sdgym 0.7.0.dev0__tar.gz → 0.8.0.dev0__tar.gz

sdgym-0.8.0.dev0/PKG-INFO

@@ -0,0 +1,237 @@
+Metadata-Version: 2.1
+Name: sdgym
+Version: 0.8.0.dev0
+Summary: Benchmark tabular synthetic data generators using a variety of datasets
+Author-email: "DataCebo, Inc." <info@sdv.dev>
+License: BSL-1.1
+Project-URL: Source Code, https://github.com/sdv-dev/SDGym/
+Project-URL: Issue Tracker, https://github.com/sdv-dev/SDGym/issues
+Project-URL: Changes, https://github.com/sdv-dev/SDGym/blob/main/HISTORY.md
+Project-URL: Twitter, https://twitter.com/sdv_dev
+Project-URL: Chat, https://bit.ly/sdv-slack-invite
+Keywords: machine learning,synthetic data generation,benchmark,generative models
+Classifier: Development Status :: 2 - Pre-Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: Free for non-commercial use
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: <3.13,>=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: appdirs>=1.3
+Requires-Dist: boto3<2,>=1.28
+Requires-Dist: botocore<2,>=1.31
+Requires-Dist: compress-pickle>=1.2.0
+Requires-Dist: humanfriendly>=8.2
+Requires-Dist: numpy>=1.21.0; python_version < "3.10"
+Requires-Dist: numpy<2,>=1.23.3; python_version >= "3.10" and python_version < "3.12"
+Requires-Dist: numpy<2,>=1.26.0; python_version >= "3.12"
+Requires-Dist: pandas>=1.4.0; python_version < "3.11"
+Requires-Dist: pandas>=1.5.0; python_version >= "3.11" and python_version < "3.12"
+Requires-Dist: pandas>=2.1.1; python_version >= "3.12"
+Requires-Dist: psutil>=5.7
+Requires-Dist: scikit-learn>=1.0.2; python_version < "3.10"
+Requires-Dist: scikit-learn>=1.1.0; python_version >= "3.10" and python_version < "3.11"
+Requires-Dist: scikit-learn>=1.1.3; python_version >= "3.11" and python_version < "3.12"
+Requires-Dist: scikit-learn>=1.3.1; python_version >= "3.12"
+Requires-Dist: scipy>=1.7.3; python_version < "3.10"
+Requires-Dist: scipy>=1.9.2; python_version >= "3.10" and python_version < "3.12"
+Requires-Dist: scipy>=1.12.0; python_version >= "3.12"
+Requires-Dist: tabulate<0.9,>=0.8.3
+Requires-Dist: torch>=1.9.0; python_version < "3.10"
+Requires-Dist: torch>=2.0.0; python_version >= "3.10" and python_version < "3.12"
+Requires-Dist: torch>=2.2.0; python_version >= "3.12"
+Requires-Dist: tqdm>=4.29
+Requires-Dist: XlsxWriter>=1.2.8
+Requires-Dist: rdt>=1.12.1
+Requires-Dist: sdmetrics>=0.14.1
+Requires-Dist: sdv>=1.13.1
+Provides-Extra: dask
+Requires-Dist: dask; extra == "dask"
+Requires-Dist: distributed; extra == "dask"
+Provides-Extra: test
+Requires-Dist: pytest>=6.2.5; extra == "test"
+Requires-Dist: pytest-cov>=2.6.0; extra == "test"
+Requires-Dist: jupyter<2,>=1.0.0; extra == "test"
+Requires-Dist: rundoc<0.5,>=0.4.3; extra == "test"
+Requires-Dist: tomli<3,>=2.0.0; extra == "test"
+Provides-Extra: dev
+Requires-Dist: sdgym[dask,test]; extra == "dev"
+Requires-Dist: build<2,>=1.0.0; extra == "dev"
+Requires-Dist: bump-my-version<1,>=0.18.3; extra == "dev"
+Requires-Dist: pip>=9.0.1; extra == "dev"
+Requires-Dist: watchdog<5,>=1.0.1; extra == "dev"
+Requires-Dist: ruff<1,>=0.4.5; extra == "dev"
+Requires-Dist: twine<6,>=1.10.0; extra == "dev"
+Requires-Dist: wheel>=0.30.0; extra == "dev"
+Requires-Dist: coverage<8,>=4.5.12; extra == "dev"
+Requires-Dist: tox<5,>=2.9.1; extra == "dev"
+Requires-Dist: importlib-metadata>=3.6; extra == "dev"
+Requires-Dist: invoke; extra == "dev"
+Provides-Extra: all
+Requires-Dist: sdgym[dask,dev,test]; extra == "all"
+
+<div align="center">
+<br/>
+<p align="center">
+    <i>This repository is part of <a href="https://sdv.dev">The Synthetic Data Vault Project</a>, a project from <a href="https://datacebo.com">DataCebo</a>.</i>
+</p>
+
+[![Development Status](https://img.shields.io/badge/Development%20Status-2%20--%20Pre--Alpha-yellow)](https://pypi.org/search/?c=Development+Status+%3A%3A+2+-+Pre-Alpha)
+[![Travis](https://travis-ci.org/sdv-dev/SDGym.svg?branch=main)](https://travis-ci.org/sdv-dev/SDGym)
+[![PyPi Shield](https://img.shields.io/pypi/v/sdgym.svg)](https://pypi.python.org/pypi/sdgym)
+[![Downloads](https://pepy.tech/badge/sdgym)](https://pepy.tech/project/sdgym)
+[![Slack](https://img.shields.io/badge/Community-Slack-blue?style=plastic&logo=slack)](https://bit.ly/sdv-slack-invite)
+
+<div align="left">
+<br/>
+<p align="center">
+<a href="https://github.com/sdv-dev/SDGym">
+<img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/stable/docs/images/SDGym-DataCebo.png"></img>
+</a>
+</p>
+</div>
+
+</div>
+
+# Overview
+
+The Synthetic Data Gym (SDGym) is a benchmarking framework for modeling and generating
+synthetic data. Measure performance and memory usage across different synthetic data modeling
+techniques – classical statistics, deep learning and more!
+
+<img align="center" src="docs/images/SDGym_Results.png"></img>
+
+The SDGym library integrates with the Synthetic Data Vault ecosystem. You can use any of its
+synthesizers, datasets or metrics for benchmarking. You can also customize the process to include
+your own work.
+
+* **Datasets**: Select any of the publicly available datasets from the SDV project, or input your own data.
+* **Synthesizers**: Choose from any of the SDV synthesizers and baselines. Or write your own custom
+machine learning model.
+* **Evaluation**: In addition to performance and memory usage, you can also measure synthetic data
+quality and privacy through a variety of metrics.
+
+# Install
+
+Install SDGym using pip or conda. We recommend using a virtual environment to avoid conflicts with other software on your device.
+
+```bash
+pip install sdgym
+```
+
+```bash
+conda install -c pytorch -c conda-forge sdgym
+```
+
+For more information about using SDGym, visit the [SDGym Documentation](https://docs.sdv.dev/sdgym).
+
+# Usage
+
+Let's benchmark synthetic data generation for single tables. First, let's define which modeling
+techniques we want to use. Let's choose a few synthesizers from the SDV library and a few others
+to use as baselines.
+
+```python
+# these synthesizers come from the SDV library
+# each one uses different modeling techniques
+sdv_synthesizers = ['GaussianCopulaSynthesizer', 'CTGANSynthesizer']
+
+# these basic synthesizers are available in SDGym
+# as baselines
+baseline_synthesizers = ['UniformSynthesizer']
+```
+
+Now, we can benchmark the different techniques:
+```python
+import sdgym
+
+sdgym.benchmark_single_table(
+    synthesizers=(sdv_synthesizers + baseline_synthesizers)
+)
+```
+
+The result is a detailed performance, memory and quality evaluation across the synthesizers
+on a variety of publicly available datasets.
+
+## Supplying a custom synthesizer
+
+Benchmark your own synthetic data generation techniques. Define your synthesizer by
+specifying the training logic (using machine learning) and the sampling logic.
+
+```python
+def my_training_logic(data, metadata):
+    # create an object to represent your synthesizer
+    # train it using the data
+    return synthesizer
+
+def my_sampling_logic(trained_synthesizer, num_rows):
+    # use the trained synthesizer to create
+    # num_rows of synthetic data
+    return synthetic_data
+```
+
+Learn more in the [Custom Synthesizers Guide](https://docs.sdv.dev/sdgym/customization/synthesizers/custom-synthesizers).
+
+## Customizing your datasets
+
+The SDGym library includes many publicly available datasets that you can include right away.
+List these using the ``get_available_datasets`` feature.
+
+```python
+sdgym.get_available_datasets()
+```
+
+```
+dataset_name   size_MB     num_tables
+KRK_v1         0.072128    1
+adult          3.907448    1
+alarm          4.520128    1
+asia           1.280128    1
+...
+```
+
+You can also include any custom, private datasets that are stored on your computer on an
+Amazon S3 bucket.
+
+```
+my_datasets_folder = 's3://my-datasets-bucket'
+```
+
+For more information, see the docs for [Customized Datasets](https://docs.sdv.dev/sdgym/customization/datasets).
+
+# What's next?
+
+Visit the [SDGym Documentation](https://docs.sdv.dev/sdgym) to learn more!
+
+---
+
+
+<div align="center">
+<a href="https://datacebo.com"><img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/stable/docs/images/DataCebo.png"></img></a>
+</div>
+<br/>
+<br/>
+
+[The Synthetic Data Vault Project](https://sdv.dev) was first created at MIT's [Data to AI Lab](
+https://dai.lids.mit.edu/) in 2016. After 4 years of research and traction with enterprise, we
+created [DataCebo](https://datacebo.com) in 2020 with the goal of growing the project.
+Today, DataCebo is the proud developer of SDV, the largest ecosystem for
+synthetic data generation & evaluation. It is home to multiple libraries that support synthetic
+data, including:
+
+* 🔄 Data discovery & transformation. Reverse the transforms to reproduce realistic data.
+* 🧠 Multiple machine learning models -- ranging from Copulas to Deep Learning -- to create tabular,
+  multi table and time series data.
+* 📊 Measuring quality and privacy of synthetic data, and comparing different synthetic data
+  generation models.
+
+[Get started using the SDV package](https://sdv.dev/SDV/getting_started/install.html) -- a fully
+integrated solution and your one-stop shop for synthetic data. Or, use the standalone libraries
+for specific needs.

{sdgym-0.7.0.dev0 → sdgym-0.8.0.dev0}/README.md

@@ -5,7 +5,7 @@
 </p>
 
 [![Development Status](https://img.shields.io/badge/Development%20Status-2%20--%20Pre--Alpha-yellow)](https://pypi.org/search/?c=Development+Status+%3A%3A+2+-+Pre-Alpha)
-[![Travis](https://travis-ci.org/sdv-dev/SDGym.svg?branch=master)](https://travis-ci.org/sdv-dev/SDGym)
+[![Travis](https://travis-ci.org/sdv-dev/SDGym.svg?branch=main)](https://travis-ci.org/sdv-dev/SDGym)
 [![PyPi Shield](https://img.shields.io/pypi/v/sdgym.svg)](https://pypi.python.org/pypi/sdgym)
 [![Downloads](https://pepy.tech/badge/sdgym)](https://pepy.tech/project/sdgym)
 [![Slack](https://img.shields.io/badge/Community-Slack-blue?style=plastic&logo=slack)](https://bit.ly/sdv-slack-invite)
@@ -14,7 +14,7 @@
 <br/>
 <p align="center">
 <a href="https://github.com/sdv-dev/SDGym">
-<img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/master/docs/images/SDGym-DataCebo.png"></img>
+<img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/stable/docs/images/SDGym-DataCebo.png"></img>
 </a>
 </p>
 </div>
@@ -135,7 +135,7 @@ Visit the [SDGym Documentation](https://docs.sdv.dev/sdgym) to learn more!
 
 
 <div align="center">
-<a href="https://datacebo.com"><img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/master/docs/images/DataCebo.png"></img></a>
+<a href="https://datacebo.com"><img align="center" width=40% src="https://github.com/sdv-dev/SDV/blob/stable/docs/images/DataCebo.png"></img></a>
 </div>
 <br/>
 <br/>

sdgym-0.8.0.dev0/pyproject.toml

@@ -0,0 +1,219 @@
+[project]
+name = 'sdgym'
+description = 'Benchmark tabular synthetic data generators using a variety of datasets'
+authors = [{ name = 'DataCebo, Inc.', email = 'info@sdv.dev' }]
+classifiers = [
+    'Development Status :: 2 - Pre-Alpha',
+    'Intended Audience :: Developers',
+    'License :: Free for non-commercial use',
+    'Natural Language :: English',
+    'Programming Language :: Python :: 3',
+    'Programming Language :: Python :: 3.8',
+    'Programming Language :: Python :: 3.9',
+    'Programming Language :: Python :: 3.10',
+    'Programming Language :: Python :: 3.11',
+    'Programming Language :: Python :: 3.12',
+    'Topic :: Scientific/Engineering :: Artificial Intelligence',
+]
+keywords = ['machine learning', 'synthetic data generation', 'benchmark', 'generative models']
+dynamic = ['version']
+license = { text = 'BSL-1.1' }
+requires-python = '>=3.8,<3.13'
+readme = 'README.md'
+dependencies = [
+    'appdirs>=1.3',
+    'boto3>=1.28,<2',
+    'botocore>=1.31,<2',
+    'compress-pickle>=1.2.0',
+    'humanfriendly>=8.2',
+    "numpy>=1.21.0;python_version<'3.10'",
+    "numpy>=1.23.3,<2;python_version>='3.10' and python_version<'3.12'",
+    "numpy>=1.26.0,<2;python_version>='3.12'",
+    "pandas>=1.4.0;python_version<'3.11'",
+    "pandas>=1.5.0;python_version>='3.11' and python_version<'3.12'",
+    "pandas>=2.1.1;python_version>='3.12'",
+    'psutil>=5.7',
+    "scikit-learn>=1.0.2;python_version<'3.10'",
+    "scikit-learn>=1.1.0;python_version>='3.10' and python_version<'3.11'",
+    "scikit-learn>=1.1.3;python_version>='3.11' and python_version<'3.12'",
+    "scikit-learn>=1.3.1;python_version>='3.12'",
+    "scipy>=1.7.3;python_version<'3.10'",
+    "scipy>=1.9.2;python_version>='3.10' and python_version<'3.12'",
+    "scipy>=1.12.0;python_version>='3.12'",
+    'tabulate>=0.8.3,<0.9',
+    "torch>=1.9.0;python_version<'3.10'",
+    "torch>=2.0.0;python_version>='3.10' and python_version<'3.12'",
+    "torch>=2.2.0;python_version>='3.12'",
+    'tqdm>=4.29',
+    'XlsxWriter>=1.2.8',
+    'rdt>=1.12.1',
+    'sdmetrics>=0.14.1',
+    'sdv>=1.13.1',
+]
+
+[project.urls]
+"Source Code"= "https://github.com/sdv-dev/SDGym/"
+"Issue Tracker" = "https://github.com/sdv-dev/SDGym/issues"
+"Changes" = "https://github.com/sdv-dev/SDGym/blob/main/HISTORY.md"
+"Twitter" = "https://twitter.com/sdv_dev"
+"Chat" = "https://bit.ly/sdv-slack-invite"
+
+[project.entry-points]
+sdgym = { main = 'sdgym.cli.__main__:main' }
+
+[project.optional-dependencies]
+dask = ['dask', 'distributed']
+test = [
+    'pytest>=6.2.5',
+    'pytest-cov>=2.6.0',
+    'jupyter>=1.0.0,<2',
+    'rundoc>=0.4.3,<0.5',
+    'tomli>=2.0.0,<3',
+]
+dev = [
+    'sdgym[dask, test]',
+
+    # general
+    'build>=1.0.0,<2',
+    'bump-my-version>=0.18.3,<1',
+    'pip>=9.0.1',
+    'watchdog>=1.0.1,<5',
+
+    # style check
+    'ruff>=0.4.5,<1',
+
+    # distribute on PyPI
+    'twine>=1.10.0,<6',
+    'wheel>=0.30.0',
+
+    # Advanced testing
+    'coverage>=4.5.12,<8',
+    'tox>=2.9.1,<5',
+    'importlib-metadata>=3.6',
+
+    # Invoke
+    'invoke',
+]
+all = [
+    'sdgym[dask, test, dev]',
+]
+
+[tool.setuptools]
+include-package-data = true
+license-files = ['LICENSE']
+
+[tool.setuptools.packages.find]
+include = ['sdgym', 'sdgym.*']
+namespaces = false
+
+[tool.setuptools.package-data]
+'*' = [
+    'AUTHORS.rst',
+    'HISTORY.md',
+    'README.md',
+    '*.md',
+    '*.rst',
+    'conf.py',
+    'Makefile',
+    'make.bat',
+    '*.jpg',
+    '*.png',
+    '*.gif'
+]
+'sdgym' = ['leaderboard.csv']
+
+[tool.setuptools.exclude-package-data]
+'*' = [
+    '* __pycache__',
+    '*.py[co]',
+    'static_code_analysis.txt',
+]
+
+[tool.setuptools.dynamic]
+version = {attr = 'sdgym.__version__'}
+
+[tool.bumpversion]
+current_version = "0.8.0.dev0"
+parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
+serialize = [
+    '{major}.{minor}.{patch}.{release}{candidate}',
+	'{major}.{minor}.{patch}'
+]
+search = '{current_version}'
+replace = '{new_version}'
+regex = false
+ignore_missing_version = false
+tag = true
+sign_tags = false
+tag_name = 'v{new_version}'
+tag_message = 'Bump version: {current_version} → {new_version}'
+allow_dirty = false
+commit = true
+message = 'Bump version: {current_version} → {new_version}'
+commit_args = ''
+
+[tool.bumpversion.parts.release]
+first_value = 'dev'
+optional_value = 'release'
+values = [
+    'dev',
+    'release'
+]
+
+[[tool.bumpversion.files]]
+filename = "sdgym/__init__.py"
+search = "__version__ = '{current_version}'"
+replace = "__version__ = '{new_version}'"
+
+[build-system]
+requires = ['setuptools', 'wheel']
+build-backend = 'setuptools.build_meta'
+
+[tool.ruff]
+preview = true
+line-length = 100
+indent-width = 4
+src = ["sdgym"]
+exclude = [
+    "docs",
+    ".tox",
+    ".git",
+    "__pycache__",
+    ".ipynb_checkpoints"
+]
+
+[tool.ruff.lint]
+select = [
+    # Pyflakes
+    "F",
+    # Pycodestyle
+    "E",
+    "W",
+    "D200",
+    # isort
+    "I001",
+]
+ignore = [
+    "E501",
+    "D107",  # Missing docstring in __init__
+    "D417",   # Missing argument descriptions in the docstring, this is a bug from pydocstyle: https://github.com/PyCQA/pydocstyle/issues/449
+]
+
+[tool.ruff.format]
+quote-style = "single"
+indent-style = "space"
+preview = true
+docstring-code-format = true
+docstring-code-line-length = "dynamic"
+
+[tool.ruff.lint.pep8-naming]
+extend-ignore-names = ["X", "C", "X_padded", "Y", "Y_padded"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["sdgym"]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401", "E402", "F403", "F405", "E501", "I001"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"

{sdgym-0.7.0.dev0 → sdgym-0.8.0.dev0}/sdgym/__init__.py

@@ -8,7 +8,7 @@ __author__ = 'DataCebo, Inc.'
 __copyright__ = 'Copyright (c) 2022 DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
 __license__ = 'BSL-1.1'
-__version__ = '0.7.0.dev0'
+__version__ = '0.8.0.dev0'
 
 import logging
 
@@ -29,5 +29,5 @@ __all__ = [
     'benchmark_single_table',
     'get_available_datasets',
     'create_sdv_synthesizer_variant',
-    'create_single_table_synthesizer'
+    'create_single_table_synthesizer',
 ]