├── .github ├── release-drafter.yml └── workflows │ ├── pytest.yml │ ├── release-drafter.yml │ └── release.yml ├── .gitignore ├── README.md ├── README_ja.md ├── daaja ├── __init__.py ├── augmentors │ ├── __init__.py │ ├── sentence │ │ ├── __init__.py │ │ ├── back_translation_augmentor.py │ │ ├── contextual_augmentor.py │ │ ├── randam_delete_augmentor.py │ │ ├── randam_insert_augmentor.py │ │ ├── randam_swap_augmentor.py │ │ ├── sentence_augmentor.py │ │ └── synonym_replace_augmentor.py │ └── sequence_labeling │ │ ├── __init__.py │ │ ├── labelwise_token_replacement_augmentor.py │ │ ├── mention_replacement_augmentor.py │ │ ├── sequence_labeling_augmentor.py │ │ ├── shuffle_within_segments_augmentor.py │ │ ├── synonym_replacement_augmentor.py │ │ └── utils.py ├── flows │ ├── __init__.py │ ├── sequential_flow.py │ └── sequential_sequence_labeling_flow.py ├── methods │ ├── eda │ │ ├── __init__.py │ │ ├── easy_data_augmentor.py │ │ └── run.py │ └── ner_sda │ │ ├── __init__.py │ │ ├── run.py │ │ └── simple_data_augmentation_for_ner.py ├── resouces.py └── tokenizer.py ├── examples └── quick_example.ipynb ├── github └── workflows │ └── pytest.yaml ├── poetry.lock ├── pyproject.toml └── tests ├── __init__.py ├── augmentors ├── __init__.py ├── sentence │ ├── __init__.py │ ├── test_back_translation_augmentor.py │ ├── test_contextual_augmentor.py │ ├── test_randam_delete_augmentor.py │ ├── test_randam_insert_augmentor.py │ ├── test_randam_swap_augmentor.py │ └── test_synonym_replace_augmentor.py └── sequence_labeling │ ├── __init__.py │ ├── test_labelwise_token_replacement_augmentor.py │ ├── test_mention_replacement_augmentor.py │ ├── test_shuffle_within_segments_augmentor.py │ └── test_synonym_replacement_augmentor.py ├── methods ├── eda │ ├── __init__.py │ ├── fixtures │ │ └── text.tsv │ ├── test_easy_data_augmentor.py │ └── test_run.py └── sda_ner │ ├── __init__.py │ ├── fixtures │ └── text.tsv │ ├── test_run.py │ ├── test_simple_data_augmentation_for_ner.py │ └── test_utils.py └── test_resouces.py /.github/release-drafter.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/.github/release-drafter.yml -------------------------------------------------------------------------------- /.github/workflows/pytest.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/.github/workflows/pytest.yml -------------------------------------------------------------------------------- /.github/workflows/release-drafter.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/.github/workflows/release-drafter.yml -------------------------------------------------------------------------------- /.github/workflows/release.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/.github/workflows/release.yml -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/README.md -------------------------------------------------------------------------------- /README_ja.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/README_ja.md -------------------------------------------------------------------------------- /daaja/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /daaja/augmentors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /daaja/augmentors/sentence/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/__init__.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/back_translation_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/back_translation_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/contextual_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/contextual_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/randam_delete_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/randam_delete_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/randam_insert_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/randam_insert_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/randam_swap_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/randam_swap_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/sentence_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/sentence_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sentence/synonym_replace_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sentence/synonym_replace_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/__init__.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/labelwise_token_replacement_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/labelwise_token_replacement_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/mention_replacement_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/mention_replacement_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/sequence_labeling_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/sequence_labeling_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/shuffle_within_segments_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/shuffle_within_segments_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/synonym_replacement_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/synonym_replacement_augmentor.py -------------------------------------------------------------------------------- /daaja/augmentors/sequence_labeling/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/augmentors/sequence_labeling/utils.py -------------------------------------------------------------------------------- /daaja/flows/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /daaja/flows/sequential_flow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/flows/sequential_flow.py -------------------------------------------------------------------------------- /daaja/flows/sequential_sequence_labeling_flow.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/flows/sequential_sequence_labeling_flow.py -------------------------------------------------------------------------------- /daaja/methods/eda/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /daaja/methods/eda/easy_data_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/methods/eda/easy_data_augmentor.py -------------------------------------------------------------------------------- /daaja/methods/eda/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/methods/eda/run.py -------------------------------------------------------------------------------- /daaja/methods/ner_sda/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /daaja/methods/ner_sda/run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/methods/ner_sda/run.py -------------------------------------------------------------------------------- /daaja/methods/ner_sda/simple_data_augmentation_for_ner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/methods/ner_sda/simple_data_augmentation_for_ner.py -------------------------------------------------------------------------------- /daaja/resouces.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/resouces.py -------------------------------------------------------------------------------- /daaja/tokenizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/daaja/tokenizer.py -------------------------------------------------------------------------------- /examples/quick_example.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/examples/quick_example.ipynb -------------------------------------------------------------------------------- /github/workflows/pytest.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/github/workflows/pytest.yaml -------------------------------------------------------------------------------- /poetry.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/poetry.lock -------------------------------------------------------------------------------- /pyproject.toml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/pyproject.toml -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/augmentors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/augmentors/sentence/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/augmentors/sentence/test_back_translation_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sentence/test_back_translation_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sentence/test_contextual_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sentence/test_contextual_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sentence/test_randam_delete_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sentence/test_randam_delete_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sentence/test_randam_insert_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sentence/test_randam_insert_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sentence/test_randam_swap_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sentence/test_randam_swap_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sentence/test_synonym_replace_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sentence/test_synonym_replace_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sequence_labeling/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/augmentors/sequence_labeling/test_labelwise_token_replacement_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sequence_labeling/test_labelwise_token_replacement_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sequence_labeling/test_mention_replacement_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sequence_labeling/test_mention_replacement_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sequence_labeling/test_shuffle_within_segments_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sequence_labeling/test_shuffle_within_segments_augmentor.py -------------------------------------------------------------------------------- /tests/augmentors/sequence_labeling/test_synonym_replacement_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/augmentors/sequence_labeling/test_synonym_replacement_augmentor.py -------------------------------------------------------------------------------- /tests/methods/eda/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/methods/eda/fixtures/text.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/eda/fixtures/text.tsv -------------------------------------------------------------------------------- /tests/methods/eda/test_easy_data_augmentor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/eda/test_easy_data_augmentor.py -------------------------------------------------------------------------------- /tests/methods/eda/test_run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/eda/test_run.py -------------------------------------------------------------------------------- /tests/methods/sda_ner/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/methods/sda_ner/fixtures/text.tsv: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/sda_ner/fixtures/text.tsv -------------------------------------------------------------------------------- /tests/methods/sda_ner/test_run.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/sda_ner/test_run.py -------------------------------------------------------------------------------- /tests/methods/sda_ner/test_simple_data_augmentation_for_ner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/sda_ner/test_simple_data_augmentation_for_ner.py -------------------------------------------------------------------------------- /tests/methods/sda_ner/test_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/methods/sda_ner/test_utils.py -------------------------------------------------------------------------------- /tests/test_resouces.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/kajyuuen/daaja/HEAD/tests/test_resouces.py --------------------------------------------------------------------------------