GoKawiilNew Rust tool Keplearn derives equations from raw data tables
Keplearn is a symbolic regression engine, written in Rust, that reads CSV or TSV data from stdin and outputs candidate closed-form equations as JSON. It ships as a single static binary with no dependencies, runs deterministically so identical inputs always produce identical outputs, and is designed to resolve exact laws within milliseconds while using a timeout for harder cases.
GoKawiil's interpretation of the reporting above, not reported fact.
By snapping fitted constants to rationals and known mathematical constants like pi and e, and verifying each snap before accepting it, the tool aims to produce clean, interpretable formulas rather than approximate fits. Its deterministic, byte-for-byte reproducible output could make it useful for researchers or engineers who need reliable, auditable results rather than probabilistic estimates from typical machine learning fitting tools.
- Keplearn recovers closed-form equations from tabular data using symbolic regression written in Rust.
- It is deterministic and produces reproducible output, with reported r2 values computed from the printed equation itself.
- Available as a free static binary for macOS, Windows, and Linux with no external dependencies.
Source: github.com, 2026-10-29
Published there as: “Keplearn: Extract Equations from Data in Seconds”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.