SinaTools 0.1.12__tar.gz → 0.1.14__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {SinaTools-0.1.12 → SinaTools-0.1.14}/PKG-INFO +1 -1
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/PKG-INFO +1 -1
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/ner/corpus_entity_extractor.py +4 -1
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/ner/entity_extractor.py +3 -1
- SinaTools-0.1.14/sinatools/VERSION +1 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/entity_extractor.py +1 -1
- SinaTools-0.1.12/sinatools/VERSION +0 -1
- {SinaTools-0.1.12 → SinaTools-0.1.14}/AUTHORS.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/CONTRIBUTING.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/LICENSE +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/MANIFEST.in +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/README.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/SOURCES.txt +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/dependency_links.txt +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/entry_points.txt +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/not-zip-safe +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/requires.txt +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/SinaTools.egg-info/top_level.txt +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/Makefile +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/_images/download.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/_static/download.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/_static/file.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/_static/minus.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/_static/plus.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_images/SinaLogo.jpg +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_images/download.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_static/SinaLogo.jpg +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_static/download.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_static/file.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_static/minus.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/build/html/_static/plus.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/make.bat +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/License.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/Overview.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/_static/SinaLogo.jpg +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/_static/download.png +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/about.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/DataDownload/downloader.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/DataDownload.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/arabiner/bin/infer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/arabiner.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/morphology/morph_analyzer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/morphology.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/salma/views.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/salma.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils/corpus_tokenizer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils/implication.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils/jaccard.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils/parser.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils/sentence_tokenizer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils/text_transliteration.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api/utils.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/api.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/authors.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/DataDownload/download_files.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/DataDownload/get_appdatadir.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/DataDownload.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/arabiner/infer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/arabiner.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/morphology/ALMA_multi_word.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/morphology/morph_analyzer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/morphology.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/salma/salma_tools.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/salma.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/arStrip.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/corpus_tokenizer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/implication.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/jaccard.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/latin_remove.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/remove_punc.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/sentence_tokenizer.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils/text_transliteration.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools/utils.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/cli_tools.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/conf.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/index.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/installation.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/docs/source/readme.rst +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/setup.cfg +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/setup.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/DataDownload/download_files.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/morphology/ALMA_multi_word.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/morphology/morph_analyzer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/arStrip.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/corpus_tokenizer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/implication.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/jaccard.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/remove_latin.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/remove_punctuation.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/sentence_tokenizer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/text_dublication_detector.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/CLI/utils/text_transliteration.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/DataDownload/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/DataDownload/downloader.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/create_classification_data.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/create_pretraining_data.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/extract_features.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/lamb_optimizer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/modeling.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/optimization.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/run_classifier.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/run_pretraining.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/run_squad.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/tokenization.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/build_openwebtext_pretraining_dataset.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/build_pretraining_dataset.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/build_pretraining_dataset_single_file.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/configure_finetuning.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/configure_pretraining.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/feature_spec.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/preprocessing.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/scorer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/task.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/task_builder.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/flops_computation.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/model/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/model/modeling.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/model/optimization.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/model/tokenization.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/pretrain/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/pretrain/pretrain_data.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/pretrain/pretrain_helpers.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/run_finetuning.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/run_pretraining.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/util/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/util/training_utils.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/util/utils.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/create_pretraining_data.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/gpt2/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/gpt2/lamb_optimizer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/gpt2/optimization.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/gpt2/run_pretraining.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/dataloader.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/modeling.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/modeling_gpt2.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/optimization_adafactor.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/train_tpu.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/utils.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/train_bpe_tokenizer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/preprocess.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/environment.yml +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/install_env.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/morphology/ALMA_multi_word.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/morphology/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/morphology/morph_analyzer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/data/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/data/datasets.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/data/transforms.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/data_format.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/datasets.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/helpers.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/metrics.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/nn/BaseModel.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/nn/BertNestedTagger.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/nn/BertSeqTagger.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/nn/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/trainers/BaseTrainer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/trainers/BertNestedTrainer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/trainers/BertTrainer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/trainers/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/ner/transforms.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/semantic_relatedness/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/semantic_relatedness/compute_relatedness.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/sinatools.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/synonyms/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/synonyms/synonyms_generator.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/charsets.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/implication.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/jaccard.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/parser.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/readfile.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/text_dublication_detector.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/text_transliteration.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/tokenizer.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/utils/tokenizers_words.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/wsd/__init__.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/wsd/disambiguator.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/wsd/settings.py +0 -0
- {SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/wsd/wsd.py +0 -0
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: SinaTools
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.14
|
4
4
|
Summary: Open-source Python toolkit for Arabic Natural Understanding, allowing people to integrate it in their system workflow.
|
5
5
|
Home-page: https://github.com/SinaLab/sinatools
|
6
6
|
License: MIT license
|
@@ -1,6 +1,6 @@
|
|
1
1
|
Metadata-Version: 2.1
|
2
2
|
Name: SinaTools
|
3
|
-
Version: 0.1.
|
3
|
+
Version: 0.1.14
|
4
4
|
Summary: Open-source Python toolkit for Arabic Natural Understanding, allowing people to integrate it in their system workflow.
|
5
5
|
Home-page: https://github.com/SinaLab/sinatools
|
6
6
|
License: MIT license
|
@@ -16,8 +16,11 @@ Run the script with the following command:
|
|
16
16
|
corpus_entity_extractor input.csv --text-columns "TextColumn1,TextColumn2" --additional-columns "Column3,Column4" --output-csv output.csv
|
17
17
|
"""
|
18
18
|
|
19
|
+
def jsons_to_list_of_lists(json_list):
|
20
|
+
return [[d['token'], d['tags']] for d in json_list]
|
21
|
+
|
19
22
|
def combine_tags(sentence):
|
20
|
-
output = extract(sentence)
|
23
|
+
output = jsons_to_list_of_lists(extract(sentence))
|
21
24
|
return [word[1] for word in output]
|
22
25
|
|
23
26
|
|
@@ -42,9 +42,11 @@ from sinatools.ner.entity_extractor import extract
|
|
42
42
|
from sinatools.utils.tokenizer import corpus_tokenizer
|
43
43
|
from sinatools.utils.tokenizers_words import simple_word_tokenize
|
44
44
|
|
45
|
+
def jsons_to_list_of_lists(json_list):
|
46
|
+
return [[d['token'], d['tags']] for d in json_list]
|
45
47
|
|
46
48
|
def combine_tags(sentence):
|
47
|
-
output = extract(sentence)
|
49
|
+
output = jsons_to_list_of_lists(extract(sentence))
|
48
50
|
return [word[1] for word in output]
|
49
51
|
|
50
52
|
|
@@ -0,0 +1 @@
|
|
1
|
+
0.1.14
|
@@ -61,7 +61,7 @@ def extract(text, batch_size=32):
|
|
61
61
|
for segment in segments:
|
62
62
|
for token in segment:
|
63
63
|
segments_list = {}
|
64
|
-
segments_list["
|
64
|
+
segments_list["token"] = token.text
|
65
65
|
list_of_tags = [t['tag'] for t in token.pred_tag]
|
66
66
|
list_of_tags = [i for i in list_of_tags if i not in('O',' ','')]
|
67
67
|
if list_of_tags == []:
|
@@ -1 +0,0 @@
|
|
1
|
-
0.1.12
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/arabert/create_classification_data.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/build_pretraining_dataset.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/finetune/preprocessing.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/pretrain/pretrain_data.py
RENAMED
File without changes
|
{SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/araelectra/pretrain/pretrain_helpers.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
{SinaTools-0.1.12 → SinaTools-0.1.14}/sinatools/arabert/aragpt2/grover/optimization_adafactor.py
RENAMED
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|
File without changes
|