[project]
name = "ml-training-data"
version = "0.1.0"
description = "Pipeline that turns the EPC open-data CSV into ML training parquet + baseline models."
requires-python = ">=3.11"
dependencies = [
    "domna-domain",
    "pandas>=2.0",
    "pandas-stubs",
    "ijson>=3.2",
    "pyarrow>=15",
    "lightgbm>=4.0",
    "scikit-learn>=1.4",
    "httpx",
    "remotezip>=0.12",
]

[tool.uv.sources]
domna-domain = { workspace = true }

[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

[tool.hatch.build.targets.wheel]
packages = ["src/ml_training_data"]