beautifulsoup4
click
html5lib
jsonschema
lxml
matplotlib
numpy
pandas
pdftotext>=3.0.0
pikepdf
Pillow>=9.2.0
pypdf[crypto]>=3.1.0
python-dateutil
dateparser
PyYAML
rapidfuzz
requests
scikit-learn
tabula-py
tqdm
setuptools-scm
ipykernel
ipywidgets
spacy
pkgconfig
seaborn
pySankeyBeta
scipy>=1.9.0
networkx
pydantic
pydantic-settings
psutil
pytesseract

[dev]
ruff==0.7.4
mypy==1.13.0
types-PyYAML
types-python-dateutil
types-requests
datasets
pytest
pytest-cov
pytest-monitor
pytest-profiling
pre-commit
pip-tools
sphinx
myst-nb>=0.14
sphinx-book-theme
sphinx-design
sphinx-copybutton
ipython!=8.7.0

[nlp]
catboost
optuna
setfit
umap-learn[plot]
plotly
scikit-learn

[test]
pytest
coverage
pytest-cov
