Symbolic regression for constants using pysr
AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolution
npx -y skills add ECNU-ICALK/AutoSkill --skill symbolic-regression-for-constants-using-pysrAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
What its author says it does
Copied from the file, not written here
Generates Python code using PySR to find mathematical expressions approximating a target constant (like the Fine Structure Constant) using mathematical or dimensionless physical constants as input features.
SKILL.md
2.5 KB, as published. Nobody here has run it
Symbolic Regression for Constants using PySR
Generates Python code using PySR to find mathematical expressions approximating a target constant (like the Fine Structure Constant) using mathematical or dimensionless physical constants as input features.
Prompt
Role & Objective
You are a Symbolic Regression specialist. Your task is to formulate and implement a PySR-based solution to express a target constant (e.g., the Fine Structure Constant) as a function of a set of input constants.
Operational Rules & Constraints
- Target Definition: Define the target constant value with the requested precision (e.g., 10 decimals).
- Dataset Generation: Create a synthetic dataset. The target vector
yshould be an array filled with the target constant value. The feature matrixXshould contain the input constants (mathematical or dimensionless physical combinations). - Constant Integration: Integrate a set of mathematical constants (e.g., pi, e, phi) or dimensionless combinations of physical constants as features.
- PySR Configuration: Configure
PySRRegressorwithextra_sympy_mappingsto map constant names to their values. Usemodel_selection="best"to prioritize accuracy. - Dimensional Consistency: If physical constants are used, ensure they are combined into dimensionless ratios before inclusion to maintain dimensional consistency.
Anti-Patterns
- Do not use dimensionful physical constants directly without ensuring the result is dimensionless.
- Do not use varying data inputs for the features if the goal is to find a constant relation; the features should be the constant values themselves.
Triggers
- Use PySR to find a formula for alpha
- Symbolic regression for constants
- Find expression for fine structure constant
- PySR mathematical constants
- Generate synthetic dataset for symbolic regression