.3.0,<0.8.0
typer>=0.3.0,<0.10.0
pathy>=0.10.0
smart-open>=5.2.1,<7.0.0
# Third party dependencies
@ -30,10 +30,11 @@ pytest-timeout>=1.3.0,<2.0.0
mock>=2.0.0,<3.0.0
flake8>=3.8.0,<6.0.0
hypothesis>=3.27.0,<7.0.0
mypy>=0.990,<1.1.0; platform_machine != "aarch64" and python_version >= "3.7"
types-dataclasses>=0.1.3; python_version < "3.7"
mypy>=0.990,<1.1.0; platform_machine != "aarch64"
types-mock>=0.1.1
types-setuptools>=57.0.0
types-requests
types-setuptools>=57.0.0
black==22.3.0
cython-lint>=0.15.0; python_version >= "3.7"
isort>=5.0,<6.0

46
setup.cfg
View File

@ -30,6 +30,14 @@ project_urls =
zip_safe = false
include_package_data = true
python_requires = >=3.8
setup_requires =
cython>=0.25,<3.0
numpy>=1.15.0
# We also need our Cython packages here to compile against
cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0
murmurhash>=0.28.0,<1.1.0
thinc>=9.0.0.dev2,<9.1.0
install_requires =
# Our libraries
spacy-legacy>=4.0.0.dev0,<4.1.0
@ -42,7 +50,7 @@ install_requires =
srsly>=2.4.3,<3.0.0
catalogue>=2.0.6,<2.1.0
# Third-party dependencies
typer>=0.3.0,<0.8.0
typer>=0.3.0,<0.10.0
pathy>=0.10.0
smart-open>=5.2.1,<7.0.0
tqdm>=4.38.0,<5.0.0
@ -67,41 +75,41 @@ transformers =
ray =
spacy_ray>=0.1.0,<1.0.0
cuda =
cupy>=5.0.0b4,<12.0.0
cupy>=5.0.0b4,<13.0.0
cuda80 =
cupy-cuda80>=5.0.0b4,<12.0.0
cupy-cuda80>=5.0.0b4,<13.0.0
cuda90 =
cupy-cuda90>=5.0.0b4,<12.0.0
cupy-cuda90>=5.0.0b4,<13.0.0
cuda91 =
cupy-cuda91>=5.0.0b4,<12.0.0
cupy-cuda91>=5.0.0b4,<13.0.0
cuda92 =
cupy-cuda92>=5.0.0b4,<12.0.0
cupy-cuda92>=5.0.0b4,<13.0.0
cuda100 =
cupy-cuda100>=5.0.0b4,<12.0.0
cupy-cuda100>=5.0.0b4,<13.0.0
cuda101 =
cupy-cuda101>=5.0.0b4,<12.0.0
cupy-cuda101>=5.0.0b4,<13.0.0
cuda102 =
cupy-cuda102>=5.0.0b4,<12.0.0
cupy-cuda102>=5.0.0b4,<13.0.0
cuda110 =
cupy-cuda110>=5.0.0b4,<12.0.0
cupy-cuda110>=5.0.0b4,<13.0.0
cuda111 =
cupy-cuda111>=5.0.0b4,<12.0.0
cupy-cuda111>=5.0.0b4,<13.0.0
cuda112 =
cupy-cuda112>=5.0.0b4,<12.0.0
cupy-cuda112>=5.0.0b4,<13.0.0
cuda113 =
cupy-cuda113>=5.0.0b4,<12.0.0
cupy-cuda113>=5.0.0b4,<13.0.0
cuda114 =
cupy-cuda114>=5.0.0b4,<12.0.0
cupy-cuda114>=5.0.0b4,<13.0.0
cuda115 =
cupy-cuda115>=5.0.0b4,<12.0.0
cupy-cuda115>=5.0.0b4,<13.0.0
cuda116 =
cupy-cuda116>=5.0.0b4,<12.0.0
cupy-cuda116>=5.0.0b4,<13.0.0
cuda117 =
cupy-cuda117>=5.0.0b4,<12.0.0
cupy-cuda117>=5.0.0b4,<13.0.0
cuda11x =
cupy-cuda11x>=11.0.0,<12.0.0
cupy-cuda11x>=11.0.0,<13.0.0
cuda-autodetect =
cupy-wheel>=11.0.0,<12.0.0
cupy-wheel>=11.0.0,<13.0.0
apple =
thinc-apple-ops>=0.1.0.dev0,<1.0.0
# Language tokenizers with external dependencies

23
spacy/__init__.py
View File

@ -1,6 +1,6 @@
from typing import Union, Iterable, Dict, Any
from pathlib import Path
import sys
from pathlib import Path
from typing import Any, Dict, Iterable, Union
# set library-specific custom warning handling before doing anything else
from .errors import setup_default_warnings
@ -8,20 +8,17 @@ from .errors import setup_default_warnings
setup_default_warnings() # noqa: E402
# These are imported as part of the API
from thinc.api import prefer_gpu, require_gpu, require_cpu # noqa: F401
from thinc.api import Config
from thinc.api import Config, prefer_gpu, require_cpu, require_gpu # noqa: F401
from . import pipeline # noqa: F401
from .cli.info import info # noqa: F401
from .glossary import explain # noqa: F401
from .about import __version__ # noqa: F401
from .util import registry, logger # noqa: F401
from .errors import Errors
from .language import Language
from .vocab import Vocab
from . import util
from .about import __version__ # noqa: F401
from .cli.info import info # noqa: F401
from .errors import Errors
from .glossary import explain # noqa: F401
from .language import Language
from .util import logger, registry # noqa: F401
from .vocab import Vocab
if sys.maxunicode == 65535:
raise SystemError(Errors.E130)

2
spacy/about.py
View File

@ -1,6 +1,6 @@
# fmt: off
__title__ = "spacy"
__version__ = "4.0.0.dev0"
__version__ = "4.0.0.dev1"
__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"

1
spacy/attrs.pxd
View File

@ -1,5 +1,6 @@
from . cimport symbols
cdef enum attr_id_t:
NULL_ATTR = 0
IS_ALPHA = symbols.IS_ALPHA

46
spacy/cli/__init__.py
View File

@ -1,35 +1,35 @@
from wasabi import msg
from ._util import app, setup_cli # noqa: F401
from .apply import apply # noqa: F401
from .assemble import assemble_cli # noqa: F401
# These are the actual functions, NOT the wrapped CLI commands. The CLI commands
# are registered automatically and won't have to be imported here.
from .benchmark_speed import benchmark_speed_cli # noqa: F401
from .download import download # noqa: F401
from .info import info # noqa: F401
from .package import package # noqa: F401
from .profile import profile # noqa: F401
from .train import train_cli # noqa: F401
from .assemble import assemble_cli # noqa: F401
from .pretrain import pretrain # noqa: F401
from .debug_data import debug_data # noqa: F401
from .debug_config import debug_config # noqa: F401
from .debug_model import debug_model # noqa: F401
from .debug_diff import debug_diff # noqa: F401
from .evaluate import evaluate # noqa: F401
from .apply import apply # noqa: F401
from .convert import convert # noqa: F401
from .init_pipeline import init_pipeline_cli # noqa: F401
from .init_config import init_config, fill_config # noqa: F401
from .validate import validate # noqa: F401
from .project.clone import project_clone # noqa: F401
from .project.assets import project_assets # noqa: F401
from .project.run import project_run # noqa: F401
from .project.dvc import project_update_dvc # noqa: F401
from .project.push import project_push # noqa: F401
from .project.pull import project_pull # noqa: F401
from .project.document import project_document # noqa: F401
from .debug_config import debug_config # noqa: F401
from .debug_data import debug_data # noqa: F401
from .debug_diff import debug_diff # noqa: F401
from .debug_model import debug_model # noqa: F401
from .download import download # noqa: F401
from .evaluate import evaluate # noqa: F401
from .find_threshold import find_threshold # noqa: F401
from .info import info # noqa: F401
from .init_config import fill_config, init_config # noqa: F401
from .init_pipeline import init_pipeline_cli # noqa: F401
from .package import package # noqa: F401
from .pretrain import pretrain # noqa: F401
from .profile import profile # noqa: F401
from .project.assets import project_assets # noqa: F401
from .project.clone import project_clone # noqa: F401
from .project.document import project_document # noqa: F401
from .project.dvc import project_update_dvc # noqa: F401
from .project.pull import project_pull # noqa: F401
from .project.push import project_push # noqa: F401
from .project.run import project_run # noqa: F401
from .train import train_cli # noqa: F401
from .validate import validate # noqa: F401
@app.command("link", no_args_is_help=True, deprecated=True, hidden=True)

49
spacy/cli/_util.py
View File

@ -1,26 +1,45 @@
from typing import Dict, Any, Union, List, Optional, Tuple, Iterable, Literal
from typing import TYPE_CHECKING, overload
import sys
import shutil
from pathlib import Path
from wasabi import msg, Printer
import srsly
import hashlib
import os
import shutil
import sys
from configparser import InterpolationError
from contextlib import contextmanager
from pathlib import Path
from typing import (
TYPE_CHECKING,
Any,
Dict,
Iterable,
List,
Literal,
Optional,
Tuple,
Union,
overload,
)
import srsly
import typer
from click import NoSuchOption
from click.parser import split_arg_string
from typer.main import get_command
from contextlib import contextmanager
from thinc.api import Config, ConfigValidationError, require_gpu
from thinc.util import gpu_is_available
from configparser import InterpolationError
import os
from typer.main import get_command
from wasabi import Printer, msg
from ..schemas import ProjectConfigSchema, validate
from ..util import import_file, run_command, make_tempdir, registry, logger
from ..util import is_compatible_version, SimpleFrozenDict, ENV_VARS
from ..errors import RENAMED_LANGUAGE_CODES
from .. import about
from ..errors import RENAMED_LANGUAGE_CODES
from ..schemas import ProjectConfigSchema, validate
from ..util import (
ENV_VARS,
SimpleFrozenDict,
import_file,
is_compatible_version,
logger,
make_tempdir,
registry,
run_command,
)
if TYPE_CHECKING:
from pathy import FluidPath # noqa: F401

13
spacy/cli/apply.py
View File

@ -1,18 +1,15 @@
import tqdm
import srsly
from itertools import chain
from pathlib import Path
from typing import Optional, List, Iterable, cast, Union
from typing import Iterable, List, Optional, Union, cast
import srsly
import tqdm
from wasabi import msg
from ._util import app, Arg, Opt, setup_gpu, import_code, walk_directory
from ..tokens import Doc, DocBin
from ..vocab import Vocab
from ..util import ensure_path, load_model
from ..vocab import Vocab
from ._util import Arg, Opt, app, import_code, setup_gpu, walk_directory
path_help = """Location of the documents to predict on.
Can be a single file in .spacy format or a .jsonl file.

19
spacy/cli/assemble.py
View File

@ -1,13 +1,20 @@
from typing import Optional
from pathlib import Path
from wasabi import msg
import typer
import logging
from pathlib import Path
from typing import Optional
import typer
from wasabi import msg
from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
from ._util import import_code
from .. import util
from ..util import get_sourced_components, load_model_from_config
from ._util import (
Arg,
Opt,
app,
import_code,
parse_config_overrides,
show_validation_error,
)
@app.command(

11
spacy/cli/benchmark_speed.py
View File

@ -1,11 +1,12 @@
from typing import Iterable, List, Optional
import random
from itertools import islice
import numpy
from pathlib import Path
import time
from tqdm import tqdm
from itertools import islice
from pathlib import Path
from typing import Iterable, List, Optional
import numpy
import typer
from tqdm import tqdm
from wasabi import msg
from .. import util

26
spacy/cli/convert.py
View File

@ -1,18 +1,22 @@
from typing import Callable, Iterable, Mapping, Optional, Any, Union
from enum import Enum
from pathlib import Path
from wasabi import Printer
import srsly
import itertools
import re
import sys
import itertools
from enum import Enum
from pathlib import Path
from typing import Any, Callable, Iterable, Mapping, Optional, Union
import srsly
from wasabi import Printer
from ._util import app, Arg, Opt, _handle_renamed_language_codes, walk_directory
from ..training import docs_to_json
from ..tokens import Doc, DocBin
from ..training.converters import iob_to_docs, conll_ner_to_docs, json_to_docs
from ..training.converters import conllu_to_docs
from ..training import docs_to_json
from ..training.converters import (
conll_ner_to_docs,
conllu_to_docs,
iob_to_docs,
json_to_docs,
)
from ._util import Arg, Opt, _handle_renamed_language_codes, app, walk_directory
# Converters are matched by file extension except for ner/iob, which are
# matched by file extension and content. To add a converter, add a new

19
spacy/cli/debug_config.py
View File

@ -1,15 +1,22 @@
from typing import Optional, Dict, Any, Union, List
from pathlib import Path
from wasabi import msg, table
from typing import Any, Dict, List, Optional, Union
import typer
from thinc.api import Config
from thinc.config import VARIABLE_RE
import typer
from wasabi import msg, table
from ._util import Arg, Opt, show_validation_error, parse_config_overrides
from ._util import import_code, debug_cli
from .. import util
from ..schemas import ConfigSchemaInit, ConfigSchemaTraining
from ..util import registry
from .. import util
from ._util import (
Arg,
Opt,
debug_cli,
import_code,
parse_config_overrides,
show_validation_error,
)
@debug_cli.command(

76
spacy/cli/debug_data.py
View File

@ -1,29 +1,49 @@
from typing import Any, Dict, Iterable, List, Optional, Sequence, Set, Tuple, Union
from typing import Literal, cast, overload
from pathlib import Path
from collections import Counter
import sys
import srsly
from wasabi import Printer, MESSAGES, msg
import typer
import math
import sys
from collections import Counter
from pathlib import Path
from typing import (
Any,
Dict,
Iterable,
List,
Literal,
Optional,
Sequence,
Set,
Tuple,
Union,
cast,
overload,
)
from ._util import app, Arg, Opt, show_validation_error, parse_config_overrides
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
import numpy
import srsly
import typer
from wasabi import MESSAGES, Printer, msg
from .. import util
from ..language import Language
from ..morphology import Morphology
from ..pipeline import Morphologizer, SpanCategorizer, TrainablePipe
from ..pipeline._edit_tree_internals.edit_trees import EditTrees
from ..pipeline._parser_internals import nonproj
from ..pipeline._parser_internals.nonproj import DELIMITER
from ..pipeline import Morphologizer, SpanCategorizer
from ..pipeline._edit_tree_internals.edit_trees import EditTrees
from ..morphology import Morphology
from ..language import Language
from ..schemas import ConfigSchemaTraining
from ..training import Example, remove_bilu_prefix
from ..training.initialize import get_sourced_components
from ..util import registry, resolve_dot_names
from ..vectors import Mode as VectorsMode
from .. import util
from ._util import (
Arg,
Opt,
_format_number,
app,
debug_cli,
import_code,
parse_config_overrides,
show_validation_error,
)
# Minimum number of expected occurrences of NER label in data to train new label
NEW_LABEL_THRESHOLD = 50
@ -210,7 +230,7 @@ def debug_data(
else:
msg.info("No word vectors present in the package")
if "spancat" in factory_names:
if "spancat" in factory_names or "spancat_singlelabel" in factory_names:
model_labels_spancat = _get_labels_from_spancat(nlp)
has_low_data_warning = False
has_no_neg_warning = False
@ -335,7 +355,7 @@ 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
@ -520,9 +540,13 @@ def debug_data(
if "tagger" in factory_names:
msg.divider("Part-of-speech Tagging")
label_list = [label for label in gold_train_data["tags"]]
model_labels = _get_labels_from_model(nlp, "tagger")
label_list, counts = zip(*gold_train_data["tags"].items())
msg.info(f"{len(label_list)} label(s) in train data")
p = numpy.array(counts)
p = p / p.sum()
norm_entropy = (-p * numpy.log2(p)).sum() / numpy.log2(len(label_list))
msg.info(f"{norm_entropy} is the normalised label entropy")
model_labels = _get_labels_from_model(nlp, "tagger")
labels = set(label_list)
missing_labels = model_labels - labels
if missing_labels:
@ -824,7 +848,7 @@ def _compile_gold(
data["boundary_cross_ents"] += 1
elif label == "-":
data["ner"]["-"] += 1
if "spancat" in factory_names:
if "spancat" in factory_names or "spancat_singlelabel" in factory_names:
for spans_key in list(eg.reference.spans.keys()):
# Obtain the span frequency
if spans_key not in data["spancat"]:
@ -1022,7 +1046,7 @@ def _get_labels_from_spancat(nlp: Language) -> Dict[str, Set[str]]:
pipe_names = [
pipe_name
for pipe_name in nlp.pipe_names
if nlp.get_pipe_meta(pipe_name).factory == "spancat"
if nlp.get_pipe_meta(pipe_name).factory in ("spancat", "spancat_singlelabel")
]
labels: Dict[str, Set[str]] = {}
for pipe_name in pipe_names:

8
spacy/cli/debug_diff.py
View File

@ -1,13 +1,13 @@
from pathlib import Path
from typing import Optional
import typer
from wasabi import Printer, diff_strings, MarkdownRenderer
from pathlib import Path
from thinc.api import Config
from wasabi import MarkdownRenderer, Printer, diff_strings
from ._util import debug_cli, Arg, Opt, show_validation_error, parse_config_overrides
from ..util import load_config
from .init_config import init_config, Optimizations
from ._util import Arg, Opt, debug_cli, parse_config_overrides, show_validation_error
from .init_config import Optimizations, init_config
@debug_cli.command(

31
spacy/cli/debug_model.py
View File

@ -1,19 +1,32 @@
from typing import Dict, Any, Optional
from pathlib import Path
import itertools
from pathlib import Path
from typing import Any, Dict, Optional
import typer
from thinc.api import (
Model,
data_validation,
fix_random_seed,
set_dropout_rate,
set_gpu_allocator,
)
from wasabi import msg
from spacy.training import Example
from spacy.util import resolve_dot_names
from wasabi import msg
from thinc.api import fix_random_seed, set_dropout_rate
from thinc.api import Model, data_validation, set_gpu_allocator
import typer
from ._util import Arg, Opt, debug_cli, show_validation_error
from ._util import parse_config_overrides, string_to_list, setup_gpu
from .. import util
from ..schemas import ConfigSchemaTraining
from ..util import registry
from .. import util
from ._util import (
Arg,
Opt,
debug_cli,
parse_config_overrides,
setup_gpu,
show_validation_error,
string_to_list,
)
@debug_cli.command(

25
spacy/cli/download.py
View File

@ -1,14 +1,20 @@
from typing import Optional, Sequence
import requests
import sys
from wasabi import msg
import typer
from typing import Optional, Sequence
import requests
import typer
from wasabi import msg
from ._util import app, Arg, Opt, WHEEL_SUFFIX, SDIST_SUFFIX
from .. import about
from ..util import is_package, get_minor_version, run_command
from ..util import is_prerelease_version, get_installed_models
from ..util import get_package_version
from ..util import (
get_installed_models,
get_minor_version,
get_package_version,
is_package,
is_prerelease_version,
run_command,
)
from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app
@app.command(
@ -83,11 +89,8 @@ 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

109
spacy/cli/evaluate.py
View File

@ -1,16 +1,16 @@
from typing import Optional, List, Dict, Any, Union
from wasabi import Printer
from pathlib import Path
import re
from pathlib import Path
from typing import Any, Dict, List, Optional, Union
import srsly
from thinc.api import fix_random_seed
from wasabi import Printer
from ..training import Corpus
from ..tokens import Doc
from ._util import app, Arg, Opt, setup_gpu, import_code, benchmark_cli
from .. import displacy, util
from ..scorer import Scorer
from .. import util
from .. import displacy
from ..tokens import Doc
from ..training import Corpus
from ._util import Arg, Opt, app, benchmark_cli, import_code, setup_gpu
@benchmark_cli.command(
@ -27,6 +27,7 @@ def evaluate_cli(
gold_preproc: bool = Opt(False, "--gold-preproc", "-G", help="Use gold preprocessing"),
displacy_path: Optional[Path] = Opt(None, "--displacy-path", "-dp", help="Directory to output rendered parses as HTML", exists=True, file_okay=False),
displacy_limit: int = Opt(25, "--displacy-limit", "-dl", help="Limit of parses to render as HTML"),
per_component: bool = Opt(False, "--per-component", "-P", help="Return scores per component, only applicable when an output JSON file is specified."),
# fmt: on
):
"""
@ -50,6 +51,7 @@ def evaluate_cli(
gold_preproc=gold_preproc,
displacy_path=displacy_path,
displacy_limit=displacy_limit,
per_component=per_component,
silent=False,
)
@ -64,6 +66,7 @@ def evaluate(
displacy_limit: int = 25,
silent: bool = True,
spans_key: str = "sc",
per_component: bool = False,
) -> Dict[str, Any]:
msg = Printer(no_print=silent, pretty=not silent)
fix_random_seed()
@ -78,50 +81,61 @@ def evaluate(
corpus = Corpus(data_path, gold_preproc=gold_preproc)
nlp = util.load_model(model)
dev_dataset = list(corpus(nlp))
scores = nlp.evaluate(dev_dataset)
metrics = {
"TOK": "token_acc",
"TAG": "tag_acc",
"POS": "pos_acc",
"MORPH": "morph_acc",
"LEMMA": "lemma_acc",
"UAS": "dep_uas",
"LAS": "dep_las",
"NER P": "ents_p",
"NER R": "ents_r",
"NER F": "ents_f",
"TEXTCAT": "cats_score",
"SENT P": "sents_p",
"SENT R": "sents_r",
"SENT F": "sents_f",
"SPAN P": f"spans_{spans_key}_p",
"SPAN R": f"spans_{spans_key}_r",
"SPAN F": f"spans_{spans_key}_f",
"SPEED": "speed",
}
results = {}
data = {}
for metric, key in metrics.items():
if key in scores:
if key == "cats_score":
metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
if isinstance(scores[key], (int, float)):
if key == "speed":
results[metric] = f"{scores[key]:.0f}"
scores = nlp.evaluate(dev_dataset, per_component=per_component)
if per_component:
data = scores
if output is None:
msg.warn(
"The per-component option is enabled but there is no output JSON file provided to save the scores to."
)
else:
msg.info("Per-component scores will be saved to output JSON file.")
else:
metrics = {
"TOK": "token_acc",
"TAG": "tag_acc",
"POS": "pos_acc",
"MORPH": "morph_acc",
"LEMMA": "lemma_acc",
"UAS": "dep_uas",
"LAS": "dep_las",
"NER P": "ents_p",
"NER R": "ents_r",
"NER F": "ents_f",
"TEXTCAT": "cats_score",
"SENT P": "sents_p",
"SENT R": "sents_r",
"SENT F": "sents_f",
"SPAN P": f"spans_{spans_key}_p",
"SPAN R": f"spans_{spans_key}_r",
"SPAN F": f"spans_{spans_key}_f",
"SPEED": "speed",
}
results = {}
data = {}
for metric, key in metrics.items():
if key in scores:
if key == "cats_score":
metric = metric + " (" + scores.get("cats_score_desc", "unk") + ")"
if isinstance(scores[key], (int, float)):
if key == "speed":
results[metric] = f"{scores[key]:.0f}"
else:
results[metric] = f"{scores[key]*100:.2f}"
else:
results[metric] = f"{scores[key]*100:.2f}"
else:
results[metric] = "-"
data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
results[metric] = "-"
data[re.sub(r"[\s/]", "_", key.lower())] = scores[key]
msg.table(results, title="Results")
data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent)
msg.table(results, title="Results")
data = handle_scores_per_type(scores, data, spans_key=spans_key, silent=silent)
if displacy_path:
factory_names = [nlp.get_pipe_meta(pipe).factory for pipe in nlp.pipe_names]
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 +143,7 @@ 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 +197,7 @@ 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 +211,11 @@ 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

14
spacy/cli/find_threshold.py
View File

@ -1,17 +1,17 @@
import functools
import logging
import operator
from pathlib import Path
import logging
from typing import Optional, Tuple, Any, Dict, List
from typing import Any, Dict, List, Optional, Tuple
import numpy
import wasabi.tables
from ..pipeline import TextCategorizer, MultiLabel_TextCategorizer
from ..errors import Errors
from ..training import Corpus
from ._util import app, Arg, Opt, import_code, setup_gpu
from .. import util
from ..errors import Errors
from ..pipeline import MultiLabel_TextCategorizer, TextCategorizer
from ..training import Corpus
from ._util import Arg, Opt, app, import_code, setup_gpu
_DEFAULTS = {
"n_trials": 11,
@ -35,7 +35,7 @@ def find_threshold_cli(
code_path: Optional[Path] = Opt(None, "--code", "-c", help="Path to Python file with additional code (registered functions) to be imported"),
use_gpu: int = Opt(_DEFAULTS["use_gpu"], "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
gold_preproc: bool = Opt(_DEFAULTS["gold_preproc"], "--gold-preproc", "-G", help="Use gold preprocessing"),
verbose: bool = Opt(False, "--silent", "-V", "-VV", help="Display more information for debugging purposes"),
verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
# fmt: on
):
"""

20
spacy/cli/info.py
View File

@ -1,15 +1,15 @@
from typing import Optional, Dict, Any, Union, List
import platform
import json
from pathlib import Path
from wasabi import Printer, MarkdownRenderer
import srsly
import importlib.metadata
import json
import platform
from pathlib import Path
from typing import Any, Dict, List, Optional, Union
from ._util import app, Arg, Opt, string_to_list
from .download import get_model_filename, get_latest_version
from .. import util
from .. import about
import srsly
from wasabi import MarkdownRenderer, Printer
from .. import about, util
from ._util import Arg, Opt, app, string_to_list
from .download import get_latest_version, get_model_filename
@app.command("info")

22
spacy/cli/init_config.py
View File

@ -1,19 +1,27 @@
from typing import Optional, List, Tuple
import re
from enum import Enum
from pathlib import Path
from wasabi import Printer, diff_strings
from thinc.api import Config
from typing import List, Optional, Tuple
import srsly
import re
from jinja2 import Template
from thinc.api import Config
from wasabi import Printer, diff_strings
from .. import util
from ..language import DEFAULT_CONFIG_DISTILL_PATH, DEFAULT_CONFIG_PRETRAIN_PATH
from ..schemas import RecommendationSchema
from ..util import SimpleFrozenList
from ._util import init_cli, Arg, Opt, show_validation_error, COMMAND
from ._util import string_to_list, import_code, _handle_renamed_language_codes
from ._util import (
COMMAND,
Arg,
Opt,
_handle_renamed_language_codes,
import_code,
init_cli,
show_validation_error,
string_to_list,
)
ROOT = Path(__file__).parent / "templates"
TEMPLATE_PATH = ROOT / "quickstart_training.jinja"

23
spacy/cli/init_pipeline.py
View File

@ -1,15 +1,24 @@
from typing import Optional
import logging
from pathlib import Path
from wasabi import msg
import typer
from typing import Optional
import srsly
import typer
from wasabi import msg
from .. import util
from ..training.initialize import init_nlp, convert_vectors
from ..language import Language
from ._util import init_cli, Arg, Opt, parse_config_overrides, show_validation_error
from ._util import import_code, setup_gpu, _handle_renamed_language_codes
from ..training.initialize import convert_vectors, init_nlp
from ._util import (
Arg,
Opt,
_handle_renamed_language_codes,
import_code,
init_cli,
parse_config_overrides,
setup_gpu,
show_validation_error,
)
@init_cli.command("vectors")
@ -23,6 +32,7 @@ def init_vectors_cli(
mode: str = Opt("default", "--mode", "-m", help="Vectors mode: default or floret"),
verbose: bool = Opt(False, "--verbose", "-V", "-VV", help="Display more information for debugging purposes"),
jsonl_loc: Optional[Path] = Opt(None, "--lexemes-jsonl", "-j", help="Location of JSONL-formatted attributes file", hidden=True),
attr: str = Opt("ORTH", "--attr", "-a", help="Optional token attribute to use for vectors, e.g. LOWER or NORM"),
# fmt: on
):
"""Convert word vectors for use with spaCy. Will export an nlp object that
@ -44,6 +54,7 @@ def init_vectors_cli(
truncate=truncate,
prune=prune,
mode=mode,
attr=attr,
)
msg.good(f"Successfully converted {len(nlp.vocab.vectors)} vectors")
nlp.to_disk(output_dir)

26
spacy/cli/package.py
View File

@ -1,18 +1,18 @@
from typing import Optional, Union, Any, Dict, List, Tuple, cast
import shutil
from pathlib import Path
from wasabi import Printer, MarkdownRenderer, get_raw_input
from thinc.api import Config
from collections import defaultdict
from catalogue import RegistryError
import srsly
import sys
import re
import shutil
import sys
from collections import defaultdict
from pathlib import Path
from typing import Any, Dict, List, Optional, Tuple, Union, cast
from ._util import app, Arg, Opt, string_to_list, WHEEL_SUFFIX, SDIST_SUFFIX
from ..schemas import validate, ModelMetaSchema
from .. import util
from .. import about
import srsly
from catalogue import RegistryError
from thinc.api import Config
from wasabi import MarkdownRenderer, Printer, get_raw_input
from .. import about, util
from ..schemas import ModelMetaSchema, validate
from ._util import SDIST_SUFFIX, WHEEL_SUFFIX, Arg, Opt, app, string_to_list
@app.command("package")

22
spacy/cli/pretrain.py
View File

@ -1,13 +1,21 @@
from typing import Optional
from pathlib import Path
from wasabi import msg
import typer
import re
from pathlib import Path
from typing import Optional
import typer
from wasabi import msg
from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
from ._util import import_code, setup_gpu
from ..training.pretrain import pretrain
from ..util import load_config
from ._util import (
Arg,
Opt,
app,
import_code,
parse_config_overrides,
setup_gpu,
show_validation_error,
)
@app.command(
@ -23,6 +31,7 @@ def pretrain_cli(
resume_path: Optional[Path] = Opt(None, "--resume-path", "-r", help="Path to pretrained weights from which to resume pretraining"),
epoch_resume: Optional[int] = Opt(None, "--epoch-resume", "-er", help="The epoch to resume counting from when using --resume-path. Prevents unintended overwriting of existing weight files."),
use_gpu: int = Opt(-1, "--gpu-id", "-g", help="GPU ID or -1 for CPU"),
skip_last: bool = Opt(False, "--skip-last", "-L", help="Skip saving model-last.bin"),
# fmt: on
):
"""
@ -74,6 +83,7 @@ def pretrain_cli(
epoch_resume=epoch_resume,
use_gpu=use_gpu,
silent=False,
skip_last=skip_last,
)
msg.good("Successfully finished pretrain")

17
spacy/cli/profile.py
View File

@ -1,17 +1,18 @@
from typing import Optional, Sequence, Union, Iterator
import tqdm
from pathlib import Path
import srsly
import cProfile
import itertools
import pstats
import sys
import itertools
from wasabi import msg, Printer
import typer
from pathlib import Path
from typing import Iterator, Optional, Sequence, Union
import srsly
import tqdm
import typer
from wasabi import Printer, msg
from ._util import app, debug_cli, Arg, Opt, NAME
from ..language import Language
from ..util import load_model
from ._util import NAME, Arg, Opt, app, debug_cli
@debug_cli.command("profile")

23
spacy/cli/project/assets.py
View File

@ -1,16 +1,27 @@
from typing import Any, Dict, Optional
from pathlib import Path
from wasabi import msg
import os
import re
import shutil
from pathlib import Path
from typing import Any, Dict, Optional
import requests
import typer
from wasabi import msg
from ...util import ensure_path, working_dir
from .._util import project_cli, Arg, Opt, PROJECT_FILE, load_project_config
from .._util import get_checksum, download_file, git_checkout, get_git_version
from .._util import SimpleFrozenDict, parse_config_overrides
from .._util import (
PROJECT_FILE,
Arg,
Opt,
SimpleFrozenDict,
download_file,
get_checksum,
get_git_version,
git_checkout,
load_project_config,
parse_config_overrides,
project_cli,
)
# Whether assets are extra if `extra` is not set.
EXTRA_DEFAULT = False

21
spacy/cli/project/clone.py
View File

@ -1,13 +1,22 @@
from typing import Optional
from pathlib import Path
from wasabi import msg
import subprocess
import re
import subprocess
from pathlib import Path
from typing import Optional
from wasabi import msg
from ... import about
from ...util import ensure_path
from .._util import project_cli, Arg, Opt, COMMAND, PROJECT_FILE
from .._util import git_checkout, get_git_version, git_repo_branch_exists
from .._util import (
COMMAND,
PROJECT_FILE,
Arg,
Opt,
get_git_version,
git_checkout,
git_repo_branch_exists,
project_cli,
)
DEFAULT_REPO = about.__projects__
DEFAULT_PROJECTS_BRANCH = about.__projects_branch__

6
spacy/cli/project/document.py
View File

@ -1,9 +1,9 @@
from pathlib import Path
from wasabi import msg, MarkdownRenderer
from wasabi import MarkdownRenderer, msg
from ...util import working_dir
from .._util import project_cli, Arg, Opt, PROJECT_FILE, load_project_config
from .._util import PROJECT_FILE, Arg, Opt, load_project_config, project_cli
DOCS_URL = "https://spacy.io"
INTRO_PROJECT = f"""The [`{PROJECT_FILE}`]({PROJECT_FILE}) defines the data assets required by the

25
spacy/cli/project/dvc.py
View File

@ -1,15 +1,28 @@
"""This module contains helpers and subcommands for integrating spaCy projects
with Data Version Controk (DVC). https://dvc.org"""
from typing import Dict, Any, List, Optional, Iterable
import subprocess
from pathlib import Path
from typing import Any, Dict, Iterable, List, Optional
from wasabi import msg
from .._util import PROJECT_FILE, load_project_config, get_hash, project_cli
from .._util import Arg, Opt, NAME, COMMAND
from ...util import working_dir, split_command, join_command, run_command
from ...util import SimpleFrozenList
from ...util import (
SimpleFrozenList,
join_command,
run_command,
split_command,
working_dir,
)
from .._util import (
COMMAND,
NAME,
PROJECT_FILE,
Arg,
Opt,
get_hash,
load_project_config,
project_cli,
)
DVC_CONFIG = "dvc.yaml"
DVC_DIR = ".dvc"

8
spacy/cli/project/pull.py
View File

@ -1,9 +1,9 @@
from pathlib import Path
from wasabi import msg
from .remote_storage import RemoteStorage
from .remote_storage import get_command_hash
from .._util import project_cli, Arg, logger
from .._util import load_project_config
from .._util import Arg, load_project_config, logger, project_cli
from .remote_storage import RemoteStorage, get_command_hash
from .run import update_lockfile

8
spacy/cli/project/push.py
View File

@ -1,9 +1,9 @@
from pathlib import Path
from wasabi import msg
from .remote_storage import RemoteStorage
from .remote_storage import get_content_hash, get_command_hash
from .._util import load_project_config
from .._util import project_cli, Arg, logger
from .._util import Arg, load_project_config, logger, project_cli
from .remote_storage import RemoteStorage, get_command_hash, get_content_hash
@project_cli.command("push")

21
spacy/cli/project/remote_storage.py
View File

@ -1,18 +1,25 @@
from typing import Optional, List, Dict, TYPE_CHECKING
import hashlib
import os
import site
import hashlib
import urllib.parse
import tarfile
import urllib.parse
from pathlib import Path
from typing import TYPE_CHECKING, Dict, List, Optional
from wasabi import msg
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
from ...git_info import GIT_VERSION
from ...util import ENV_VARS, check_bool_env_var, get_minor_version
from .._util import (
download_file,
ensure_pathy,
get_checksum,
get_hash,
make_tempdir,
upload_file,
)
if TYPE_CHECKING:
from pathy import FluidPath # noqa: F401

39
spacy/cli/project/run.py
View File

@ -1,20 +1,39 @@
from typing import Optional, List, Dict, Sequence, Any, Iterable, Tuple
import os.path
from pathlib import Path
from wasabi import msg
from wasabi.util import locale_escape
import sys
from pathlib import Path
from typing import Any, Dict, Iterable, List, Optional, Sequence, Tuple
import srsly
import typer
from wasabi import msg
from wasabi.util import locale_escape
from ... import about
from ...git_info import GIT_VERSION
from ...util import working_dir, run_command, split_command, is_cwd, join_command
from ...util import SimpleFrozenList, is_minor_version_match, ENV_VARS
from ...util import check_bool_env_var, SimpleFrozenDict
from .._util import PROJECT_FILE, PROJECT_LOCK, load_project_config, get_hash
from .._util import get_checksum, project_cli, Arg, Opt, COMMAND, parse_config_overrides
from ...util import (
ENV_VARS,
SimpleFrozenDict,
SimpleFrozenList,
check_bool_env_var,
is_cwd,
is_minor_version_match,
join_command,
run_command,
split_command,
working_dir,
)
from .._util import (
COMMAND,
PROJECT_FILE,
PROJECT_LOCK,
Arg,
Opt,
get_checksum,
get_hash,
load_project_config,
parse_config_overrides,
project_cli,
)
@project_cli.command(

137
spacy/cli/templates/quickstart_training.jinja
View File

@ -3,7 +3,7 @@ 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" 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"] -%}
{%- set listener_components = ["tagger", "morphologizer", "parser", "ner", "textcat", "textcat_multilabel", "entity_linker", "span_finder", "spancat", "spancat_singlelabel", "trainable_lemmatizer"] -%}
[paths]
train = null
dev = null
@ -24,8 +24,11 @@ gpu_allocator = null
lang = "{{ lang }}"
{%- set has_textcat = ("textcat" in components or "textcat_multilabel" in components) -%}
{%- set with_accuracy = optimize == "accuracy" -%}
{%- set has_accurate_textcat = has_textcat and with_accuracy -%}
{%- if ("tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "spancat" in components or "trainable_lemmatizer" in components or "entity_linker" in components or has_accurate_textcat) -%}
{# The BOW textcat doesn't need a source of features, so it can omit the
tok2vec/transformer. #}
{%- set with_accuracy_or_transformer = (use_transformer or with_accuracy) -%}
{%- set textcat_needs_features = has_textcat and with_accuracy_or_transformer -%}
{%- if ("tagger" in components or "morphologizer" in components or "parser" in components or "ner" in components or "span_finder" in components or "spancat" in components or "spancat_singlelabel" in components or "trainable_lemmatizer" in components or "entity_linker" in components or textcat_needs_features) -%}
{%- set full_pipeline = ["transformer" if use_transformer else "tok2vec"] + components -%}
{%- else -%}
{%- set full_pipeline = components -%}
@ -122,6 +125,30 @@ grad_factor = 1.0
@layers = "reduce_mean.v1"
{% endif -%}
{% if "span_finder" in components -%}
[components.span_finder]
factory = "span_finder"
max_length = 25
min_length = null
scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
spans_key = "sc"
threshold = 0.5
[components.span_finder.model]
@architectures = "spacy.SpanFinder.v1"
[components.span_finder.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = 2
[components.span_finder.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.span_finder.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
{% endif -%}
{% if "spancat" in components -%}
[components.spancat]
factory = "spancat"
@ -154,6 +181,36 @@ grad_factor = 1.0
sizes = [1,2,3]
{% endif -%}
{% if "spancat_singlelabel" in components %}
[components.spancat_singlelabel]
factory = "spancat_singlelabel"
negative_weight = 1.0
allow_overlap = true
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = "sc"
[components.spancat_singlelabel.model]
@architectures = "spacy.SpanCategorizer.v1"
[components.spancat_singlelabel.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128
[components.spancat_singlelabel.model.scorer]
@layers = "Softmax.v2"
[components.spancat_singlelabel.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.spancat_singlelabel.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
[components.spancat_singlelabel.suggester]
@misc = "spacy.ngram_suggester.v1"
sizes = [1,2,3]
{% endif %}
{% if "trainable_lemmatizer" in components -%}
[components.trainable_lemmatizer]
factory = "trainable_lemmatizer"
@ -219,10 +276,16 @@ no_output_layer = false
{% else -%}
[components.textcat.model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatCNN.v2"
exclusive_classes = true
ngram_size = 1
no_output_layer = false
nO = null
[components.textcat.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.textcat.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
{%- endif %}
{%- endif %}
@ -250,10 +313,16 @@ no_output_layer = false
{% else -%}
[components.textcat_multilabel.model]
@architectures = "spacy.TextCatBOW.v2"
@architectures = "spacy.TextCatCNN.v2"
exclusive_classes = false
ngram_size = 1
no_output_layer = false
nO = null
[components.textcat_multilabel.model.tok2vec]
@architectures = "spacy-transformers.TransformerListener.v1"
grad_factor = 1.0
[components.textcat_multilabel.model.tok2vec.pooling]
@layers = "reduce_mean.v1"
{%- endif %}
{%- endif %}
@ -284,6 +353,7 @@ maxout_pieces = 3
{% if "morphologizer" in components %}
[components.morphologizer]
factory = "morphologizer"
label_smoothing = 0.05
[components.morphologizer.model]
@architectures = "spacy.Tagger.v2"
@ -297,6 +367,7 @@ width = ${components.tok2vec.model.encode.width}
{% if "tagger" in components %}
[components.tagger]
factory = "tagger"
label_smoothing = 0.05
[components.tagger.model]
@architectures = "spacy.Tagger.v2"
@ -341,6 +412,27 @@ nO = null
width = ${components.tok2vec.model.encode.width}
{% endif %}
{% if "span_finder" in components %}
[components.span_finder]
factory = "span_finder"
max_length = 25
min_length = null
scorer = {"@scorers":"spacy.span_finder_scorer.v1"}
spans_key = "sc"
threshold = 0.5
[components.span_finder.model]
@architectures = "spacy.SpanFinder.v1"
[components.span_finder.model.scorer]
@layers = "spacy.LinearLogistic.v1"
nO = 2
[components.span_finder.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
{% endif %}
{% if "spancat" in components %}
[components.spancat]
factory = "spancat"
@ -370,6 +462,33 @@ width = ${components.tok2vec.model.encode.width}
sizes = [1,2,3]
{% endif %}
{% if "spancat_singlelabel" in components %}
[components.spancat_singlelabel]
factory = "spancat_singlelabel"
negative_weight = 1.0
allow_overlap = true
scorer = {"@scorers":"spacy.spancat_scorer.v1"}
spans_key = "sc"
[components.spancat_singlelabel.model]
@architectures = "spacy.SpanCategorizer.v1"
[components.spancat_singlelabel.model.reducer]
@layers = "spacy.mean_max_reducer.v1"
hidden_size = 128
[components.spancat_singlelabel.model.scorer]
@layers = "Softmax.v2"
[components.spancat_singlelabel.model.tok2vec]
@architectures = "spacy.Tok2VecListener.v1"
width = ${components.tok2vec.model.encode.width}
[components.spancat_singlelabel.suggester]
@misc = "spacy.ngram_suggester.v1"
sizes = [1,2,3]
{% endif %}
{% if "trainable_lemmatizer" in components -%}
[components.trainable_lemmatizer]
factory = "trainable_lemmatizer"

24
spacy/cli/train.py
View File

@ -1,15 +1,23 @@
from typing import Optional, Dict, Any, Union
from pathlib import Path
from wasabi import msg
import typer
import logging
import sys
from pathlib import Path
from typing import Any, Dict, Optional, Union
import typer
from wasabi import msg
from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
from ._util import import_code, setup_gpu
from ..training.loop import train as train_nlp
from ..training.initialize import init_nlp
from .. import util
from ..training.initialize import init_nlp
from ..training.loop import train as train_nlp
from ._util import (
Arg,
Opt,
app,
import_code,
parse_config_overrides,
setup_gpu,
show_validation_error,
)
@app.command(

21
spacy/cli/validate.py
View File

@ -1,14 +1,21 @@
from typing import Tuple
from pathlib import Path
import sys
import requests
from wasabi import msg, Printer
import warnings
from pathlib import Path
from typing import Tuple
import requests
from wasabi import Printer, msg
from ._util import app
from .. import about
from ..util import get_package_version, get_installed_models, get_minor_version
from ..util import get_package_path, get_model_meta, is_compatible_version
from ..util import (
get_installed_models,
get_minor_version,
get_model_meta,
get_package_path,
get_package_version,
is_compatible_version,
)
from ._util import app
@app.command("validate")

1
spacy/compat.py
View File

@ -1,5 +1,6 @@
"""Helpers for Python and platform compatibility."""
import sys
from thinc.util import copy_array
try:

20
spacy/displacy/__init__.py
View File

@ -4,15 +4,13 @@ spaCy's built in visualization suite for dependencies and named entities.
DOCS: https://spacy.io/api/top-level#displacy
USAGE: https://spacy.io/usage/visualizers
"""
from typing import Union, Iterable, Optional, Dict, Any, Callable
import warnings
from typing import Any, Callable, Dict, Iterable, Optional, Union
from .render import DependencyRenderer, EntityRenderer, SpanRenderer
from ..tokens import Doc, Span
from ..errors import Errors, Warnings
from ..util import is_in_jupyter
from ..util import find_available_port
from ..tokens import Doc, Span
from ..util import find_available_port, is_in_jupyter
from .render import DependencyRenderer, EntityRenderer, SpanRenderer
_html = {}
RENDER_WRAPPER = None
@ -68,7 +66,7 @@ def render(
if jupyter or (jupyter is None and is_in_jupyter()):
# return HTML rendered by IPython display()
# See #4840 for details on span wrapper to disable mathjax
from IPython.core.display import display, HTML
from IPython.core.display import HTML, display
return display(HTML('<span class="tex2jax_ignore">{}</span>'.format(html)))
return html
@ -125,13 +123,17 @@ def app(environ, start_response):
return [res]
def parse_deps(orig_doc: Doc, options: Dict[str, Any] = {}) -> Dict[str, Any]:
def parse_deps(
orig_doc: Union[Doc, Span], options: Dict[str, Any] = {}
) -> Dict[str, Any]:
"""Generate dependency parse in {'words': [], 'arcs': []} format.
orig_doc (Doc): Document to parse.
orig_doc (Union[Doc, Span]): Document to parse.
options (Dict[str, Any]): Dependency parse specific visualisation options.
RETURNS (dict): Generated dependency parse keyed by words and arcs.
"""
if isinstance(orig_doc, Span):
orig_doc = orig_doc.as_doc()
doc = Doc(orig_doc.vocab).from_bytes(
orig_doc.to_bytes(exclude=["user_data", "user_hooks"])
)

31
spacy/displacy/render.py
View File

@ -1,15 +1,28 @@
from typing import Any, Dict, List, Optional, Tuple, Union
import uuid
import itertools
from typing import Any, Dict, List, Optional, Tuple, Union
from ..errors import Errors
from ..util import escape_html, minify_html, registry
from .templates import TPL_DEP_ARCS, TPL_DEP_SVG, TPL_DEP_WORDS
from .templates import TPL_DEP_WORDS_LEMMA, TPL_ENT, TPL_ENT_RTL, TPL_ENTS
from .templates import TPL_FIGURE, TPL_KB_LINK, TPL_PAGE, TPL_SPAN
from .templates import TPL_SPAN_RTL, TPL_SPAN_SLICE, TPL_SPAN_SLICE_RTL
from .templates import TPL_SPAN_START, TPL_SPAN_START_RTL, TPL_SPANS
from .templates import TPL_TITLE
from .templates import (
TPL_DEP_ARCS,
TPL_DEP_SVG,
TPL_DEP_WORDS,
TPL_DEP_WORDS_LEMMA,
TPL_ENT,
TPL_ENT_RTL,
TPL_ENTS,
TPL_FIGURE,
TPL_KB_LINK,
TPL_PAGE,
TPL_SPAN,
TPL_SPAN_RTL,
TPL_SPAN_SLICE,
TPL_SPAN_SLICE_RTL,
TPL_SPAN_START,
TPL_SPAN_START_RTL,
TPL_SPANS,
TPL_TITLE,
)
DEFAULT_LANG = "en"
DEFAULT_DIR = "ltr"
@ -204,7 +217,7 @@ class SpanRenderer:
+ (self.offset_step * (len(entities) - 1))
)
markup += self.span_template.format(
text=token["text"],
text=escape_html(token["text"]),
span_slices=slices,
span_starts=starts,
total_height=total_height,

16
spacy/errors.py
View File

@ -1,5 +1,5 @@
from typing import Literal
import warnings
from typing import Literal
class ErrorsWithCodes(type):
@ -208,6 +208,9 @@ class Warnings(metaclass=ErrorsWithCodes):
W123 = ("Argument `enable` with value {enable} does not contain all values specified in the config option "
"`enabled` ({enabled}). Be aware that this might affect other components in your pipeline.")
W124 = ("{host}:{port} is already in use, using the nearest available port {serve_port} as an alternative.")
W125 = ("The StaticVectors key_attr is no longer used. To set a custom "
"key attribute for vectors, configure it through Vectors(attr=) or "
"'spacy init vectors --attr'")
# v4 warning strings
W400 = ("`use_upper=False` is ignored, the upper layer is always enabled")
@ -546,6 +549,8 @@ class Errors(metaclass=ErrorsWithCodes):
"during training, make sure to include it in 'annotating components'")
# New errors added in v3.x
E850 = ("The PretrainVectors objective currently only supports default or "
"floret vectors, not {mode} vectors.")
E851 = ("The 'textcat' component labels should only have values of 0 or 1, "
"but found value of '{val}'.")
E852 = ("The tar file pulled from the remote attempted an unsafe path "
@ -954,6 +959,14 @@ class Errors(metaclass=ErrorsWithCodes):
"with `displacy.serve(doc, port=port)`")
E1050 = ("Port {port} is already in use. Please specify an available port with `displacy.serve(doc, port=port)` "
"or use `auto_select_port=True` to pick an available port automatically.")
E1051 = ("'allow_overlap' can only be False when max_positive is 1, but found 'max_positive': {max_positive}.")
E1052 = ("Unable to copy spans: the character offsets for the span at "
"index {i} in the span group do not align with the tokenization "
"in the target doc.")
E1053 = ("Both 'min_length' and 'max_length' should be larger than 0, but found"
" 'min_length': {min_length}, 'max_length': {max_length}")
E1054 = ("The text, including whitespace, must match between reference and "
"predicted docs when training {component}.")
# v4 error strings
E4000 = ("Expected a Doc as input, but got: '{type}'")
@ -968,6 +981,7 @@ class Errors(metaclass=ErrorsWithCodes):
E4007 = ("Span {var} {value} must be {op} Span {existing_var} "
"{existing_value}.")
E4008 = ("Span {pos}_char {value} does not correspond to a token {pos}.")
E4009 = ("The '{attr}' parameter should be 'None' or 'True', but found '{value}'.")
RENAMED_LANGUAGE_CODES = {"xx": "mul", "is": "isl"}

1
spacy/glossary.py
View File

@ -1,4 +1,5 @@
import warnings
from .errors import Warnings

2
spacy/kb/__init__.py
View File

@ -1,5 +1,5 @@
from .candidate import Candidate, InMemoryCandidate
from .kb import KnowledgeBase
from .kb_in_memory import InMemoryLookupKB
from .candidate import Candidate, InMemoryCandidate
__all__ = ["KnowledgeBase", "InMemoryLookupKB", "Candidate", "InMemoryCandidate"]

6
spacy/kb/candidate.pxd
View File

@ -1,6 +1,8 @@
from libcpp.vector cimport vector
from .kb_in_memory cimport InMemoryLookupKB
from ..typedefs cimport hash_t
from .kb_in_memory cimport InMemoryLookupKB
cdef class Candidate:
pass
@ -9,7 +11,7 @@ cdef class Candidate:
cdef class InMemoryCandidate(Candidate):
cdef readonly hash_t _entity_hash
cdef readonly hash_t _alias_hash
cpdef vector[float] _entity_vector
cdef vector[float] _entity_vector
cdef float _prior_prob
cdef readonly InMemoryLookupKB _kb
cdef float _entity_freq

2
spacy/kb/candidate.pyx
View File

@ -1,8 +1,10 @@
# cython: infer_types=True, profile=True
from .kb_in_memory cimport InMemoryLookupKB
from ..errors import Errors
cdef class Candidate:
"""A `Candidate` object refers to a textual mention that may or may not be resolved
to a specific entity from a Knowledge Base. This will be used as input for the entity linking

2
spacy/kb/kb.pxd
View File

@ -2,8 +2,10 @@
from cymem.cymem cimport Pool
from libc.stdint cimport int64_t
from ..vocab cimport Vocab
cdef class KnowledgeBase:
cdef Pool mem
cdef readonly Vocab vocab

44
spacy/kb/kb.pyx
View File

@ -1,18 +1,20 @@
# cython: infer_types=True, profile=True
from pathlib import Path
from typing import Iterable, Tuple, Union, Iterator
from typing import Iterable, Iterator, Tuple, Union
from cymem.cymem cimport Pool
from .candidate import Candidate
from ..errors import Errors
from ..tokens import Span, SpanGroup
from ..util import SimpleFrozenList
from ..errors import Errors
from .candidate import Candidate
cdef class KnowledgeBase:
"""A `KnowledgeBase` instance stores unique identifiers for entities and their textual aliases,
to support entity linking of named entities to real-world concepts.
"""A `KnowledgeBase` instance stores unique identifiers for entities and
their textual aliases, to support entity linking of named entities to
real-world concepts.
This is an abstract class and requires its operations to be implemented.
DOCS: https://spacy.io/api/kb
@ -40,7 +42,9 @@ cdef class KnowledgeBase:
RETURNS (Iterator[Iterable[Iterable[Candidate]]]): Identified candidates.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="get_candidates", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="get_candidates", name=self.__name__
)
)
def get_vectors(self, entities: Iterable[str]) -> Iterable[Iterable[float]]:
@ -58,7 +62,9 @@ cdef class KnowledgeBase:
RETURNS (Iterable[float]): Vector for specified entity.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="get_vector", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="get_vector", name=self.__name__
)
)
def to_bytes(self, **kwargs) -> bytes:
@ -66,7 +72,9 @@ cdef class KnowledgeBase:
RETURNS (bytes): Current state as binary string.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="to_bytes", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="to_bytes", name=self.__name__
)
)
def from_bytes(self, bytes_data: bytes, *, exclude: Tuple[str] = tuple()):
@ -75,27 +83,37 @@ cdef class KnowledgeBase:
exclude (Tuple[str]): Properties to exclude when restoring KB.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="from_bytes", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="from_bytes", name=self.__name__
)
)
def to_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None:
def to_disk(
self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
) -> None:
"""
Write KnowledgeBase content to disk.
path (Union[str, Path]): Target file path.
exclude (Iterable[str]): List of components to exclude.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="to_disk", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="to_disk", name=self.__name__
)
)
def from_disk(self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()) -> None:
def from_disk(
self, path: Union[str, Path], exclude: Iterable[str] = SimpleFrozenList()
) -> None:
"""
Load KnowledgeBase content from disk.
path (Union[str, Path]): Target file path.
exclude (Iterable[str]): List of components to exclude.
"""
raise NotImplementedError(
Errors.E1045.format(parent="KnowledgeBase", method="from_disk", name=self.__name__)
Errors.E1045.format(
parent="KnowledgeBase", method="from_disk", name=self.__name__
)
)
@property

68
spacy/kb/kb_in_memory.pxd
View File

@ -1,11 +1,11 @@
"""Knowledge-base for entity or concept linking."""
from preshed.maps cimport PreshMap
from libcpp.vector cimport vector
from libc.stdint cimport int32_t, int64_t
from libc.stdio cimport FILE
from libcpp.vector cimport vector
from preshed.maps cimport PreshMap
from ..structs cimport AliasC, KBEntryC
from ..typedefs cimport hash_t
from ..structs cimport KBEntryC, AliasC
from .kb cimport KnowledgeBase
ctypedef vector[KBEntryC] entry_vec
@ -55,23 +55,28 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# optional data, we can let users configure a DB as the backend for this.
cdef object _features_table
cdef inline int64_t c_add_vector(self, vector[float] entity_vector) nogil:
"""Add an entity vector to the vectors table."""
cdef int64_t new_index = self._vectors_table.size()
self._vectors_table.push_back(entity_vector)
return new_index
cdef inline int64_t c_add_entity(self, hash_t entity_hash, float freq,
int32_t vector_index, int feats_row) nogil:
cdef inline int64_t c_add_entity(
self,
hash_t entity_hash,
float freq,
int32_t vector_index,
int feats_row
) nogil:
"""Add an entry to the vector of entries.
After calling this method, make sure to update also the _entry_index using the return value"""
After calling this method, make sure to update also the _entry_index
using the return value"""
# This is what we'll map the entity hash key to. It's where the entry will sit
# in the vector of entries, so we can get it later.
cdef int64_t new_index = self._entries.size()
# Avoid struct initializer to enable nogil, cf https://github.com/cython/cython/issues/1642
# Avoid struct initializer to enable nogil, cf.
# https://github.com/cython/cython/issues/1642
cdef KBEntryC entry
entry.entity_hash = entity_hash
entry.vector_index = vector_index
@ -81,11 +86,17 @@ cdef class InMemoryLookupKB(KnowledgeBase):
self._entries.push_back(entry)
return new_index
cdef inline int64_t c_add_aliases(self, hash_t alias_hash, vector[int64_t] entry_indices, vector[float] probs) nogil:
"""Connect a mention to a list of potential entities with their prior probabilities .
After calling this method, make sure to update also the _alias_index using the return value"""
# This is what we'll map the alias hash key to. It's where the alias will be defined
# in the vector of aliases.
cdef inline int64_t c_add_aliases(
self,
hash_t alias_hash,
vector[int64_t] entry_indices,
vector[float] probs
) nogil:
"""Connect a mention to a list of potential entities with their prior
probabilities. After calling this method, make sure to update also the
_alias_index using the return value"""
# This is what we'll map the alias hash key to. It's where the alias will be
# defined in the vector of aliases.
cdef int64_t new_index = self._aliases_table.size()
# Avoid struct initializer to enable nogil
@ -98,8 +109,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
cdef inline void _create_empty_vectors(self, hash_t dummy_hash) nogil:
"""
Initializing the vectors and making sure the first element of each vector is a dummy,
because the PreshMap maps pointing to indices in these vectors can not contain 0 as value
Initializing the vectors and making sure the first element of each vector is a
dummy, because the PreshMap maps pointing to indices in these vectors can not
contain 0 as value.
cf. https://github.com/explosion/preshed/issues/17
"""
cdef int32_t dummy_value = 0
@ -130,12 +142,18 @@ cdef class InMemoryLookupKB(KnowledgeBase):
cdef class Writer:
cdef FILE* _fp
cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1
cdef int write_header(
self, int64_t nr_entries, int64_t entity_vector_length
) except -1
cdef int write_vector_element(self, float element) except -1
cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1
cdef int write_entry(
self, hash_t entry_hash, float entry_freq, int32_t vector_index
) except -1
cdef int write_alias_length(self, int64_t alias_length) except -1
cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1
cdef int write_alias_header(
self, hash_t alias_hash, int64_t candidate_length
) except -1
cdef int write_alias(self, int64_t entry_index, float prob) except -1
cdef int _write(self, void* value, size_t size) except -1
@ -143,12 +161,18 @@ cdef class Writer:
cdef class Reader:
cdef FILE* _fp
cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1
cdef int read_header(
self, int64_t* nr_entries, int64_t* entity_vector_length
) except -1
cdef int read_vector_element(self, float* element) except -1
cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1
cdef int read_entry(
self, hash_t* entity_hash, float* freq, int32_t* vector_index
) except -1
cdef int read_alias_length(self, int64_t* alias_length) except -1
cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1
cdef int read_alias_header(
self, hash_t* alias_hash, int64_t* candidate_length
) except -1
cdef int read_alias(self, int64_t* entry_index, float* prob) except -1
cdef int _read(self, void* value, size_t size) except -1

161
spacy/kb/kb_in_memory.pyx
View File

@ -1,29 +1,35 @@
# cython: infer_types=True, profile=True
from typing import Iterable, Callable, Dict, Any, Union, Iterator
from typing import Any, Callable, Dict, Iterable, Union
import srsly
from preshed.maps cimport PreshMap
from cpython.exc cimport PyErr_SetFromErrno
from libc.stdio cimport fopen, fclose, fread, fwrite, feof, fseek
from libc.stdint cimport int32_t, int64_t
from libc.stdio cimport fclose, feof, fopen, fread, fseek, fwrite
from libcpp.vector cimport vector
from preshed.maps cimport PreshMap
from pathlib import Path
import warnings
from pathlib import Path
from ..tokens import Span, SpanGroup
from ..tokens import SpanGroup
from ..typedefs cimport hash_t
from ..errors import Errors, Warnings
from .. import util
from ..errors import Errors, Warnings
from ..util import SimpleFrozenList, ensure_path
from ..vocab cimport Vocab
from .kb cimport KnowledgeBase
from .candidate import InMemoryCandidate
cdef class InMemoryLookupKB(KnowledgeBase):
"""An `InMemoryLookupKB` instance stores unique identifiers for entities and their textual aliases,
to support entity linking of named entities to real-world concepts.
"""An `InMemoryLookupKB` instance stores unique identifiers for entities
and their textual aliases, to support entity linking of named entities to
real-world concepts.
DOCS: https://spacy.io/api/inmemorylookupkb
"""
@ -66,7 +72,8 @@ cdef class InMemoryLookupKB(KnowledgeBase):
def add_entity(self, str entity, float freq, vector[float] entity_vector):
"""
Add an entity to the KB, optionally specifying its log probability based on corpus frequency
Add an entity to the KB, optionally specifying its log probability
based on corpus frequency.
Return the hash of the entity ID/name at the end.
"""
cdef hash_t entity_hash = self.vocab.strings.add(entity)
@ -78,14 +85,20 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# Raise an error if the provided entity vector is not of the correct length
if len(entity_vector) != self.entity_vector_length:
raise ValueError(Errors.E141.format(found=len(entity_vector), required=self.entity_vector_length))
raise ValueError(
Errors.E141.format(
found=len(entity_vector), required=self.entity_vector_length
)
)
vector_index = self.c_add_vector(entity_vector=entity_vector)
new_index = self.c_add_entity(entity_hash=entity_hash,
freq=freq,
vector_index=vector_index,
feats_row=-1) # Features table currently not implemented
new_index = self.c_add_entity(
entity_hash=entity_hash,
freq=freq,
vector_index=vector_index,
feats_row=-1
) # Features table currently not implemented
self._entry_index[entity_hash] = new_index
return entity_hash
@ -110,7 +123,12 @@ cdef class InMemoryLookupKB(KnowledgeBase):
else:
entity_vector = vector_list[i]
if len(entity_vector) != self.entity_vector_length:
raise ValueError(Errors.E141.format(found=len(entity_vector), required=self.entity_vector_length))
raise ValueError(
Errors.E141.format(
found=len(entity_vector),
required=self.entity_vector_length
)
)
entry.entity_hash = entity_hash
entry.freq = freq_list[i]
@ -144,11 +162,15 @@ cdef class InMemoryLookupKB(KnowledgeBase):
previous_alias_nr = self.get_size_aliases()
# Throw an error if the length of entities and probabilities are not the same
if not len(entities) == len(probabilities):
raise ValueError(Errors.E132.format(alias=alias,
entities_length=len(entities),
probabilities_length=len(probabilities)))
raise ValueError(
Errors.E132.format(
alias=alias,
entities_length=len(entities),
probabilities_length=len(probabilities))
)
# Throw an error if the probabilities sum up to more than 1 (allow for some rounding errors)
# Throw an error if the probabilities sum up to more than 1 (allow for
# some rounding errors)
prob_sum = sum(probabilities)
if prob_sum > 1.00001:
raise ValueError(Errors.E133.format(alias=alias, sum=prob_sum))
@ -165,40 +187,47 @@ cdef class InMemoryLookupKB(KnowledgeBase):
for entity, prob in zip(entities, probabilities):
entity_hash = self.vocab.strings[entity]
if not entity_hash in self._entry_index:
if entity_hash not in self._entry_index:
raise ValueError(Errors.E134.format(entity=entity))
entry_index = <int64_t>self._entry_index.get(entity_hash)
entry_indices.push_back(int(entry_index))
probs.push_back(float(prob))
new_index = self.c_add_aliases(alias_hash=alias_hash, entry_indices=entry_indices, probs=probs)
new_index = self.c_add_aliases(
alias_hash=alias_hash, entry_indices=entry_indices, probs=probs
)
self._alias_index[alias_hash] = new_index
if previous_alias_nr + 1 != self.get_size_aliases():
raise RuntimeError(Errors.E891.format(alias=alias))
return alias_hash
def append_alias(self, str alias, str entity, float prior_prob, ignore_warnings=False):
def append_alias(
self, str alias, str entity, float prior_prob, ignore_warnings=False
):
"""
For an alias already existing in the KB, extend its potential entities with one more.
For an alias already existing in the KB, extend its potential entities
with one more.
Throw a warning if either the alias or the entity is unknown,
or when the combination is already previously recorded.
Throw an error if this entity+prior prob would exceed the sum of 1.
For efficiency, it's best to use the method `add_alias` as much as possible instead of this one.
For efficiency, it's best to use the method `add_alias` as much as
possible instead of this one.
"""
# Check if the alias exists in the KB
cdef hash_t alias_hash = self.vocab.strings[alias]
if not alias_hash in self._alias_index:
if alias_hash not in self._alias_index:
raise ValueError(Errors.E176.format(alias=alias))
# Check if the entity exists in the KB
cdef hash_t entity_hash = self.vocab.strings[entity]
if not entity_hash in self._entry_index:
if entity_hash not in self._entry_index:
raise ValueError(Errors.E134.format(entity=entity))
entry_index = <int64_t>self._entry_index.get(entity_hash)
# Throw an error if the prior probabilities (including the new one) sum up to more than 1
# Throw an error if the prior probabilities (including the new one)
# sum up to more than 1
alias_index = <int64_t>self._alias_index.get(alias_hash)
alias_entry = self._aliases_table[alias_index]
current_sum = sum([p for p in alias_entry.probs])
@ -232,12 +261,13 @@ cdef class InMemoryLookupKB(KnowledgeBase):
def _get_alias_candidates(self, str alias) -> Iterable[InMemoryCandidate]:
"""
Return candidate entities for an alias. Each candidate defines the entity, the original alias,
and the prior probability of that alias resolving to that entity.
Return candidate entities for an alias. Each candidate defines the
entity, the original alias, and the prior probability of that alias
resolving to that entity.
If the alias is not known in the KB, and empty list is returned.
"""
cdef hash_t alias_hash = self.vocab.strings[alias]
if not alias_hash in self._alias_index:
if alias_hash not in self._alias_index:
return []
alias_index = <int64_t>self._alias_index.get(alias_hash)
alias_entry = self._aliases_table[alias_index]
@ -266,8 +296,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
return self._vectors_table[self._entries[entry_index].vector_index]
def get_prior_prob(self, str entity, str alias):
""" Return the prior probability of a given alias being linked to a given entity,
or return 0.0 when this combination is not known in the knowledge base"""
""" Return the prior probability of a given alias being linked to a
given entity, or return 0.0 when this combination is not known in the
knowledge base."""
cdef hash_t alias_hash = self.vocab.strings[alias]
cdef hash_t entity_hash = self.vocab.strings[entity]
@ -278,7 +309,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
entry_index = self._entry_index[entity_hash]
alias_entry = self._aliases_table[alias_index]
for (entry_index, prior_prob) in zip(alias_entry.entry_indices, alias_entry.probs):
for (entry_index, prior_prob) in zip(
alias_entry.entry_indices, alias_entry.probs
):
if self._entries[entry_index].entity_hash == entity_hash:
return prior_prob
@ -291,13 +324,19 @@ cdef class InMemoryLookupKB(KnowledgeBase):
"""Serialize the current state to a binary string.
"""
def serialize_header():
header = (self.get_size_entities(), self.get_size_aliases(), self.entity_vector_length)
header = (
self.get_size_entities(),
self.get_size_aliases(),
self.entity_vector_length
)
return srsly.json_dumps(header)
def serialize_entries():
i = 1
tuples = []
for entry_hash, entry_index in sorted(self._entry_index.items(), key=lambda x: x[1]):
for entry_hash, entry_index in sorted(
self._entry_index.items(), key=lambda x: x[1]
):
entry = self._entries[entry_index]
assert entry.entity_hash == entry_hash
assert entry_index == i
@ -310,7 +349,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
headers = []
indices_lists = []
probs_lists = []
for alias_hash, alias_index in sorted(self._alias_index.items(), key=lambda x: x[1]):
for alias_hash, alias_index in sorted(
self._alias_index.items(), key=lambda x: x[1]
):
alias = self._aliases_table[alias_index]
assert alias_index == i
candidate_length = len(alias.entry_indices)
@ -368,7 +409,7 @@ cdef class InMemoryLookupKB(KnowledgeBase):
indices = srsly.json_loads(all_data[1])
probs = srsly.json_loads(all_data[2])
for header, indices, probs in zip(headers, indices, probs):
alias_hash, candidate_length = header
alias_hash, _candidate_length = header
alias.entry_indices = indices
alias.probs = probs
self._aliases_table[i] = alias
@ -417,10 +458,14 @@ cdef class InMemoryLookupKB(KnowledgeBase):
writer.write_vector_element(element)
i = i+1
# dumping the entry records in the order in which they are in the _entries vector.
# index 0 is a dummy object not stored in the _entry_index and can be ignored.
# dumping the entry records in the order in which they are in the
# _entries vector.
# index 0 is a dummy object not stored in the _entry_index and can
# be ignored.
i = 1
for entry_hash, entry_index in sorted(self._entry_index.items(), key=lambda x: x[1]):
for entry_hash, entry_index in sorted(
self._entry_index.items(), key=lambda x: x[1]
):
entry = self._entries[entry_index]
assert entry.entity_hash == entry_hash
assert entry_index == i
@ -432,7 +477,9 @@ cdef class InMemoryLookupKB(KnowledgeBase):
# dumping the aliases in the order in which they are in the _alias_index vector.
# index 0 is a dummy object not stored in the _aliases_table and can be ignored.
i = 1
for alias_hash, alias_index in sorted(self._alias_index.items(), key=lambda x: x[1]):
for alias_hash, alias_index in sorted(
self._alias_index.items(), key=lambda x: x[1]
):
alias = self._aliases_table[alias_index]
assert alias_index == i
@ -538,7 +585,8 @@ cdef class Writer:
def __init__(self, path):
assert isinstance(path, Path)
content = bytes(path)
cdef bytes bytes_loc = content.encode('utf8') if type(content) == str else content
cdef bytes bytes_loc = content.encode('utf8') \
if type(content) == str else content
self._fp = fopen(<char*>bytes_loc, 'wb')
if not self._fp:
raise IOError(Errors.E146.format(path=path))
@ -548,14 +596,18 @@ cdef class Writer:
cdef size_t status = fclose(self._fp)
assert status == 0
cdef int write_header(self, int64_t nr_entries, int64_t entity_vector_length) except -1:
cdef int write_header(
self, int64_t nr_entries, int64_t entity_vector_length
) except -1:
self._write(&nr_entries, sizeof(nr_entries))
self._write(&entity_vector_length, sizeof(entity_vector_length))
cdef int write_vector_element(self, float element) except -1:
self._write(&element, sizeof(element))
cdef int write_entry(self, hash_t entry_hash, float entry_freq, int32_t vector_index) except -1:
cdef int write_entry(
self, hash_t entry_hash, float entry_freq, int32_t vector_index
) except -1:
self._write(&entry_hash, sizeof(entry_hash))
self._write(&entry_freq, sizeof(entry_freq))
self._write(&vector_index, sizeof(vector_index))
@ -564,7 +616,9 @@ cdef class Writer:
cdef int write_alias_length(self, int64_t alias_length) except -1:
self._write(&alias_length, sizeof(alias_length))
cdef int write_alias_header(self, hash_t alias_hash, int64_t candidate_length) except -1:
cdef int write_alias_header(
self, hash_t alias_hash, int64_t candidate_length
) except -1:
self._write(&alias_hash, sizeof(alias_hash))
self._write(&candidate_length, sizeof(candidate_length))
@ -580,16 +634,19 @@ cdef class Writer:
cdef class Reader:
def __init__(self, path):
content = bytes(path)
cdef bytes bytes_loc = content.encode('utf8') if type(content) == str else content
cdef bytes bytes_loc = content.encode('utf8') \
if type(content) == str else content
self._fp = fopen(<char*>bytes_loc, 'rb')
if not self._fp:
PyErr_SetFromErrno(IOError)
status = fseek(self._fp, 0, 0) # this can be 0 if there is no header
fseek(self._fp, 0, 0) # this can be 0 if there is no header
def __dealloc__(self):
fclose(self._fp)
cdef int read_header(self, int64_t* nr_entries, int64_t* entity_vector_length) except -1:
cdef int read_header(
self, int64_t* nr_entries, int64_t* entity_vector_length
) except -1:
status = self._read(nr_entries, sizeof(int64_t))
if status < 1:
if feof(self._fp):
@ -609,7 +666,9 @@ cdef class Reader:
return 0 # end of file
raise IOError(Errors.E145.format(param="vector element"))
cdef int read_entry(self, hash_t* entity_hash, float* freq, int32_t* vector_index) except -1:
cdef int read_entry(
self, hash_t* entity_hash, float* freq, int32_t* vector_index
) except -1:
status = self._read(entity_hash, sizeof(hash_t))
if status < 1:
if feof(self._fp):
@ -640,7 +699,9 @@ cdef class Reader:
return 0 # end of file
raise IOError(Errors.E145.format(param="alias length"))
cdef int read_alias_header(self, hash_t* alias_hash, int64_t* candidate_length) except -1:
cdef int read_alias_header(
self, hash_t* alias_hash, int64_t* candidate_length
) except -1:
status = self._read(alias_hash, sizeof(hash_t))
if status < 1:
if feof(self._fp):

2
spacy/lang/af/__init__.py
View File

@ -1,5 +1,5 @@
from ...language import BaseDefaults, Language
from .stop_words import STOP_WORDS
from ...language import Language, BaseDefaults
class AfrikaansDefaults(BaseDefaults):

11
spacy/lang/am/__init__.py
View File

@ -1,12 +1,11 @@
from .stop_words import STOP_WORDS
from ...attrs import LANG
from ...language import BaseDefaults, Language
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...language import Language, BaseDefaults
from ...attrs import LANG
from ...util import update_exc
class AmharicDefaults(BaseDefaults):

10
spacy/lang/am/punctuation.py
View File

@ -1,5 +1,11 @@
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
from ..char_classes import UNITS, ALPHA_UPPER
from ..char_classes import (
ALPHA_UPPER,
CURRENCY,
LIST_ELLIPSES,
LIST_PUNCT,
LIST_QUOTES,
UNITS,
)
_list_punct = LIST_PUNCT + "፡ ። ፣ ፤ ፥ ፦ ፧ ፠ ፨".strip().split()

3
spacy/lang/am/tokenizer_exceptions.py
View File

@ -1,5 +1,4 @@
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
_exc = {}

4
spacy/lang/ar/__init__.py
View File

@ -1,8 +1,8 @@
from .stop_words import STOP_WORDS
from ...language import BaseDefaults, Language
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from ...language import Language, BaseDefaults
class ArabicDefaults(BaseDefaults):

10
spacy/lang/ar/punctuation.py
View File

@ -1,5 +1,11 @@
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
from ..char_classes import UNITS, ALPHA_UPPER
from ..char_classes import (
ALPHA_UPPER,
CURRENCY,
LIST_ELLIPSES,
LIST_PUNCT,
LIST_QUOTES,
UNITS,
)
_suffixes = (
LIST_PUNCT

5
spacy/lang/ar/tokenizer_exceptions.py
View File

@ -1,7 +1,6 @@
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}

4
spacy/lang/az/__init__.py
View File

@ -1,6 +1,6 @@
from .stop_words import STOP_WORDS
from ...language import BaseDefaults, Language
from .lex_attrs import LEX_ATTRS
from ...language import Language, BaseDefaults
from .stop_words import STOP_WORDS
class AzerbaijaniDefaults(BaseDefaults):

1
spacy/lang/az/lex_attrs.py
View File

@ -1,6 +1,5 @@
from ...attrs import LIKE_NUM
# Eleven, twelve etc. are written separate: on bir, on iki
_num_words = [

16
spacy/lang/bg/__init__.py
View File

@ -1,12 +1,14 @@
from ...attrs import LANG
from ...language import BaseDefaults, Language
from ...util import update_exc
from ..punctuation import (
COMBINING_DIACRITICS_TOKENIZER_INFIXES,
COMBINING_DIACRITICS_TOKENIZER_SUFFIXES,
)
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .lex_attrs import LEX_ATTRS
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_INFIXES
from ..punctuation import COMBINING_DIACRITICS_TOKENIZER_SUFFIXES
from ...language import Language, BaseDefaults
from ...attrs import LANG
from ...util import update_exc
class BulgarianDefaults(BaseDefaults):

1
spacy/lang/bg/lex_attrs.py
View File

@ -1,6 +1,5 @@
from ...attrs import LIKE_NUM
_num_words = [
"нула",
"едно",

3
spacy/lang/bg/tokenizer_exceptions.py
View File

@ -4,8 +4,7 @@ References:
(countries, occupations, fields of studies and more).
"""
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
_exc = {}

12
spacy/lang/bn/__init__.py
View File

@ -1,10 +1,12 @@
from typing import Optional, Callable
from typing import Callable, Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from .stop_words import STOP_WORDS
from ...language import Language, BaseDefaults
from ...language import BaseDefaults, Language
from ...pipeline import Lemmatizer
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class BengaliDefaults(BaseDefaults):

14
spacy/lang/bn/punctuation.py
View File

@ -1,6 +1,14 @@
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
from ..char_classes import ALPHA_LOWER, ALPHA, HYPHENS, CONCAT_QUOTES, UNITS
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
CONCAT_QUOTES,
HYPHENS,
LIST_ELLIPSES,
LIST_ICONS,
LIST_PUNCT,
LIST_QUOTES,
UNITS,
)
_currency = r"\$¢£€¥฿৳"
_quotes = CONCAT_QUOTES.replace("'", "")

5
spacy/lang/bn/tokenizer_exceptions.py
View File

@ -1,7 +1,6 @@
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}

14
spacy/lang/ca/__init__.py
View File

@ -1,14 +1,14 @@
from typing import Optional, Callable
from typing import Callable, Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES, TOKENIZER_PREFIXES
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from ...language import Language, BaseDefaults
from ...language import BaseDefaults, Language
from .lemmatizer import CatalanLemmatizer
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class CatalanDefaults(BaseDefaults):

1
spacy/lang/ca/lex_attrs.py
View File

@ -1,6 +1,5 @@
from ...attrs import LIKE_NUM
_num_words = [
"zero",
"un",

21
spacy/lang/ca/punctuation.py
View File

@ -1,9 +1,18 @@
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_ICONS
from ..char_classes import LIST_CURRENCY
from ..char_classes import CURRENCY
from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA, PUNCT
from ..char_classes import merge_chars, _units
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
CURRENCY,
LIST_CURRENCY,
LIST_ELLIPSES,
LIST_ICONS,
LIST_PUNCT,
LIST_QUOTES,
PUNCT,
_units,
merge_chars,
)
ELISION = " ' ’ ".strip().replace(" ", "").replace("\n", "")

7
spacy/lang/ca/syntax_iterators.py
View File

@ -1,7 +1,8 @@
from typing import Union, Iterator, Tuple
from ...tokens import Doc, Span
from ...symbols import NOUN, PROPN
from typing import Iterator, Tuple, Union
from ...errors import Errors
from ...symbols import NOUN, PROPN
from ...tokens import Doc, Span
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:

5
spacy/lang/ca/tokenizer_exceptions.py
View File

@ -1,7 +1,6 @@
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}

4
spacy/lang/cs/__init__.py
View File

@ -1,6 +1,6 @@
from .stop_words import STOP_WORDS
from ...language import BaseDefaults, Language
from .lex_attrs import LEX_ATTRS
from ...language import Language, BaseDefaults
from .stop_words import STOP_WORDS
class CzechDefaults(BaseDefaults):

6
spacy/lang/da/__init__.py
View File

@ -1,9 +1,9 @@
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from ...language import BaseDefaults, Language
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from ...language import Language, BaseDefaults
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class DanishDefaults(BaseDefaults):

1
spacy/lang/da/lex_attrs.py
View File

@ -1,6 +1,5 @@
from ...attrs import LIKE_NUM
# Source http://fjern-uv.dk/tal.php
_num_words = """nul
en et to tre fire fem seks syv otte ni ti

11
spacy/lang/da/punctuation.py
View File

@ -1,8 +1,13 @@
from ..char_classes import LIST_ELLIPSES, LIST_ICONS
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
LIST_ELLIPSES,
LIST_ICONS,
)
from ..punctuation import TOKENIZER_SUFFIXES
_quotes = CONCAT_QUOTES.replace("'", "")
_infixes = (

7
spacy/lang/da/syntax_iterators.py
View File

@ -1,7 +1,8 @@
from typing import Union, Iterator, Tuple
from ...tokens import Doc, Span
from ...symbols import NOUN, PROPN, PRON, VERB, AUX
from typing import Iterator, Tuple, Union
from ...errors import Errors
from ...symbols import AUX, NOUN, PRON, PROPN, VERB
from ...tokens import Doc, Span
def noun_chunks(doclike: Union[Doc, Span]) -> Iterator[Tuple[int, int, int]]:

5
spacy/lang/da/tokenizer_exceptions.py
View File

@ -2,10 +2,9 @@
Tokenizer Exceptions.
Source: https://forkortelse.dk/ and various others.
"""
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}

6
spacy/lang/de/__init__.py
View File

@ -1,8 +1,8 @@
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from ...language import BaseDefaults, Language
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from ...language import Language, BaseDefaults
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class GermanDefaults(BaseDefaults):

17
spacy/lang/de/punctuation.py
View File

@ -1,9 +1,18 @@
from ..char_classes import LIST_ELLIPSES, LIST_ICONS, LIST_PUNCT, LIST_QUOTES
from ..char_classes import CURRENCY, UNITS, PUNCT
from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
CURRENCY,
LIST_ELLIPSES,
LIST_ICONS,
LIST_PUNCT,
LIST_QUOTES,
PUNCT,
UNITS,
)
from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
_prefixes = ["``"] + BASE_TOKENIZER_PREFIXES
_suffixes = (

4
spacy/lang/de/syntax_iterators.py
View File

@ -1,7 +1,7 @@
from typing import Union, Iterator, Tuple
from typing import Iterator, Tuple, Union
from ...symbols import NOUN, PROPN, PRON
from ...errors import Errors
from ...symbols import NOUN, PRON, PROPN
from ...tokens import Doc, Span

5
spacy/lang/de/tokenizer_exceptions.py
View File

@ -1,7 +1,6 @@
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {
"auf'm": [{ORTH: "auf"}, {ORTH: "'m", NORM: "dem"}],

2
spacy/lang/dsb/__init__.py
View File

@ -1,6 +1,6 @@
from ...language import BaseDefaults, Language
from .lex_attrs import LEX_ATTRS
from .stop_words import STOP_WORDS
from ...language import Language, BaseDefaults
class LowerSorbianDefaults(BaseDefaults):

15
spacy/lang/el/__init__.py
View File

@ -1,13 +1,14 @@
from typing import Optional, Callable
from typing import Callable, Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES, TOKENIZER_INFIXES
from ...language import BaseDefaults, Language
from .lemmatizer import GreekLemmatizer
from ...language import Language, BaseDefaults
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_INFIXES, TOKENIZER_PREFIXES, TOKENIZER_SUFFIXES
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class GreekDefaults(BaseDefaults):

1
spacy/lang/el/get_pos_from_wiktionary.py
View File

@ -1,5 +1,6 @@
def get_pos_from_wiktionary():
import re
from gensim.corpora.wikicorpus import extract_pages
regex = re.compile(r"==={{(\w+)\|el}}===")

16
spacy/lang/el/punctuation.py
View File

@ -1,6 +1,16 @@
from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, LIST_CURRENCY
from ..char_classes import LIST_ICONS, ALPHA_LOWER, ALPHA_UPPER, ALPHA, HYPHENS
from ..char_classes import CONCAT_QUOTES, CURRENCY
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
CURRENCY,
HYPHENS,
LIST_CURRENCY,
LIST_ELLIPSES,
LIST_ICONS,
LIST_PUNCT,
LIST_QUOTES,
)
_units = (
"km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft "

4
spacy/lang/el/syntax_iterators.py
View File

@ -1,7 +1,7 @@
from typing import Union, Iterator, Tuple
from typing import Iterator, Tuple, Union
from ...symbols import NOUN, PROPN, PRON
from ...errors import Errors
from ...symbols import NOUN, PRON, PROPN
from ...tokens import Doc, Span

4
spacy/lang/el/tokenizer_exceptions.py
View File

@ -1,6 +1,6 @@
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc = {}

15
spacy/lang/en/__init__.py
View File

@ -1,13 +1,14 @@
from typing import Optional, Callable
from typing import Callable, Optional
from thinc.api import Model
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
from .stop_words import STOP_WORDS
from .lex_attrs import LEX_ATTRS
from .syntax_iterators import SYNTAX_ITERATORS
from .punctuation import TOKENIZER_INFIXES
from ...language import BaseDefaults, Language
from .lemmatizer import EnglishLemmatizer
from ...language import Language, BaseDefaults
from .lex_attrs import LEX_ATTRS
from .punctuation import TOKENIZER_INFIXES
from .stop_words import STOP_WORDS
from .syntax_iterators import SYNTAX_ITERATORS
from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
class EnglishDefaults(BaseDefaults):

11
spacy/lang/en/punctuation.py
View File

@ -1,5 +1,12 @@
from ..char_classes import LIST_ELLIPSES, LIST_ICONS, HYPHENS
from ..char_classes import CONCAT_QUOTES, ALPHA_LOWER, ALPHA_UPPER, ALPHA
from ..char_classes import (
ALPHA,
ALPHA_LOWER,
ALPHA_UPPER,
CONCAT_QUOTES,
HYPHENS,
LIST_ELLIPSES,
LIST_ICONS,
)
_infixes = (
LIST_ELLIPSES

4
spacy/lang/en/syntax_iterators.py
View File

@ -1,7 +1,7 @@
from typing import Union, Iterator, Tuple
from typing import Iterator, Tuple, Union
from ...symbols import NOUN, PROPN, PRON
from ...errors import Errors
from ...symbols import NOUN, PRON, PROPN
from ...tokens import Doc, Span

6
spacy/lang/en/tokenizer_exceptions.py
View File

@ -1,8 +1,8 @@
from typing import Dict, List
from ..tokenizer_exceptions import BASE_EXCEPTIONS
from ...symbols import ORTH, NORM
from ...util import update_exc
from ...symbols import NORM, ORTH
from ...util import update_exc
from ..tokenizer_exceptions import BASE_EXCEPTIONS
_exc: Dict[str, List[Dict]] = {}
_exclude = [

Some files were not shown because too many files have changed in this diff Show More