pycurate 0.4.0__tar.gz

pycurate-0.4.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

pycurate-0.4.0/PKG-INFO

@@ -0,0 +1,118 @@
+Metadata-Version: 2.4
+Name: pycurate
+Version: 0.4.0
+Summary: Automatic data curation and curation auto-research: signals as zero-copy columns, recipes as views, agents that search recipes against a fixed eval.
+License: Apache-2.0
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23
+Requires-Dist: pyarrow>=14
+Requires-Dist: lancedb>=0.40
+Requires-Dist: pylance>=0.30
+Provides-Extra: torch
+Requires-Dist: torch>=2.2; extra == "torch"
+Provides-Extra: text
+Requires-Dist: transformers>=4.45; extra == "text"
+Requires-Dist: tiktoken; extra == "text"
+Requires-Dist: fasttext-numpy2; extra == "text"
+Provides-Extra: vision
+Requires-Dist: transformers>=4.45; extra == "vision"
+Requires-Dist: open_clip_torch; extra == "vision"
+Requires-Dist: pillow; extra == "vision"
+Requires-Dist: webdataset; extra == "vision"
+Provides-Extra: dense
+Requires-Dist: cleanlab>=2.6; extra == "dense"
+Requires-Dist: pycocotools; extra == "dense"
+Requires-Dist: scipy; extra == "dense"
+Requires-Dist: transformers>=4.45; extra == "dense"
+Requires-Dist: pillow; extra == "dense"
+Provides-Extra: research
+Requires-Dist: optuna; extra == "research"
+Requires-Dist: anthropic; extra == "research"
+Provides-Extra: test
+Requires-Dist: pytest>=7; extra == "test"
+Requires-Dist: scikit-learn>=1.2; extra == "test"
+Provides-Extra: docs
+Requires-Dist: mkdocs-material>=9.5; extra == "docs"
+Requires-Dist: mkdocstrings[python]>=0.25; extra == "docs"
+Provides-Extra: all
+Requires-Dist: pycurate[dense,research,text,torch,vision]; extra == "all"
+Dynamic: license-file
+
+# pycurate
+
+Curation is a compute multiplier: train on the right subset of your data and you reach the same quality with less
+compute. pycurate does it in one call. Point it at a table of training data. It detects what kind of data it is,
+scores every row with the signals that matter for that kind, applies the strongest established public filter, and
+hands you the subset to train on as a view: read straight from the table without copying it, in a globally shuffled
+order. Seven kinds of data are routed from the schema: web text, noisy labels, image-text pairs, SFT chats,
+preference pairs, RL prompts and robot episodes. Nothing in a default path calls an LLM. Give it your evaluation and
+it tunes the recipe; add `agent=True` and an LLM agent surveys the literature and writes recipes. A tuned recipe is
+applied only if it beats the default on your held-out metric. This is research code, and APIs may change.
+
+## Install
+
+```bash
+pip install "pycurate[all]"   # torch, transformers, fastText (DCLM), open_clip, optuna (TPE search), anthropic (opt-in agent)
+# from a checkout: pip install -e ".[all]"
+```
+
+## One verb, three levels
+
+```python
+import pycurate as pc
+
+ds = pc.load("data/*.parquet", name="pool", uri="./db")      # parquet, pandas, pyarrow, hf://... into a Lance table
+
+def train_eval(recipe, ids):                                 # your proxy training; higher is better
+    model = train(ds.view(ids, columns=["text"]))
+    return {"score": evaluate(model), "heldout": evaluate(model)}   # use a held-out set the search never sees
+```
+
+```python
+cur = pc.curate(ds)                                          # 1. default: domain recipe, no LLM, no training
+cur = pc.curate(ds, eval=train_eval, budget=8)               # 2. tuned: TPE on your eval, guarded by the default
+cur = pc.curate(ds, eval=train_eval, budget=8, agent=True)   # 3. agent: literature signals + LLM recipes, guarded
+print(cur, cur.report["level"], cur.report["guard"])         # what ran, what was picked and why
+loader = cur.to_torch(columns=["text"], batch_size=256)      # zero-copy, globally shuffled batches
+```
+
+`pc.diagnose(ds)` runs pre-flight checks before you spend compute. Level 2 is TPE by default (no LLM); level 3 is
+opt-in and the only path that calls an LLM (a logged-in `claude` CLI, `ANTHROPIC_API_KEY`, `OPENAI_API_KEY` or the
+`codex` CLI). Without `eval=`, `agent=True` only runs signal discovery and applies the default. Every signal is a
+column, cataloged with its citations and provenance. Tables live on local disk or an object store (S3).
+
+## Defaults
+
+| kind of data | detected from | `pc.curate(ds)` applies | vs no curation |
+|---|---|---|---|
+| web text | one long text column | DCLM fastText top 10% + SemDeDup | 1.8× (GPT-2-small, 4B tokens) |
+| image-text pairs | image + caption | DFN top 30% + SemDeDup | 3.3× (DataComp-medium) |
+| noisy labels | a class label column | lowest k-NN label disagreement per class | 1.0-6.0×, median 2.8× (13 tasks) |
+| SFT chats | `messages` or prompt/response | reward-model top 50% + prompt SemDeDup | 2.2× (Tulu-3 → Qwen2.5-0.5B) |
+| preference pairs | prompt/chosen/rejected | top 75% by reward-model margin | better held-out z; no curve |
+| RL prompts | problem/answer | learnability: 0 < pass rate < 1, ranked by p(1-p) | ≈1× |
+| robot episodes | episode/action columns | lowest k-NN task-label disagreement per task | n.s. on small sims |
+| object detection / instance masks | box-list or COCO annotation column | ObjectLab: drop flagged images | not benchmarked |
+| semantic segmentation | image + label map | cleanlab.segmentation score ≥ 0.1 | not benchmarked |
+
+Each is a compute multiplier against training on the whole pool at matched quality, read off measured curves and
+never extrapolated (gross; DataComp-medium is the 80.2M-pair pool). An agent-searched recipe scored above DFN top 30%
+there on all 3 seeds (3.90×, p = 0.051). Net of curation compute, and against the strongest public filter, see
+[results](docs/results.md#headline-results). Fallbacks when a model cannot run are logged in `cur.report`.
+
+## Docs
+
+`pip install -e ".[docs]" && mkdocs serve`, or read them in [docs/](docs/index.md):
+[quickstart](docs/quickstart.md) · [which level do I need?](docs/which_level.md) ·
+[the guard](docs/guard.md) · [guides](docs/guides/lm_pretraining.md) · [agent mode](docs/agent.md) ·
+[API](docs/api/index.md) · [results](docs/results.md) · [benchmarks](docs/benchmarks.md) ·
+[contributing](docs/contributing.md).
+Runnable before/after examples on real noisy data (CIFAR-10N, FineWeb, COCO, VOC): [docs/examples.md](docs/examples.md#example-scripts).
+
+**Continuing the project?** Start at [HANDOFF.md](HANDOFF.md) (state, results, open items); the full account of what was built and why is [docs/DEVELOPMENT_HISTORY.md](docs/DEVELOPMENT_HISTORY.md), and the day-by-day log is [bench/PLAN.md](bench/PLAN.md).
+
+## License
+
+Apache-2.0.

pycurate-0.4.0/README.md

@@ -0,0 +1,76 @@
+# pycurate
+
+Curation is a compute multiplier: train on the right subset of your data and you reach the same quality with less
+compute. pycurate does it in one call. Point it at a table of training data. It detects what kind of data it is,
+scores every row with the signals that matter for that kind, applies the strongest established public filter, and
+hands you the subset to train on as a view: read straight from the table without copying it, in a globally shuffled
+order. Seven kinds of data are routed from the schema: web text, noisy labels, image-text pairs, SFT chats,
+preference pairs, RL prompts and robot episodes. Nothing in a default path calls an LLM. Give it your evaluation and
+it tunes the recipe; add `agent=True` and an LLM agent surveys the literature and writes recipes. A tuned recipe is
+applied only if it beats the default on your held-out metric. This is research code, and APIs may change.
+
+## Install
+
+```bash
+pip install "pycurate[all]"   # torch, transformers, fastText (DCLM), open_clip, optuna (TPE search), anthropic (opt-in agent)
+# from a checkout: pip install -e ".[all]"
+```
+
+## One verb, three levels
+
+```python
+import pycurate as pc
+
+ds = pc.load("data/*.parquet", name="pool", uri="./db")      # parquet, pandas, pyarrow, hf://... into a Lance table
+
+def train_eval(recipe, ids):                                 # your proxy training; higher is better
+    model = train(ds.view(ids, columns=["text"]))
+    return {"score": evaluate(model), "heldout": evaluate(model)}   # use a held-out set the search never sees
+```
+
+```python
+cur = pc.curate(ds)                                          # 1. default: domain recipe, no LLM, no training
+cur = pc.curate(ds, eval=train_eval, budget=8)               # 2. tuned: TPE on your eval, guarded by the default
+cur = pc.curate(ds, eval=train_eval, budget=8, agent=True)   # 3. agent: literature signals + LLM recipes, guarded
+print(cur, cur.report["level"], cur.report["guard"])         # what ran, what was picked and why
+loader = cur.to_torch(columns=["text"], batch_size=256)      # zero-copy, globally shuffled batches
+```
+
+`pc.diagnose(ds)` runs pre-flight checks before you spend compute. Level 2 is TPE by default (no LLM); level 3 is
+opt-in and the only path that calls an LLM (a logged-in `claude` CLI, `ANTHROPIC_API_KEY`, `OPENAI_API_KEY` or the
+`codex` CLI). Without `eval=`, `agent=True` only runs signal discovery and applies the default. Every signal is a
+column, cataloged with its citations and provenance. Tables live on local disk or an object store (S3).
+
+## Defaults
+
+| kind of data | detected from | `pc.curate(ds)` applies | vs no curation |
+|---|---|---|---|
+| web text | one long text column | DCLM fastText top 10% + SemDeDup | 1.8× (GPT-2-small, 4B tokens) |
+| image-text pairs | image + caption | DFN top 30% + SemDeDup | 3.3× (DataComp-medium) |
+| noisy labels | a class label column | lowest k-NN label disagreement per class | 1.0-6.0×, median 2.8× (13 tasks) |
+| SFT chats | `messages` or prompt/response | reward-model top 50% + prompt SemDeDup | 2.2× (Tulu-3 → Qwen2.5-0.5B) |
+| preference pairs | prompt/chosen/rejected | top 75% by reward-model margin | better held-out z; no curve |
+| RL prompts | problem/answer | learnability: 0 < pass rate < 1, ranked by p(1-p) | ≈1× |
+| robot episodes | episode/action columns | lowest k-NN task-label disagreement per task | n.s. on small sims |
+| object detection / instance masks | box-list or COCO annotation column | ObjectLab: drop flagged images | not benchmarked |
+| semantic segmentation | image + label map | cleanlab.segmentation score ≥ 0.1 | not benchmarked |
+
+Each is a compute multiplier against training on the whole pool at matched quality, read off measured curves and
+never extrapolated (gross; DataComp-medium is the 80.2M-pair pool). An agent-searched recipe scored above DFN top 30%
+there on all 3 seeds (3.90×, p = 0.051). Net of curation compute, and against the strongest public filter, see
+[results](docs/results.md#headline-results). Fallbacks when a model cannot run are logged in `cur.report`.
+
+## Docs
+
+`pip install -e ".[docs]" && mkdocs serve`, or read them in [docs/](docs/index.md):
+[quickstart](docs/quickstart.md) · [which level do I need?](docs/which_level.md) ·
+[the guard](docs/guard.md) · [guides](docs/guides/lm_pretraining.md) · [agent mode](docs/agent.md) ·
+[API](docs/api/index.md) · [results](docs/results.md) · [benchmarks](docs/benchmarks.md) ·
+[contributing](docs/contributing.md).
+Runnable before/after examples on real noisy data (CIFAR-10N, FineWeb, COCO, VOC): [docs/examples.md](docs/examples.md#example-scripts).
+
+**Continuing the project?** Start at [HANDOFF.md](HANDOFF.md) (state, results, open items); the full account of what was built and why is [docs/DEVELOPMENT_HISTORY.md](docs/DEVELOPMENT_HISTORY.md), and the day-by-day log is [bench/PLAN.md](bench/PLAN.md).
+
+## License
+
+Apache-2.0.

pycurate-0.4.0/pyproject.toml

@@ -0,0 +1,31 @@
+[build-system]
+requires = ["setuptools>=64"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pycurate"
+version = "0.4.0"
+description = "Automatic data curation and curation auto-research: signals as zero-copy columns, recipes as views, agents that search recipes against a fixed eval."
+readme = "README.md"
+license = { text = "Apache-2.0" }
+requires-python = ">=3.10"
+dependencies = ["numpy>=1.23", "pyarrow>=14", "lancedb>=0.40", "pylance>=0.30"]
+
+[project.optional-dependencies]
+# faiss is optional so an existing faiss-gpu install is never replaced; install faiss-cpu or faiss-gpu yourself.
+torch = ["torch>=2.2"]
+text = ["transformers>=4.45", "tiktoken", "fasttext-numpy2"]  # fasttext-numpy2: maintained fastText wheels (DCLM / FineWeb-Edu text defaults)
+vision = ["transformers>=4.45", "open_clip_torch", "pillow", "webdataset"]
+dense = ["cleanlab>=2.6", "pycocotools", "scipy", "transformers>=4.45", "pillow"]  # detection / segmentation domains (ObjectLab, cleanlab.segmentation, COCO masks)
+research = ["optuna", "anthropic"]  # optuna: TPE (the default pc.search strategy); anthropic: opt-in agent
+test = ["pytest>=7", "scikit-learn>=1.2"]
+docs = ["mkdocs-material>=9.5", "mkdocstrings[python]>=0.25"]  # the docs site: mkdocs serve / mkdocs build --strict
+all = ["pycurate[torch,text,vision,dense,research]"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+markers = ["gpu: runs the examples on a CUDA GPU at reduced size (opt-in: pytest -m gpu; skipped without CUDA)"]
+addopts = "-m 'not gpu'"

pycurate-0.4.0/setup.cfg

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