symbolic-data 0.1.0__tar.gz

symbolic_data-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Paul Saegert
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

symbolic_data-0.1.0/PKG-INFO

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: symbolic-data
+Version: 0.1.0
+Summary: Model-agnostic symbolic-regression data layer: skeleton/expression sampling, priors, holdout, datasets.
+Author: Paul Saegert
+License-Expression: MIT
+Project-URL: Homepage, https://github.com/psaegert/symbolic-data
+Project-URL: Repository, https://github.com/psaegert/symbolic-data
+Keywords: symbolic-regression,dataset,sampling,holdout,expression
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy
+Requires-Dist: scikit-learn
+Requires-Dist: simplipy>=0.3.1
+Requires-Dist: pyyaml
+Requires-Dist: tqdm
+Requires-Dist: huggingface_hub
+Provides-Extra: sympy
+Requires-Dist: sympy; extra == "sympy"
+Provides-Extra: dev
+Requires-Dist: pytest; extra == "dev"
+Requires-Dist: pytest-cov; extra == "dev"
+Dynamic: license-file
+
+# symbolic_data
+
+The model-agnostic symbolic-regression **data layer**, carved out of
+[flash-ansr](https://github.com/psaegert/flash-ansr): skeleton/expression sampling,
+priors, `(X, y)` support sampling, holdout management, and dataset construction.
+
+Both symbolic-regression methods (for training holdout) and the
+[srbf](https://github.com/psaegert/srbf) eval framework depend on it, so training,
+holdout, and evaluation draw from one source of truth. Depends only on
+[`simplipy`](https://github.com/psaegert/simplipy) + numpy/sklearn.
+
+## Install
+
+```bash
+pip install symbolic-data
+```
+
+## Quick start
+
+```python
+import symbolic_data
+
+# 1. Sample (X, y) problems from a skeleton pool (the model-agnostic seam)
+pool = symbolic_data.SkeletonPool.from_config("skeleton_pool.yaml")
+pool.create(100)
+for sample in symbolic_data.iter_samples(pool, n_support=32, noise_level=0.01, seed=0):
+    sample.x_support, sample.y_support, sample.expression  # ready to fit / tokenize
+
+# 2. Load a benchmark (spec fetched + cached from the psaegert/ansr-data HF dataset)
+fastsrb = symbolic_data.load_benchmark("fastsrb")
+dataset = fastsrb.sample("II.38.3", n_points=100)
+```
+
+## Extensibility
+
+Distributions and benchmarks are pluggable via registries: in-process with
+`@symbolic_data.DISTRIBUTIONS.register("name")` / `@symbolic_data.BENCHMARKS.register("name")`, or
+across packages via `importlib.metadata` entry points (groups `symbolic_data.distributions`,
+`symbolic_data.benchmarks`). A registered name drops into the same config slot as a builtin.
+
+## Versioning / reproducibility
+
+v1 guarantees **leak-safety** (a seeded, shipped holdout grid + a robust symbolic/numeric
+matcher), not cross-consumer byte-identical regeneration (the rng-Generator threading is a
+separate, later phase). Benchmark specs are HF-versioned and stamped on `.provenance`.
+
+> Status: v0.1.0. Registry, `iter_samples` seam, and `load_benchmark` (FastSRB) are in.
+> Deferred: the MIA matched-control audit, curated benchmark loaders (Feynman/Nguyen), the
+> canonical-v1 holdout grid mint, and cross-consumer byte-identical sampling.

symbolic_data-0.1.0/README.md

@@ -0,0 +1,49 @@
+# symbolic_data
+
+The model-agnostic symbolic-regression **data layer**, carved out of
+[flash-ansr](https://github.com/psaegert/flash-ansr): skeleton/expression sampling,
+priors, `(X, y)` support sampling, holdout management, and dataset construction.
+
+Both symbolic-regression methods (for training holdout) and the
+[srbf](https://github.com/psaegert/srbf) eval framework depend on it, so training,
+holdout, and evaluation draw from one source of truth. Depends only on
+[`simplipy`](https://github.com/psaegert/simplipy) + numpy/sklearn.
+
+## Install
+
+```bash
+pip install symbolic-data
+```
+
+## Quick start
+
+```python
+import symbolic_data
+
+# 1. Sample (X, y) problems from a skeleton pool (the model-agnostic seam)
+pool = symbolic_data.SkeletonPool.from_config("skeleton_pool.yaml")
+pool.create(100)
+for sample in symbolic_data.iter_samples(pool, n_support=32, noise_level=0.01, seed=0):
+    sample.x_support, sample.y_support, sample.expression  # ready to fit / tokenize
+
+# 2. Load a benchmark (spec fetched + cached from the psaegert/ansr-data HF dataset)
+fastsrb = symbolic_data.load_benchmark("fastsrb")
+dataset = fastsrb.sample("II.38.3", n_points=100)
+```
+
+## Extensibility
+
+Distributions and benchmarks are pluggable via registries: in-process with
+`@symbolic_data.DISTRIBUTIONS.register("name")` / `@symbolic_data.BENCHMARKS.register("name")`, or
+across packages via `importlib.metadata` entry points (groups `symbolic_data.distributions`,
+`symbolic_data.benchmarks`). A registered name drops into the same config slot as a builtin.
+
+## Versioning / reproducibility
+
+v1 guarantees **leak-safety** (a seeded, shipped holdout grid + a robust symbolic/numeric
+matcher), not cross-consumer byte-identical regeneration (the rng-Generator threading is a
+separate, later phase). Benchmark specs are HF-versioned and stamped on `.provenance`.
+
+> Status: v0.1.0. Registry, `iter_samples` seam, and `load_benchmark` (FastSRB) are in.
+> Deferred: the MIA matched-control audit, curated benchmark loaders (Feynman/Nguyen), the
+> canonical-v1 holdout grid mint, and cross-consumer byte-identical sampling.

symbolic_data-0.1.0/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "symbolic-data"
+version = "0.1.0"
+description = "Model-agnostic symbolic-regression data layer: skeleton/expression sampling, priors, holdout, datasets."
+readme = "README.md"
+requires-python = ">=3.11"
+license = "MIT"
+authors = [{ name = "Paul Saegert" }]
+keywords = ["symbolic-regression", "dataset", "sampling", "holdout", "expression"]
+dependencies = [
+    "numpy",
+    "scikit-learn",
+    "simplipy>=0.3.1",
+    "pyyaml",
+    "tqdm",
+    "huggingface_hub",
+]
+
+[project.optional-dependencies]
+sympy = ["sympy"]
+dev = ["pytest", "pytest-cov"]
+
+[project.urls]
+Homepage = "https://github.com/psaegert/symbolic-data"
+Repository = "https://github.com/psaegert/symbolic-data"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.flake8]
+max-line-length = 250
+extend-ignore = ["E203", "W503"]
+per-file-ignores = ["__init__.py:F401"]
+exclude = [".git", "__pycache__", "build", "dist", ".venv", "venv"]

symbolic_data-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

symbolic_data-0.1.0/src/symbolic_data/__init__.py

@@ -0,0 +1,19 @@
+"""symbolic_data -- the model-agnostic symbolic-regression data layer.
+
+Skeleton/expression sampling, priors, (X, y) support sampling, holdout management, and
+dataset construction -- carved out of flash-ansr so symbolic-regression methods and the
+srbf eval framework share one data substrate. Depends only on simplipy + numpy/sklearn.
+"""
+from symbolic_data.skeleton_pool import SkeletonPool, NoValidSampleFoundError
+from symbolic_data.holdout import HoldoutManager
+from symbolic_data.skeleton_sampling import SkeletonSampler
+from symbolic_data.support_sampling import SupportSampler, SupportSamplingError
+from symbolic_data.distributions import get_distribution, DISTRIBUTIONS, BASE_DISTRIBUTIONS
+from symbolic_data.prior_factory import build_prior_callable
+from symbolic_data.registry import Registry
+from symbolic_data.samples import Sample, sample_from_skeleton, iter_samples
+from symbolic_data.tensor_ops import mask_unused_variable_columns
+from symbolic_data.datasets import load_benchmark, BENCHMARKS
+from symbolic_data.benchmarks import FastSRBBenchmark
+from symbolic_data.paths import get_path, get_root, substitute_root_path
+from symbolic_data.config_io import load_config, save_config

symbolic_data-0.1.0/src/symbolic_data/benchmarks/__init__.py

@@ -0,0 +1,4 @@
+"""Benchmark loaders (model-agnostic equation specs + (X, y) sampling)."""
+from symbolic_data.benchmarks.fastsrb import FastSRBBenchmark
+
+__all__ = ["FastSRBBenchmark"]