srbf 0.1.0

srbf: the symbolic-regression evaluation framework (engine, adapters, benchmarks, metrics) carved from flash-ansr.

srbf: Symbolic Regression Benchmark Framework

srbf evaluates symbolic-regression models on shared benchmarks with shared metrics. It is the evaluation framework carved out of flash-ansr: the evaluation engine, model adapters, benchmarks, and metrics. It depends one-way on flash-ansr (srbf imports flash-ansr; flash-ansr never imports srbf).

Built for contributions. Developers of SR methods add their model by opening a PR with an adapter (two methods) plus install instructions. The built-in adapters (flash_ansr, pysr, nesymres, e2e, skeleton_pool, brute_force) are reference examples, not a closed set. See the adapter contribution guide.

Status: 0.1, cleanly-carved eval. The engine seam (srbf.eval.core Protocols + srbf.eval.engine) is model-agnostic, but every built-in adapter imports flash-ansr and the adapter set is a registry edited by PR. A plugin register_adapter() entry-point and raw-dataset ((X, y) CSV/parquet) ingestion are planned follow-ons.

Install

pip install srbf                 # engine + metrics + the pip-installable adapters (flash-ansr, PySR)
pip install "srbf[baselines]"    # + pip baseline deps (sympy, pysr, omegaconf)

srbf pulls in flash-ansr and simplipy automatically. The unpackaged research baselines (NeSymReS, E2E) are provisioned out-of-band; see docs/models.md.

Quickstart

# 1. point srbf at a tree holding configs/, data/, and models/ (your srbf checkout works)
export FLASH_ANSR_ROOT=$(pwd)

# 2. get a model to evaluate (flash-ansr's CLI ships with srbf)
flash_ansr install psaegert/flash-ansr-v23.0-3M

# 3. fetch a benchmark + build its skeleton pool   (see docs/benchmarks.md)
#    ...then run an evaluation:
srbf run -c configs/evaluation/scaling/v23.0-3M_val.yaml --limit 50 -v

Outputs land under results/evaluation/.../*.pkl, one row per evaluated dataset with flat metric columns. Run programmatically instead:

from srbf import build_evaluation_run

plan = build_evaluation_run(config="configs/evaluation/scaling/v23.0-3M_val.yaml")
plan.engine.run(limit=plan.remaining, output_path=plan.output_path)

Documentation

Guide	What it covers
Running evaluations	the srbf run CLI, config anatomy (data_source / model_adapter / runner / experiments), outputs, resume
Benchmarks & datasets	fetching FastSRB, building skeleton pools with flash_ansr import-data, custom sets
Models & provisioning	installing/patching the built-in models; the model_adapter block per type
Adding your model	the adapter protocol + registry, and the PR flow to contribute a new SR method

Development

pip install -e ".[dev]"
pre-commit run --all-files
pytest tests

License

MIT (see LICENSE). Third-party attributions in THIRD_PARTY_LICENSES.