├── .dvcignore ├── .github ├── ISSUE_TEMPLATE │ ├── bug.md │ └── feature.md ├── pull_request_template.md └── workflows │ ├── documentation.yml │ └── tests.yml ├── .gitignore ├── .gitlab-ci.yml ├── .pre-commit-config.yaml ├── LICENSE ├── README.md ├── changelog.md ├── configs ├── config-cpu.cfg └── config.cfg ├── data ├── .gitignore ├── gen_dataset │ └── README.md └── templates.txt ├── demo ├── app.py └── requirements.txt ├── docs ├── assets │ ├── figures │ │ └── data-augmentation.png │ ├── logo │ │ ├── aphp-blue.svg │ │ ├── aphp-white.svg │ │ ├── eds-pseudo-blue.svg │ │ └── eds-pseudo-white.svg │ ├── stylesheets │ │ └── extra.css │ └── termynal │ │ ├── termynal.css │ │ └── termynal.js ├── dataset.md ├── index.md ├── inference.md ├── pretrained.md ├── references.bib ├── reproducibility.md ├── results.md ├── rule-based.md ├── scripts │ └── generate_development.py ├── synthetic-dataset.md └── training.md ├── dvc.yaml ├── eds_pseudo ├── __init__.py ├── adapter.py ├── pipes │ ├── __init__.py │ ├── addresses │ │ ├── __init__.py │ │ ├── addresses.py │ │ └── patterns.py │ ├── clean_entities.py │ ├── dates │ │ ├── __init__.py │ │ ├── dates.py │ │ └── patterns.py │ ├── dates_normalizer │ │ ├── __init__.py │ │ ├── dates_normalizer.py │ │ └── patterns.py │ ├── merge_entities.py │ ├── pseudonymisation │ │ ├── __init__.py │ │ ├── patterns.py │ │ └── pseudonymisation.py │ └── structured.py └── scorer.py ├── mkdocs.yml ├── pyproject.toml ├── scripts ├── analysis.py ├── evaluate.py ├── experiments.py ├── generate_dataset.py ├── package.py ├── train.py └── visualize_model.py ├── tests ├── conftest.py ├── test_adapter.py ├── test_addresses.py ├── test_clean_entities.py ├── test_context.py ├── test_dates.py ├── test_dates_normalizer.py ├── test_merge.py ├── test_scorer.py ├── test_simple_rules.py └── test_train.py └── uv.lock /.dvcignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.dvcignore -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/bug.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.github/ISSUE_TEMPLATE/bug.md -------------------------------------------------------------------------------- /.github/ISSUE_TEMPLATE/feature.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.github/ISSUE_TEMPLATE/feature.md -------------------------------------------------------------------------------- /.github/pull_request_template.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.github/pull_request_template.md -------------------------------------------------------------------------------- /.github/workflows/documentation.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.github/workflows/documentation.yml -------------------------------------------------------------------------------- /.github/workflows/tests.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.github/workflows/tests.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.gitignore -------------------------------------------------------------------------------- /.gitlab-ci.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.gitlab-ci.yml -------------------------------------------------------------------------------- /.pre-commit-config.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/.pre-commit-config.yaml -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/README.md -------------------------------------------------------------------------------- /changelog.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/changelog.md -------------------------------------------------------------------------------- /configs/config-cpu.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/configs/config-cpu.cfg -------------------------------------------------------------------------------- /configs/config.cfg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/configs/config.cfg -------------------------------------------------------------------------------- /data/.gitignore: -------------------------------------------------------------------------------- 1 | /dataset 2 | -------------------------------------------------------------------------------- /data/gen_dataset/README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/data/gen_dataset/README.md -------------------------------------------------------------------------------- /data/templates.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/data/templates.txt -------------------------------------------------------------------------------- /demo/app.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/demo/app.py -------------------------------------------------------------------------------- /demo/requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/demo/requirements.txt -------------------------------------------------------------------------------- /docs/assets/figures/data-augmentation.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/figures/data-augmentation.png -------------------------------------------------------------------------------- /docs/assets/logo/aphp-blue.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/logo/aphp-blue.svg -------------------------------------------------------------------------------- /docs/assets/logo/aphp-white.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/logo/aphp-white.svg -------------------------------------------------------------------------------- /docs/assets/logo/eds-pseudo-blue.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/logo/eds-pseudo-blue.svg -------------------------------------------------------------------------------- /docs/assets/logo/eds-pseudo-white.svg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/logo/eds-pseudo-white.svg -------------------------------------------------------------------------------- /docs/assets/stylesheets/extra.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/stylesheets/extra.css -------------------------------------------------------------------------------- /docs/assets/termynal/termynal.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/termynal/termynal.css -------------------------------------------------------------------------------- /docs/assets/termynal/termynal.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/assets/termynal/termynal.js -------------------------------------------------------------------------------- /docs/dataset.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/dataset.md -------------------------------------------------------------------------------- /docs/index.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/index.md -------------------------------------------------------------------------------- /docs/inference.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/inference.md -------------------------------------------------------------------------------- /docs/pretrained.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/pretrained.md -------------------------------------------------------------------------------- /docs/references.bib: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /docs/reproducibility.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/reproducibility.md -------------------------------------------------------------------------------- /docs/results.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/results.md -------------------------------------------------------------------------------- /docs/rule-based.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/rule-based.md -------------------------------------------------------------------------------- /docs/scripts/generate_development.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/scripts/generate_development.py -------------------------------------------------------------------------------- /docs/synthetic-dataset.md: -------------------------------------------------------------------------------- 1 | # Synthetic Dataset 2 | -------------------------------------------------------------------------------- /docs/training.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/docs/training.md -------------------------------------------------------------------------------- /dvc.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/dvc.yaml -------------------------------------------------------------------------------- /eds_pseudo/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/__init__.py -------------------------------------------------------------------------------- /eds_pseudo/adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/adapter.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/__init__.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/addresses/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eds_pseudo/pipes/addresses/addresses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/addresses/addresses.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/addresses/patterns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/addresses/patterns.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/clean_entities.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/clean_entities.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/dates/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eds_pseudo/pipes/dates/dates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/dates/dates.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/dates/patterns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/dates/patterns.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/dates_normalizer/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eds_pseudo/pipes/dates_normalizer/dates_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/dates_normalizer/dates_normalizer.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/dates_normalizer/patterns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/dates_normalizer/patterns.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/merge_entities.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/merge_entities.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/pseudonymisation/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /eds_pseudo/pipes/pseudonymisation/patterns.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/pseudonymisation/patterns.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/pseudonymisation/pseudonymisation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/pseudonymisation/pseudonymisation.py -------------------------------------------------------------------------------- /eds_pseudo/pipes/structured.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/pipes/structured.py -------------------------------------------------------------------------------- /eds_pseudo/scorer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/eds_pseudo/scorer.py -------------------------------------------------------------------------------- /mkdocs.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/mkdocs.yml -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/pyproject.toml -------------------------------------------------------------------------------- /scripts/analysis.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/analysis.py -------------------------------------------------------------------------------- /scripts/evaluate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/evaluate.py -------------------------------------------------------------------------------- /scripts/experiments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/experiments.py -------------------------------------------------------------------------------- /scripts/generate_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/generate_dataset.py -------------------------------------------------------------------------------- /scripts/package.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/package.py -------------------------------------------------------------------------------- /scripts/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/train.py -------------------------------------------------------------------------------- /scripts/visualize_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/scripts/visualize_model.py -------------------------------------------------------------------------------- /tests/conftest.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/conftest.py -------------------------------------------------------------------------------- /tests/test_adapter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_adapter.py -------------------------------------------------------------------------------- /tests/test_addresses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_addresses.py -------------------------------------------------------------------------------- /tests/test_clean_entities.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_clean_entities.py -------------------------------------------------------------------------------- /tests/test_context.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_context.py -------------------------------------------------------------------------------- /tests/test_dates.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_dates.py -------------------------------------------------------------------------------- /tests/test_dates_normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_dates_normalizer.py -------------------------------------------------------------------------------- /tests/test_merge.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_merge.py -------------------------------------------------------------------------------- /tests/test_scorer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_scorer.py -------------------------------------------------------------------------------- /tests/test_simple_rules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_simple_rules.py -------------------------------------------------------------------------------- /tests/test_train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/tests/test_train.py -------------------------------------------------------------------------------- /uv.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/aphp/eds-pseudo/HEAD/uv.lock --------------------------------------------------------------------------------