├── .coveragerc ├── .flake8 ├── .github └── workflows │ └── ci.yml ├── .gitignore ├── .isort.cfg ├── .pre-commit-config.yaml ├── CITATION.cff ├── CONTRIBUTING.md ├── LICENSE.md ├── Makefile ├── Pipfile ├── Pipfile.lock ├── README.md ├── dcbench ├── __init__.py ├── __main__.py ├── common │ ├── __init__.py │ ├── artifact.py │ ├── artifact_container.py │ ├── modeling.py │ ├── problem.py │ ├── result.py │ ├── solution.py │ ├── solution_set.py │ ├── solve.py │ ├── solver.py │ ├── table.py │ ├── task.py │ ├── trial.py │ └── utils.py ├── config.py ├── constants.py ├── tasks │ ├── .DS_Store │ ├── __init__.py │ ├── budgetclean │ │ ├── __init__.py │ │ ├── baselines.py │ │ ├── common.py │ │ ├── cpclean │ │ │ ├── README.md │ │ │ ├── algorithm │ │ │ │ ├── min_max.py │ │ │ │ ├── select.py │ │ │ │ ├── sort_count.py │ │ │ │ └── utils.py │ │ │ ├── clean.py │ │ │ ├── debugger.py │ │ │ ├── knn_evaluator.py │ │ │ ├── query.py │ │ │ └── utils.py │ │ └── problem.py │ ├── minidata │ │ ├── __init__.py │ │ └── unagi_configs.py │ └── slice_discovery │ │ ├── __init__.py │ │ ├── baselines.py │ │ ├── metrics.py │ │ ├── pipeline.py │ │ ├── problem.py │ │ └── run.py └── version.py ├── docs ├── Makefile ├── assets │ ├── banner.png │ └── logo.png ├── make.bat ├── populate_docs.py ├── requirements.txt └── source │ ├── apidocs │ ├── dcbench.budgetclean.rst │ ├── dcbench.common.rst │ ├── dcbench.rst │ ├── dcbench.tasks.budgetclean.rst │ ├── dcbench.tasks.minidata.rst │ ├── dcbench.tasks.rst │ ├── dcbench.tasks.slice.rst │ ├── dcbench.tasks.slice_discovery.rst │ └── modules.rst │ ├── conf.py │ ├── index.rst │ ├── install.rst │ ├── intro.rst │ ├── task_descriptions │ ├── budgetclean.rst │ ├── minidata.rst │ └── slice_discovery.rst │ ├── task_template.rst │ └── tasks.rst ├── notebooks ├── Untitled.ipynb ├── dcbench_budgetclean.ipynb ├── dcbench_slice_discovery-Copy1.ipynb └── dcbench_slice_discovery.ipynb ├── pyproject.toml ├── setup.py └── tests ├── __init__.py ├── conftest.py └── dcbench ├── __init__.py ├── common ├── __init__.py ├── test_artifact.py ├── test_artifact_container.py ├── test_problem.py └── test_task.py ├── tasks └── test_slice_discovery.py ├── test_config.py └── test_dcbench.py /.coveragerc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/.coveragerc -------------------------------------------------------------------------------- /.flake8: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/.flake8 -------------------------------------------------------------------------------- /.github/workflows/ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/.github/workflows/ci.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/.gitignore -------------------------------------------------------------------------------- /.isort.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/.isort.cfg -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /CITATION.cff: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/CITATION.cff -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/LICENSE.md -------------------------------------------------------------------------------- /Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/Makefile -------------------------------------------------------------------------------- /Pipfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/Pipfile -------------------------------------------------------------------------------- /Pipfile.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/Pipfile.lock -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/README.md -------------------------------------------------------------------------------- /dcbench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/__init__.py -------------------------------------------------------------------------------- /dcbench/__main__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/__main__.py -------------------------------------------------------------------------------- /dcbench/common/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/__init__.py -------------------------------------------------------------------------------- /dcbench/common/artifact.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/artifact.py -------------------------------------------------------------------------------- /dcbench/common/artifact_container.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/artifact_container.py -------------------------------------------------------------------------------- /dcbench/common/modeling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/modeling.py -------------------------------------------------------------------------------- /dcbench/common/problem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/problem.py -------------------------------------------------------------------------------- /dcbench/common/result.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/result.py -------------------------------------------------------------------------------- /dcbench/common/solution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/solution.py -------------------------------------------------------------------------------- /dcbench/common/solution_set.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/solution_set.py -------------------------------------------------------------------------------- /dcbench/common/solve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/solve.py -------------------------------------------------------------------------------- /dcbench/common/solver.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/solver.py -------------------------------------------------------------------------------- /dcbench/common/table.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/table.py -------------------------------------------------------------------------------- /dcbench/common/task.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/task.py -------------------------------------------------------------------------------- /dcbench/common/trial.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/common/trial.py -------------------------------------------------------------------------------- /dcbench/common/utils.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /dcbench/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/config.py -------------------------------------------------------------------------------- /dcbench/constants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/constants.py -------------------------------------------------------------------------------- /dcbench/tasks/.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/.DS_Store -------------------------------------------------------------------------------- /dcbench/tasks/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/__init__.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/baselines.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/common.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/common.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/README.md -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/algorithm/min_max.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/algorithm/min_max.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/algorithm/select.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/algorithm/select.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/algorithm/sort_count.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/algorithm/sort_count.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/algorithm/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/algorithm/utils.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/clean.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/clean.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/debugger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/debugger.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/knn_evaluator.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/knn_evaluator.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/query.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/query.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/cpclean/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/cpclean/utils.py -------------------------------------------------------------------------------- /dcbench/tasks/budgetclean/problem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/budgetclean/problem.py -------------------------------------------------------------------------------- /dcbench/tasks/minidata/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/minidata/__init__.py -------------------------------------------------------------------------------- /dcbench/tasks/minidata/unagi_configs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/minidata/unagi_configs.py -------------------------------------------------------------------------------- /dcbench/tasks/slice_discovery/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/slice_discovery/__init__.py -------------------------------------------------------------------------------- /dcbench/tasks/slice_discovery/baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/slice_discovery/baselines.py -------------------------------------------------------------------------------- /dcbench/tasks/slice_discovery/metrics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/slice_discovery/metrics.py -------------------------------------------------------------------------------- /dcbench/tasks/slice_discovery/pipeline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/slice_discovery/pipeline.py -------------------------------------------------------------------------------- /dcbench/tasks/slice_discovery/problem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/slice_discovery/problem.py -------------------------------------------------------------------------------- /dcbench/tasks/slice_discovery/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/dcbench/tasks/slice_discovery/run.py -------------------------------------------------------------------------------- /dcbench/version.py: -------------------------------------------------------------------------------- 1 | __version__ = "0.0.4" 2 | -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/assets/banner.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/assets/banner.png -------------------------------------------------------------------------------- /docs/assets/logo.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/assets/logo.png -------------------------------------------------------------------------------- /docs/make.bat: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/make.bat -------------------------------------------------------------------------------- /docs/populate_docs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/populate_docs.py -------------------------------------------------------------------------------- /docs/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/requirements.txt -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.budgetclean.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.budgetclean.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.common.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.common.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.tasks.budgetclean.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.tasks.budgetclean.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.tasks.minidata.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.tasks.minidata.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.tasks.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.tasks.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.tasks.slice.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.tasks.slice.rst -------------------------------------------------------------------------------- /docs/source/apidocs/dcbench.tasks.slice_discovery.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/dcbench.tasks.slice_discovery.rst -------------------------------------------------------------------------------- /docs/source/apidocs/modules.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/apidocs/modules.rst -------------------------------------------------------------------------------- /docs/source/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/conf.py -------------------------------------------------------------------------------- /docs/source/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/index.rst -------------------------------------------------------------------------------- /docs/source/install.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/install.rst -------------------------------------------------------------------------------- /docs/source/intro.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/intro.rst -------------------------------------------------------------------------------- /docs/source/task_descriptions/budgetclean.rst: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /docs/source/task_descriptions/minidata.rst: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /docs/source/task_descriptions/slice_discovery.rst: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /docs/source/task_template.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/task_template.rst -------------------------------------------------------------------------------- /docs/source/tasks.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/docs/source/tasks.rst -------------------------------------------------------------------------------- /notebooks/Untitled.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/notebooks/Untitled.ipynb -------------------------------------------------------------------------------- /notebooks/dcbench_budgetclean.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/notebooks/dcbench_budgetclean.ipynb -------------------------------------------------------------------------------- /notebooks/dcbench_slice_discovery-Copy1.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/notebooks/dcbench_slice_discovery-Copy1.ipynb -------------------------------------------------------------------------------- /notebooks/dcbench_slice_discovery.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/notebooks/dcbench_slice_discovery.ipynb -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/pyproject.toml -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/setup.py -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/dcbench/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/dcbench/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/dcbench/common/test_artifact.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/dcbench/common/test_artifact.py -------------------------------------------------------------------------------- /tests/dcbench/common/test_artifact_container.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/dcbench/common/test_artifact_container.py -------------------------------------------------------------------------------- /tests/dcbench/common/test_problem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/dcbench/common/test_problem.py -------------------------------------------------------------------------------- /tests/dcbench/common/test_task.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/dcbench/tasks/test_slice_discovery.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/dcbench/tasks/test_slice_discovery.py -------------------------------------------------------------------------------- /tests/dcbench/test_config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/dcbench/test_config.py -------------------------------------------------------------------------------- /tests/dcbench/test_dcbench.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/data-centric-ai/dcbench/HEAD/tests/dcbench/test_dcbench.py --------------------------------------------------------------------------------