tabdat-synth 0.1.0__tar.gz

tabdat_synth-0.1.0/LICENSE

@@ -0,0 +1,159 @@
+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.
+
+"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

tabdat_synth-0.1.0/PKG-INFO

@@ -0,0 +1,172 @@
+Metadata-Version: 2.4
+Name: tabdat-synth
+Version: 0.1.0
+Summary: Spec-driven tabular data synthesis with reusable fitted bundles.
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/SaehwanPark/tabdat-synth
+Project-URL: Repository, https://github.com/SaehwanPark/tabdat-synth
+Project-URL: Documentation, https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/user-manual.md
+Keywords: synthetic-data,tabular-data,data-generation,research
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: lightgbm>=4.6.0
+Requires-Dist: numpy>=2.2.0
+Requires-Dist: pandas>=2.3.0
+Requires-Dist: polars>=1.40.1
+Requires-Dist: PyYAML>=6.0.2
+Requires-Dist: pyarrow>=18.0.0
+Requires-Dist: scikit-learn>=1.6.0
+Requires-Dist: scipy>=1.15.0
+Provides-Extra: env
+Requires-Dist: python-dotenv>=1.2.2; extra == "env"
+Dynamic: license-file
+
+# TabDat-Synth
+
+![banner](https://raw.githubusercontent.com/SaehwanPark/tabdat-synth/main/tabdat-learn-banner.png)
+
+TabDat-Synth is a Python package for spec-driven synthetic tabular data generation. It is intended for research, education, benchmarking, and data-science prototyping where real tabular data is sensitive, unavailable, or inconvenient to share.
+
+The package learns reusable synthesis artifacts from a source table, then generates new rows from an explicit directed acyclic graph (DAG) specification. It supports empirical sampling, conditioned categorical models, numeric summaries, coefficient-based outcomes, fitted bundle reuse, and evaluation reports.
+
+## Motivation
+
+Real tabular data often carries privacy, governance, licensing, or access constraints. These constraints can slow method development, teaching, and reproducible examples. TabDat-Synth provides a small, inspectable synthesis engine that can generate plausible tabular datasets while keeping assumptions visible in configuration.
+
+## Intended users
+
+| User group | Typical use | Relevant docs |
+| --- | --- | --- |
+| Research scientists | Simulate data for methods work, sensitivity analyses, and reproducible studies. | [Use cases](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/use-cases.md), [concepts](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/concepts.md) |
+| Data scientists and ML engineers | Prototype pipelines, benchmark models, and create shareable fixtures. | [Getting started](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/getting-started.md), [user manual](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/user-manual.md) |
+| Privacy and governance reviewers | Inspect whether generated data is too close to source records. | [Evaluation metrics](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/evaluation-metrics.md), [concepts](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/concepts.md) |
+| Educators and students | Build realistic classroom or workshop datasets without distributing restricted data. | [Getting started](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/getting-started.md), [examples](https://github.com/SaehwanPark/tabdat-synth/tree/main/docs/examples) |
+| Healthcare data collaborators | Work with public-style examples inspired by claims-data workflows. | [Data-file notes](https://github.com/SaehwanPark/tabdat-synth/tree/main/docs/datafiles-related) |
+
+## Features
+
+- Spec-driven generation from YAML configuration.
+- Directed synthesis workflows with stable topological execution.
+- Empirical, truncated-normal, categorical-model, coefficient-sum, sigmoid-probability, and Bernoulli-response steps.
+- Built-in categorical backends for LightGBM and logistic regression.
+- Reusable fitted bundles for generating later without the original source file.
+- Evaluation reports for marginal quality and row-level disclosure-risk heuristics.
+- Small public API designed for programmatic Python workflows.
+
+## How it works
+
+A synthesis run has five stages:
+
+1. Load a generation specification and source table.
+2. Prepare source columns according to the declared schema.
+3. Fit step-level artifacts in DAG order.
+4. Sample synthetic rows from the fitted artifacts.
+5. Evaluate the synthetic table against source data when appropriate.
+
+The DAG controls which generated columns are available to later steps. For categorical-model steps, declared parents define graph edges, and the fitted model receives the full incoming ancestor context in stable order.
+
+## Installation
+
+TabDat-Synth requires Python 3.12 or newer and is distributed on PyPI.
+
+```bash
+uv add tabdat-synth
+```
+
+For one-off installation into an active environment:
+
+```bash
+uv pip install tabdat-synth
+```
+
+For workflows that load local `.env` files through package helpers:
+
+```bash
+uv add "tabdat-synth[env]"
+```
+
+Because the package is alpha software, pin downstream projects to an exact release version when reproducibility matters.
+
+## Quick start
+
+Run the coefficient-based example from the repository root:
+
+```python
+from tabdat_synth import generate_from_spec, load_generation_spec
+
+spec = load_generation_spec("docs/examples/tiny_coefficient_outcomes.yaml")
+df = generate_from_spec(spec)
+
+print(df.shape)
+print(df.head())
+```
+
+Fit once, save a reusable bundle, and generate later:
+
+```python
+from tabdat_synth import (
+  fit_synthesizer,
+  generate_from_fitted,
+  load_fitted_synthesizer,
+  load_generation_spec,
+  save_fitted_synthesizer,
+)
+
+spec = load_generation_spec("docs/examples/de_synpuf_beneficiary_phase3.yaml")
+fitted = fit_synthesizer(spec)
+save_fitted_synthesizer(fitted, "tmp/de_synpuf_bundle")
+
+reloaded = load_fitted_synthesizer("tmp/de_synpuf_bundle")
+synthetic = generate_from_fitted(reloaded, n_samples=20, random_seed=999)
+print(synthetic.shape)
+```
+
+## Documentation
+
+- [Getting started](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/getting-started.md): installation, first run, and tests.
+- [Use cases](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/use-cases.md): user groups, workflows, and appropriate boundaries.
+- [Concepts](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/concepts.md): motivation, synthesis mechanism, fitted bundles, and limitations.
+- [User manual](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/user-manual.md): public API, step reference, backend configuration, and bundle details.
+- [Evaluation metrics](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/evaluation-metrics.md): fidelity metrics and disclosure-risk heuristics.
+- [Synthpop comparison](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/synthpop-comparison.md): conceptual relationship to R's `synthpop` package.
+
+## Acknowledgement
+
+TabDat-Synth is conceptually inspired by R's `synthpop` package and the broader statistical tradition of synthetic data generation.
+
+> Nowok, B., Raab, G. M., & Dibben, C. (2016). synthpop: Bespoke creation of synthetic data in R. *Journal of statistical software*, 74, 1-26.
+
+Note that this project is a cleanroom Python implementation, not built by reverse engineering `synthpop`, nor reuse `synthpop` source code.
+See [docs/synthpop-comparison.md](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/synthpop-comparison.md) for a full comparison.
+
+## Public API
+
+Common entry points:
+
+- `load_generation_spec(path)`
+- `generate_from_spec(spec)`
+- `fit_synthesizer(spec)`
+- `generate_from_fitted(fitted, *, n_samples=None, random_seed=None)`
+- `save_fitted_synthesizer(fitted, path)`
+- `load_fitted_synthesizer(path)`
+- `evaluate_synthetic_data(source_df, synthetic_df, schema, ...)`
+- `evaluate_from_spec(spec, synthetic_df, ...)`
+- `evaluation_report_to_dict(report)`
+- `save_evaluation_report(report, path)`
+
+## Testing
+
+```bash
+uv run --group dev pytest tests/unit tests/regression
+```
+
+## License
+
+Apache-2.0. See [LICENSE](LICENSE).

tabdat_synth-0.1.0/README.md

@@ -0,0 +1,142 @@
+# TabDat-Synth
+
+![banner](https://raw.githubusercontent.com/SaehwanPark/tabdat-synth/main/tabdat-learn-banner.png)
+
+TabDat-Synth is a Python package for spec-driven synthetic tabular data generation. It is intended for research, education, benchmarking, and data-science prototyping where real tabular data is sensitive, unavailable, or inconvenient to share.
+
+The package learns reusable synthesis artifacts from a source table, then generates new rows from an explicit directed acyclic graph (DAG) specification. It supports empirical sampling, conditioned categorical models, numeric summaries, coefficient-based outcomes, fitted bundle reuse, and evaluation reports.
+
+## Motivation
+
+Real tabular data often carries privacy, governance, licensing, or access constraints. These constraints can slow method development, teaching, and reproducible examples. TabDat-Synth provides a small, inspectable synthesis engine that can generate plausible tabular datasets while keeping assumptions visible in configuration.
+
+## Intended users
+
+| User group | Typical use | Relevant docs |
+| --- | --- | --- |
+| Research scientists | Simulate data for methods work, sensitivity analyses, and reproducible studies. | [Use cases](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/use-cases.md), [concepts](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/concepts.md) |
+| Data scientists and ML engineers | Prototype pipelines, benchmark models, and create shareable fixtures. | [Getting started](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/getting-started.md), [user manual](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/user-manual.md) |
+| Privacy and governance reviewers | Inspect whether generated data is too close to source records. | [Evaluation metrics](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/evaluation-metrics.md), [concepts](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/concepts.md) |
+| Educators and students | Build realistic classroom or workshop datasets without distributing restricted data. | [Getting started](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/getting-started.md), [examples](https://github.com/SaehwanPark/tabdat-synth/tree/main/docs/examples) |
+| Healthcare data collaborators | Work with public-style examples inspired by claims-data workflows. | [Data-file notes](https://github.com/SaehwanPark/tabdat-synth/tree/main/docs/datafiles-related) |
+
+## Features
+
+- Spec-driven generation from YAML configuration.
+- Directed synthesis workflows with stable topological execution.
+- Empirical, truncated-normal, categorical-model, coefficient-sum, sigmoid-probability, and Bernoulli-response steps.
+- Built-in categorical backends for LightGBM and logistic regression.
+- Reusable fitted bundles for generating later without the original source file.
+- Evaluation reports for marginal quality and row-level disclosure-risk heuristics.
+- Small public API designed for programmatic Python workflows.
+
+## How it works
+
+A synthesis run has five stages:
+
+1. Load a generation specification and source table.
+2. Prepare source columns according to the declared schema.
+3. Fit step-level artifacts in DAG order.
+4. Sample synthetic rows from the fitted artifacts.
+5. Evaluate the synthetic table against source data when appropriate.
+
+The DAG controls which generated columns are available to later steps. For categorical-model steps, declared parents define graph edges, and the fitted model receives the full incoming ancestor context in stable order.
+
+## Installation
+
+TabDat-Synth requires Python 3.12 or newer and is distributed on PyPI.
+
+```bash
+uv add tabdat-synth
+```
+
+For one-off installation into an active environment:
+
+```bash
+uv pip install tabdat-synth
+```
+
+For workflows that load local `.env` files through package helpers:
+
+```bash
+uv add "tabdat-synth[env]"
+```
+
+Because the package is alpha software, pin downstream projects to an exact release version when reproducibility matters.
+
+## Quick start
+
+Run the coefficient-based example from the repository root:
+
+```python
+from tabdat_synth import generate_from_spec, load_generation_spec
+
+spec = load_generation_spec("docs/examples/tiny_coefficient_outcomes.yaml")
+df = generate_from_spec(spec)
+
+print(df.shape)
+print(df.head())
+```
+
+Fit once, save a reusable bundle, and generate later:
+
+```python
+from tabdat_synth import (
+  fit_synthesizer,
+  generate_from_fitted,
+  load_fitted_synthesizer,
+  load_generation_spec,
+  save_fitted_synthesizer,
+)
+
+spec = load_generation_spec("docs/examples/de_synpuf_beneficiary_phase3.yaml")
+fitted = fit_synthesizer(spec)
+save_fitted_synthesizer(fitted, "tmp/de_synpuf_bundle")
+
+reloaded = load_fitted_synthesizer("tmp/de_synpuf_bundle")
+synthetic = generate_from_fitted(reloaded, n_samples=20, random_seed=999)
+print(synthetic.shape)
+```
+
+## Documentation
+
+- [Getting started](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/getting-started.md): installation, first run, and tests.
+- [Use cases](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/use-cases.md): user groups, workflows, and appropriate boundaries.
+- [Concepts](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/concepts.md): motivation, synthesis mechanism, fitted bundles, and limitations.
+- [User manual](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/user-manual.md): public API, step reference, backend configuration, and bundle details.
+- [Evaluation metrics](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/evaluation-metrics.md): fidelity metrics and disclosure-risk heuristics.
+- [Synthpop comparison](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/synthpop-comparison.md): conceptual relationship to R's `synthpop` package.
+
+## Acknowledgement
+
+TabDat-Synth is conceptually inspired by R's `synthpop` package and the broader statistical tradition of synthetic data generation.
+
+> Nowok, B., Raab, G. M., & Dibben, C. (2016). synthpop: Bespoke creation of synthetic data in R. *Journal of statistical software*, 74, 1-26.
+
+Note that this project is a cleanroom Python implementation, not built by reverse engineering `synthpop`, nor reuse `synthpop` source code.
+See [docs/synthpop-comparison.md](https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/synthpop-comparison.md) for a full comparison.
+
+## Public API
+
+Common entry points:
+
+- `load_generation_spec(path)`
+- `generate_from_spec(spec)`
+- `fit_synthesizer(spec)`
+- `generate_from_fitted(fitted, *, n_samples=None, random_seed=None)`
+- `save_fitted_synthesizer(fitted, path)`
+- `load_fitted_synthesizer(path)`
+- `evaluate_synthetic_data(source_df, synthetic_df, schema, ...)`
+- `evaluate_from_spec(spec, synthetic_df, ...)`
+- `evaluation_report_to_dict(report)`
+- `save_evaluation_report(report, path)`
+
+## Testing
+
+```bash
+uv run --group dev pytest tests/unit tests/regression
+```
+
+## License
+
+Apache-2.0. See [LICENSE](LICENSE).

tabdat_synth-0.1.0/pyproject.toml

@@ -0,0 +1,66 @@
+[build-system]
+requires = ["setuptools>=77", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "tabdat-synth"
+version = "0.1.0"
+description = "Spec-driven tabular data synthesis with reusable fitted bundles."
+readme = "README.md"
+requires-python = ">=3.12"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+keywords = [
+    "synthetic-data",
+    "tabular-data",
+    "data-generation",
+    "research",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Topic :: Scientific/Engineering",
+]
+dependencies = [
+    "lightgbm>=4.6.0",
+    "numpy>=2.2.0",
+    "pandas>=2.3.0",
+    "polars>=1.40.1",
+    "PyYAML>=6.0.2",
+    "pyarrow>=18.0.0",
+    "scikit-learn>=1.6.0",
+    "scipy>=1.15.0",
+]
+
+[project.optional-dependencies]
+env = [
+    "python-dotenv>=1.2.2",
+]
+
+[project.urls]
+Homepage = "https://github.com/SaehwanPark/tabdat-synth"
+Repository = "https://github.com/SaehwanPark/tabdat-synth"
+Documentation = "https://github.com/SaehwanPark/tabdat-synth/blob/main/docs/user-manual.md"
+
+[dependency-groups]
+dev = [
+    "pytest>=8.3.0",
+    "ruff>=0.15.0",
+    "twine>=6.2.0",
+]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+markers = [
+    "local_data: tests that require private or local data paths and explicit opt-in",
+]
+
+[tool.mypy]
+python_version = "3.12"
+ignore_missing_imports = true

tabdat_synth-0.1.0/setup.cfg

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

tabdat_synth-0.1.0/src/tabdat_synth/__init__.py

@@ -0,0 +1,67 @@
+"""Synthetic data generator package."""
+
+from tabdat_synth.version import __version__
+from tabdat_synth.domain.contracts import (
+  BernoulliResponseSpec,
+  CategoricalModelStepArtifact,
+  ColumnSpec,
+  CoefficientSumSpec,
+  CoefficientTerm,
+  ConfiguredStepArtifact,
+  EmpiricalStepArtifact,
+  DatasetSchema,
+  EvaluationReport,
+  FittedSynthesizer,
+  GenerationSpec,
+  GenerationStep,
+  MetricResult,
+  ModelBackendSpec,
+  TruncatedNormalStepArtifact,
+)
+from tabdat_synth.interfaces.bundles import (
+  load_fitted_synthesizer,
+  save_fitted_synthesizer,
+)
+from tabdat_synth.interfaces.io import load_generation_spec
+from tabdat_synth.interfaces.reports import (
+  evaluation_report_to_dict,
+  save_evaluation_report,
+)
+from tabdat_synth.workflows.evaluation import (
+  evaluate_from_spec,
+  evaluate_synthetic_data,
+)
+from tabdat_synth.workflows.pipelines import (
+  fit_synthesizer,
+  generate_from_fitted,
+  generate_from_spec,
+)
+
+__all__ = [
+  "__version__",
+  "BernoulliResponseSpec",
+  "CategoricalModelStepArtifact",
+  "ColumnSpec",
+  "CoefficientSumSpec",
+  "CoefficientTerm",
+  "ConfiguredStepArtifact",
+  "DatasetSchema",
+  "EmpiricalStepArtifact",
+  "EvaluationReport",
+  "MetricResult",
+  "FittedSynthesizer",
+  "GenerationSpec",
+  "GenerationStep",
+  "ModelBackendSpec",
+  "TruncatedNormalStepArtifact",
+  "evaluate_from_spec",
+  "evaluate_synthetic_data",
+  "evaluation_report_to_dict",
+  "fit_synthesizer",
+  "generate_from_fitted",
+  "generate_from_spec",
+  "load_fitted_synthesizer",
+  "load_generation_spec",
+  "save_evaluation_report",
+  "save_fitted_synthesizer",
+]

tabdat_synth-0.1.0/src/tabdat_synth/core/__init__.py

@@ -0,0 +1 @@
+"""Pure scientific kernels for synthetic data generation."""