run linting, fix typos

OpenBioML · Aug 12, 2024 · da28ebc · da28ebc
1 parent fd0fa92
commit da28ebc
Show file tree

Hide file tree

Showing 240 changed files with 19,229 additions and 19,955 deletions.
diff --git a/.DS_Store b/.DS_Store
diff --git a/.github/workflows/install.yaml b/.github/workflows/install.yaml
@@ -1,29 +1,27 @@
----
 # GitHub action that attempts to install the conda env
 # from conda.yaml
 # then run black, isort, flake8
-
 name: Install
 on: [push, pull_request]
 jobs:
-    install:
-        runs-on: ubuntu-latest
-        steps:
-            - uses: actions/checkout@v2
-            - uses: conda-incubator/setup-miniconda@v2
-              with:
-                  environment-file: conda.yaml
-                  activate-environment: chemnlp
-                  python-version: 3.9
-                  auto-update-conda: true
-                  auto-activate-base: false
-            - name: Validate yaml
-              shell: bash -l {0}
-              run: |
-                  conda activate chemnlp
-                  python -m src.chemnlp.data_val.validate data
-            - name: Tests
-              shell: bash -l {0}
-              run: |
-                  pip install pytest
-                  pytest tests
+  install:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - uses: conda-incubator/setup-miniconda@v2
+        with:
+          environment-file: conda.yaml
+          activate-environment: chemnlp
+          python-version: 3.9
+          auto-update-conda: true
+          auto-activate-base: false
+      - name: Validate yaml
+        shell: bash -l {0}
+        run: |
+          conda activate chemnlp
+          python -m src.chemnlp.data_val.validate data
+      - name: Tests
+        shell: bash -l {0}
+        run: |
+          pip install pytest
+          pytest tests
diff --git a/.gitignore b/.gitignore
@@ -144,3 +144,5 @@ scratch/
 # vim
 *~
 *.swp
+
+.DS_Store
diff --git a/.gitmodules b/.gitmodules
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -1,41 +1,90 @@
----
-ci:
-    autoupdate_schedule: quarterly
-    autofix_prs: false
-    submodules: false
-
+default_language_version:
+  python: python3
 repos:
-    - repo: https://github.com/pre-commit/pre-commit-hooks
-      rev: v4.5.0
-      hooks:
-          - id: check-json
-          - id: check-yaml
-          - id: end-of-file-fixer
-          - id: trailing-whitespace
-            exclude: miscellaneous/structures/SiO2.xyz
-
-    - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt
-      rev: 0.2.3
-      hooks:
-          - id: yamlfmt
-            exclude: ^experiments/configs
-
-    - repo: https://github.com/psf/black
-      rev: 24.3.0
-      hooks:
-          - id: black
-            language_version: python3 # Should be a command that runs python3.6+
-
-    - repo: https://github.com/PyCQA/flake8
-      rev: 7.0.0
-      hooks:
-          - id: flake8
-            args: [--count, --show-source, --statistics]
-            additional_dependencies:
-                - flake8-bugbear==22.7.1
-
-    - repo: https://github.com/pycqa/isort
-      rev: 5.13.2
-      hooks:
-          - id: isort
-            args: [--profile, black, --filter-files]
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-byte-order-marker
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-yaml
+        exclude: "kubernetes.yaml$" # This line excludes kubernetes.yaml from being checked as it is WIP
+      - id: debug-statements
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        exclude: .gitignore
+      - id: trailing-whitespace
+        exclude: .gitignore
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 24.4.2
+    hooks:
+      - id: black-jupyter
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.5.1
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: v3.3.2
+    hooks:
+      - id: prettier
+  - repo: https://github.com/google/yamlfmt
+    rev: v0.13.0
+    hooks:
+      - id: yamlfmt
+  - repo: https://github.com/Yelp/detect-secrets
+    rev: v1.5.0
+    hooks:
+      - id: detect-secrets
+  - repo: https://github.com/pappasam/toml-sort
+    rev: v0.23.1
+    hooks:
+      - id: toml-sort-fix
+        exclude: poetry.lock
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        additional_dependencies: [".[toml]"]
+  - repo: https://github.com/sqlfluff/sqlfluff
+    rev: 3.1.0
+    hooks:
+      - id: sqlfluff-fix
+  - repo: https://github.com/hadolint/hadolint
+    rev: v2.13.0-beta
+    hooks:
+      - id: hadolint-docker
+  - repo: https://github.com/jsh9/markdown-toc-creator
+    rev: 0.0.6
+    hooks:
+      - id: markdown-toc-creator
+  - repo: https://github.com/jumanjihouse/pre-commit-hooks
+    rev: 3.0.0
+    hooks:
+      - id: check-mailmap
+  - repo: https://github.com/python-poetry/poetry
+    rev: 1.8.0
+    hooks:
+      - id: poetry-check
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.1
+    hooks:
+      - id: mypy
+        additional_dependencies:
+          - types-requests
+  - repo: https://github.com/srstevenson/nb-clean
+    rev: 3.3.0
+    hooks:
+      - id: nb-clean
+        args: [--preserve-cell-outputs, --remove-empty-cells]
+  - repo: https://github.com/abravalheri/validate-pyproject
+    rev: v0.18
+    hooks:
+      - id: validate-pyproject
+        additional_dependencies:
+          - "validate-pyproject-schema-store[all]>=2024.06.24" # Pin for Ruff's FURB154
diff --git a/README.md b/README.md
@@ -32,14 +32,12 @@ ChemNLP is an open-source project - your involvement is warmly welcome! If you'r
 - Looking for ideas? See our [task board](https://github.com/orgs/OpenBioML/projects/5/views/1) to see what we may need help with.
 - Have an idea? Create an [issue](https://github.com/OpenBioML/chemnlp/issues)!
 
-
 Over the past months ChemNLP has received many contributions and a lot of feedback. We appreciate all contributions from community to make ChemNLP thrive.
 
 <a href="https://github.com/openbioml/chemnlp/graphs/contributors">
   <img src="https://contrib.rocks/image?repo=openbioml/chemnlp" />
 </a>
 
-
 # Note on the "ChemNLP" name
 
 Our OpenBioML ChemNLP project is not affiliated to the [ChemNLP library from NIST](https://arxiv.org/abs/2209.08203) and we use "ChemNLP" as a general term to highlight our project focus. The datasets and models we create through our project will have a unique and recognizable name when we release them.

diff --git a/code_of_conduct.md b/code_of_conduct.md
@@ -1,4 +1,3 @@
-
 # Contributor Covenant Code of Conduct
 
 ## Our Pledge
@@ -18,23 +17,23 @@ diverse, inclusive, and healthy community.
 Examples of behavior that contributes to a positive environment for our
 community include:
 
-* Demonstrating empathy and kindness toward other people
-* Being respectful of differing opinions, viewpoints, and experiences
-* Giving and gracefully accepting constructive feedback
-* Accepting responsibility and apologizing to those affected by our mistakes,
+- Demonstrating empathy and kindness toward other people
+- Being respectful of differing opinions, viewpoints, and experiences
+- Giving and gracefully accepting constructive feedback
+- Accepting responsibility and apologizing to those affected by our mistakes,
   and learning from the experience
-* Focusing on what is best not just for us as individuals, but for the overall
+- Focusing on what is best not just for us as individuals, but for the overall
   community
 
 Examples of unacceptable behavior include:
 
-* The use of sexualized language or imagery, and sexual attention or advances of
+- The use of sexualized language or imagery, and sexual attention or advances of
   any kind
-* Trolling, insulting or derogatory comments, and personal or political attacks
-* Public or private harassment
-* Publishing others' private information, such as a physical or email address,
+- Trolling, insulting or derogatory comments, and personal or political attacks
+- Public or private harassment
+- Publishing others' private information, such as a physical or email address,
   without their explicit permission
-* Other conduct which could reasonably be considered inappropriate in a
+- Other conduct which could reasonably be considered inappropriate in a
   professional setting
 
 ## Enforcement Responsibilities

diff --git a/conda.yaml b/conda.yaml
@@ -1,9 +1,8 @@
----
 name: dummy
 dependencies:
-    - python==3.9.*
-    - pip
-    - pip:
-          - .
-          - .[dev]
-          - .[dataset_creation]
+  - python==3.9.*
+  - pip
+  - pip:
+      - .
+      - .[dev]
+      - .[dataset_creation]
diff --git a/data/kg/chebi_chebi/meta.yaml b/data/kg/chebi_chebi/meta.yaml
@@ -1,48 +1,43 @@
----
 name: chebi_chebi
 description: Knowledgegraph data samples.
 targets:
-    - id: node2_type
-      description: node2_type
-      type: Other
-      units: node2_type
-      names:
-          - noun: node2_type
-    - id: node2_name
-      description: node2_name
-      type: Other
-      units: node2_name
-      names:
-          - noun: node2_name
-    - id: node2_id
-      description: node2_id
-      type: Other
-      units: node2_id
-      names:
-          - noun: node2_id
+  - id: node2_type
+    description: node2_type
+    type: Other
+    units: node2_type
+    names:
+      - noun: node2_type
+  - id: node2_name
+    description: node2_name
+    type: Other
+    units: node2_name
+    names:
+      - noun: node2_name
+  - id: node2_id
+    description: node2_id
+    type: Other
+    units: node2_id
+    names:
+      - noun: node2_id
 identifiers:
-    - id: node1_type
-      description: node1_type
-      type: Other
-    - id: node1_name
-      description: node1_name
-      type: Other
-    - id: node1_id
-      description: node1_id
-      type: Other
-    - id: rel1_type
-      description: rel1_type
-      type: Other
+  - id: node1_type
+    description: node1_type
+    type: Other
+  - id: node1_name
+    description: node1_name
+    type: Other
+  - id: node1_id
+    description: node1_id
+    type: Other
+  - id: rel1_type
+    description: rel1_type
+    type: Other
 license: CC BY 4.0
 links:
-    - url: https://crossbar.kansil.org
-      description: original knowledge graph web GUI link
+  - url: https://crossbar.kansil.org
+    description: original knowledge graph web GUI link
 num_points: 638182
 bibtex:
-    - "@article{10.1093/nar/gkab543,\nauthor = {Doğan, Tunca and Atas, Heval and Joshi, Vishal and Atakan, Ahmet and Rifaioglu, Ahmet Sureyya and Nalbat,\
-      \ Esra and Nightingale, Andrew and Saidi, Rabie and Volynkin, Vladimir and Zellner, Hermann and Cetin-Atalay, Rengul and Martin, Maria and Atalay,\
-      \ Volkan},\ntitle = \"{CROssBAR: comprehensive resource of biomedical relations with knowledge graph representations}\",\njournal = {Nucleic Acids\
-      \ Research},\nvolume = {49},\nnumber = {16},\npages = {e96-e96},\nyear = {2021},\nmonth = {06},\nissn = {0305-1048},\ndoi = {10.1093/nar/gkab543},\n\
-      url = {https://doi.org/10.1093/nar/gkab543},\n}"
+  - "@article{10.1093/nar/gkab543,\nauthor = {Doğan, Tunca and Atas, Heval and Joshi, Vishal and Atakan, Ahmet and Rifaioglu, Ahmet Sureyya and Nalbat, Esra and Nightingale, Andrew and Saidi, Rabie and Volynkin, Vladimir and Zellner, Hermann and Cetin-Atalay, Rengul and Martin, Maria and Atalay, Volkan},\ntitle = \"{CROssBAR: comprehensive resource of biomedical relations with knowledge graph representations}\",\njournal = {Nucleic Acids Research},\nvolume = {49},\nnumber = {16},\npages = {e96-e96},\nyear = {2021},\nmonth = {06},\nissn = {0305-1048},\ndoi = {10.1093/nar/gkab543},\nurl = {https://doi.org/10.1093/nar/gkab543},\n}"
 templates:
-    - The {node1_name#} {rel1_type#} {node2_name#}.
+  - The {node1_name#} {rel1_type#} {node2_name#}.
-Original file line number
+Diff line change
@@ Expand Up / @@ -144,3 +144,5 @@ scratch/ @@
     # vim
     *~
     *.swp
+    .DS_Store