# PySpark dependencies (required) | |
py4j | |
# PySpark dependencies (optional) | |
numpy | |
pyarrow | |
pandas | |
scipy | |
plotly | |
mlflow>=1.0 | |
sklearn | |
matplotlib<3.3.0 | |
# PySpark test dependencies | |
xmlrunner | |
# Linter | |
mypy | |
flake8 | |
# Documentation (SQL) | |
mkdocs | |
# Documentation (Python) | |
pydata_sphinx_theme | |
ipython | |
nbsphinx | |
numpydoc | |
jinja2<3.0.0 | |
sphinx<3.1.0 | |
sphinx-plotly-directive | |
# Development scripts | |
jira | |
PyGithub | |
# pandas API on Spark Code formatter. | |
black |