add pyproject.toml and lockfile.

README.md

@@ -22,11 +22,24 @@ pip install -e .
 ```
 
 If you run into cryptic errors about GCC on macOS while installing the requirments, try this instead:
+
 ```bash
 CFLAGS='-stdlib=libc++' pip install -r requirements.in
 ```
 
-## Data 
+Alternatively, you can use `uv`:
+
+```bash
+git clone https://github.com/allenai/S2APLER.git
+cd S2APLER
+uv venv
+source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+uv sync
+uv pip install -e .
+```
+
+## Data
+
 To obtain the paper clustering dataset, run the following command after the package is installed (from inside the `S2APLER` directory):  
 ```[Expected download size is: 3.1 GiB]```
 

pyproject.toml

@@ -0,0 +1,107 @@
+[project]
+name = "s2apler"
+version = "0.2.6"
+description = "S2APLER: Semantic Scholar (S2) Agglomeration of Papers with Low Error Rate"
+readme = "README.md"
+requires-python = ">=3.8"
+license = { text = "Apache-2.0" }
+authors = [
+    { name = "Allen Institute for Artificial Intelligence" }
+]
+keywords = ["clustering", "papers", "semantic-scholar", "machine-learning"]
+classifiers = [
+    "Development Status :: 4 - Beta",
+    "Intended Audience :: Science/Research",
+    "License :: OSI Approved :: Apache Software License",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.8",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+
+dependencies = [
+    "numpy>=1.23.4,<2",
+    "scikit-learn>=1.1.3",
+    "text-unidecode==1.3",
+    "requests==2.28.1",
+    "hyperopt==0.2.7",
+    "pandas==1.5.1",
+    "lightgbm>=3.3.5",
+    "fastcluster==1.2.6",
+    "shap==0.41.0",
+    "matplotlib>=3.6.2",
+    "seaborn==0.12.1",
+    "tqdm==4.64.1",
+    "jellyfish==0.9.0",
+    "pylatexenc==2.10",
+    "awscli>=1.27.12",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest==7.2.0",
+    "pytest-cov==4.0.0",
+    "flake8==5.0.4",
+    "black==22.10",
+    "click==8.0.4",
+    "mypy==0.991",
+    "pydantic==1.10.2",
+]
+
+[project.urls]
+Homepage = "https://github.com/allenai/S2APLER"
+Repository = "https://github.com/allenai/S2APLER"
+Issues = "https://github.com/allenai/S2APLER/issues"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[tool.hatch.build.targets.wheel]
+packages = ["s2apler"]
+
+[tool.uv]
+dev-dependencies = [
+    "pytest==7.2.0",
+    "pytest-cov==4.0.0",
+    "flake8==5.0.4",
+    "black==22.10",
+    "click==8.0.4",
+    "mypy==0.991",
+    "pydantic==1.10.2",
+]
+
+[tool.black]
+line-length = 120
+target-version = ["py38"]
+include = '\.pyi?$'
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+python_files = "test_*.py"
+python_classes = "Test*"
+python_functions = "test_*"
+addopts = "-v --cov=s2apler --cov-report=term-missing"
+
+[tool.mypy]
+python_version = "3.8"
+warn_return_any = true
+warn_unused_configs = true
+disallow_untyped_defs = false
+ignore_missing_imports = true
+
+[tool.coverage.run]
+source = ["s2apler"]
+omit = ["*/tests/*", "*/test_*.py"]
+
+[tool.coverage.report]
+exclude_lines = [
+    "pragma: no cover",
+    "def __repr__",
+    "raise AssertionError",
+    "raise NotImplementedError",
+    "if __name__ == .__main__.:",
+    "if TYPE_CHECKING:",
+]