Opensourcing the citation-graph repo

.github/workflows/ci.yaml

@@ -0,0 +1,70 @@
+name: CI
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+  workflow_dispatch:
+    inputs:
+      debug_enabled:
+        description: "Run the build with tmate debugging enabled"
+        required: false
+
+jobs:
+  linting:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout latest commit
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # fetch all history with version tags
+      - name: Set up python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.10"
+      - name: Set up pip cache
+        uses: actions/cache@v2
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('**/pyproject.toml') }}
+      - name: Set up environment
+        run: |
+          pip install --upgrade pip wheel setuptools
+          pip install black==24.4.2 flake8==6.0.0 flake8-builtins==2.1.0 flake8-bugbear==22.10.27 flake8-comprehensions==3.10.1 flake8-docstrings==1.6.0 toml-sort==0.23.1 isort==5.12.0 mypy
+      - name: Linting check
+        run: |
+          black --check src/
+          flake8 src/
+          isort --check src/
+          toml-sort --check pyproject.toml
+          mypy src/ --ignore-missing-imports
+  unit-tests:
+    runs-on: ${{ matrix.os }}
+    env:
+      PIP_CACHE_DIR: .cache/pip
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python-version: ["3.10"]
+    steps:
+      - name: Checkout latest commit
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0 # fetch all history with version tags
+      - name: Set up python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Set up pip cache
+        uses: actions/cache@v2
+        with:
+          path: .cache/pip
+          key: ${{ matrix.tox-env }}-${{ matrix.os }}
+      - name: Set up environment
+        run: |
+          pip install --upgrade pip
+          pip install ".[dev]"
+      - name: Running mypy and tests
+        run: |
+          pytest --cov=src --cov-report=html tests

.gitignore

@@ -0,0 +1,181 @@
+# Data dir except dvc files
+
+data/*.csv
+data/*.json
+data/*.jsonl
+data/*.md
+!data/*.dvc
+!data/pdfs/*.dvc
+!data/author_profiles
+!data/author_profiles/*.dvc
+!data/bbp_publications
+!data/bbp_publications/pdfs/*.dvc
+!data/clustering/
+!data/clustering/*.dvc
+!data/articles
+!data/articles/orcid/*.dvc
+!data/articles/author_name/*.dvc
+!data/author_profiles/orcid/*.dvc
+!data/author_profiles/serp/*.dvc
+!data/bbp_publications/*.dvc
+
+# Custom entries
+/.idea/
+.DS_Store
+.env*
+!.env*.example
+.python-version
+.vscode
+.pypirc
+
+# Version file
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# static files generated from Django application using `collectstatic`
+media
+static
+
+# ignore flask app related filess
+statuc
+yarn.lock
+templates
+node_modules

data_checks/conftest.py

@@ -0,0 +1,72 @@
+"""Configuration for data tests."""
+
+import json
+import os
+
+import pandas as pd
+import pytest
+
+
+@pytest.fixture(scope="session")
+def articles():
+    """Return articles data."""
+    return pd.read_csv(
+        os.path.join("data", "articles.csv"), dtype={"pmid": str}
+    )
+
+
+@pytest.fixture(scope="session")
+def authors():
+    """Return authors data."""
+    return pd.read_csv(os.path.join("data", "authors.csv"))
+
+
+@pytest.fixture(scope="session")
+def institutions():
+    """Return institutions data."""
+    return pd.read_csv(os.path.join("data", "institutions.csv"))
+
+
+@pytest.fixture(scope="session")
+def article_cites_article():
+    """Return citation data."""
+    return pd.read_csv(os.path.join("data", "article_cites_article.csv"))
+
+
+@pytest.fixture(scope="session")
+def author_wrote_article():
+    """Return author wrote data."""
+    return pd.read_csv(os.path.join("data", "author_wrote_article.csv"))
+
+
+@pytest.fixture(scope="session")
+def author_affiliated_with_institution():
+    """Return affiliation data."""
+    return pd.read_csv(
+        os.path.join("data", "author_affiliated_with_institution.csv")
+    )
+
+
+@pytest.fixture(scope="session")
+def embedded_article_uids():
+    """Return embedding uids."""
+    uids = []
+    with open(
+        os.path.join("data", "articles_embedded.jsonl"), "r", encoding="utf-8"
+    ) as articles_file:
+        for line in articles_file:
+            embedded_article = json.loads(line)
+            uids.append(embedded_article["article_uid"])
+    return uids
+
+
+@pytest.fixture(scope="session")
+def clusterings():
+    """Return all clusterings."""
+    clustering_dir = os.path.join("data", "clustering")
+    clusterings = {}
+    for clustering in os.listdir(clustering_dir):
+        clustering_path = os.path.join(clustering_dir, clustering)
+        with open(clustering_path, "r", encoding="utf-8") as clustering_file:
+            clusterings[clustering] = json.load(clustering_file)
+    return clusterings

pyproject.toml

@@ -0,0 +1,71 @@
+[build-system]
+requires = ["setuptools"]
+
+[project]
+name = "citations"
+authors = [
+  {name = "Blue Brain Project, EPFL"}
+]
+description = "Tools for analysing Blue Brain citations"
+readme = "README.md"
+requires-python = ">=3.10"
+dynamic = ["version"]
+dependencies = [
+  "dvc-s3",
+  "httpx",
+  "pandas",
+  "tqdm",
+  "pydantic",
+  "openai",
+  "asyncio",
+  "aiohttp",
+  "python-dotenv",
+  "scikit-learn",
+  "neo4j",
+  "serpapi"
+]
+
+[project.optional-dependencies]
+dev = [
+  "black==24.4.2",
+  "flake8==6.0.0",
+  "flake8-builtins==2.1.0",
+  "flake8-bugbear==22.10.27",
+  "flake8-comprehensions==3.10.1",
+  "flake8-docstrings==1.6.0",
+  "toml-sort==0.23.1",
+  "isort==5.12.0",
+  "pytest==8.2.1",
+  "pytest_httpx",
+  "pytest-cov",
+  "types-PyYAML",
+  "validators",
+  "pandas-stubs",
+  "types-tqdm",
+  "mypy"
+]
+
+[project.scripts]
+gather_articles = "citations.scripts.gather_articles:main"
+gather_authors = "citations.scripts.gather_authors:main"
+
+[tool.black]
+line-length = 79
+preview = true
+
+[tool.isort]
+profile = "black"
+line_length = 79
+
+[tool.pytest.ini_options]
+addopts = "--cov=src --cov-report=html --cov-config=.coveragerc"
+
+[tool.setuptools.dynamic]
+version = {attr = "citations.__version__"}
+
+[tool.setuptools.packages.find]
+where = ["src"]
+namespaces = false
+
+[tool.tomlsort]
+in_place = true