Add files via upload

README.md

@@ -65,6 +65,7 @@ You can also put a symlink to a pdf file (see `data/test_pdf.tsv` for an example
 ```
 Report_id_X   Doe  John  Example.pdf
 ```
+You'll need poppler installed in your os to use OCR on pdf file (https://pdf2image.readthedocs.io/en/latest/installation.html)
 
 Outputs will be placed in the `results` folder according to the file extension, using first three columns in filename. 
 - The deidentify report will be generated and placed in the `results/Reports` folder.

requirements.txt

@@ -1,43 +1,45 @@
-altair==5.1.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-argostranslate==1.9.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-attrs==23.1.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+altair==5.3.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+argostranslate==1.9.6 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+attrs==23.2.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 backports-cached-property==1.0.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-backports-zoneinfo==0.2.1 ; python_version >= "3.8" and python_version < "3.9"
-blinker==1.7.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+blinker==1.8.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 blis==0.7.11 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-cachetools==5.3.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+cachetools==5.3.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 catalogue==2.0.10 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-certifi==2023.11.17 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+certifi==2024.7.4 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 charset-normalizer==3.3.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 click==8.1.7 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-cloudpathlib==0.16.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+cloudpathlib==0.18.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 colorama==0.4.6 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12" and (platform_system == "Windows" or sys_platform == "win32")
-confection==0.1.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-ctranslate2==3.20.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+confection==0.1.5 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+ctranslate2==4.3.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 cymem==2.0.8 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-filelock==3.13.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-fsspec==2023.10.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+filelock==3.15.4 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+fsspec==2024.6.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 gitdb==4.0.11 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-gitpython==3.1.40 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-huggingface-hub==0.19.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-idna==3.6 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-importlib-metadata==6.8.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-importlib-resources==6.1.1 ; python_version >= "3.8" and python_version < "3.9"
-jinja2==3.1.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-joblib==1.3.2 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-jsonschema-specifications==2023.11.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-jsonschema==4.20.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-langcodes==3.3.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+gitpython==3.1.43 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+huggingface-hub==0.23.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+idna==3.7 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+importlib-resources==6.4.0 ; python_version >= "3.8" and python_version < "3.9"
+intel-openmp==2021.4.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12" and platform_system == "Windows"
+jinja2==3.1.4 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+joblib==1.4.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+jsonschema-specifications==2023.12.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+jsonschema==4.23.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+langcodes==3.4.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+language-data==1.2.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+marisa-trie==1.2.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 markdown-it-py==3.0.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-markupsafe==2.1.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+markupsafe==2.1.5 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 mdurl==0.1.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 memory-profiler==0.61.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+mkl==2021.4.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12" and platform_system == "Windows"
 mpmath==1.3.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 murmurhash==1.0.10 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 networkx==3.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 nltk==3.8.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 numpy==1.24.4 ; python_version >= "3.8" and python_version < "3.9"
-numpy==1.26.2 ; python_version >= "3.9" and python_full_version != "3.9.7" and python_version < "3.12"
+numpy==1.26.4 ; python_version >= "3.9" and python_full_version != "3.9.7" and python_version < "3.12"
 nvidia-cublas-cu12==12.1.3.1 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 nvidia-cuda-cupti-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 nvidia-cuda-nvrtc-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
@@ -47,67 +49,69 @@ nvidia-cufft-cu12==11.0.2.54 ; platform_system == "Linux" and platform_machine =
 nvidia-curand-cu12==10.3.2.106 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 nvidia-cusolver-cu12==11.4.5.107 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 nvidia-cusparse-cu12==12.1.0.106 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-nvidia-nccl-cu12==2.18.1 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-nvidia-nvjitlink-cu12==12.3.101 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+nvidia-nccl-cu12==2.20.5 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+nvidia-nvjitlink-cu12==12.5.82 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 nvidia-nvtx-cu12==12.1.105 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-packaging==23.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+packaging==24.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 pandas==1.5.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-phonenumbers==8.13.26 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-pillow==10.1.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+pdf2image==1.17.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+phonenumbers==8.13.40 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+pillow==10.4.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 pkgutil-resolve-name==1.3.10 ; python_version >= "3.8" and python_version < "3.9"
 preshed==3.0.9 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-presidio-analyzer==2.2.351 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-presidio-anonymizer==2.2.351 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+presidio-analyzer==2.2.354 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+presidio-anonymizer==2.2.354 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 protobuf==3.20.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-psutil==5.9.6 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-pyarrow==14.0.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-pycryptodome==3.19.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+psutil==6.0.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+pyarrow==16.1.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+pycryptodome==3.20.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 pydantic==1.10.13 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-pydeck==0.8.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-pygments==2.17.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+pydeck==0.9.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+pygments==2.18.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 pyhpo==3.1.5 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-python-dateutil==2.8.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-pytz==2023.3.post1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+pytesseract==0.3.10 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+python-dateutil==2.9.0.post0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+pytz==2024.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 pyyaml==6.0.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-referencing==0.31.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-regex==2023.10.3 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-requests-file==1.5.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-requests==2.31.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-rich==13.7.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-rpds-py==0.13.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+referencing==0.35.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+regex==2024.5.15 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+requests-file==2.1.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+requests==2.32.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+rich==13.7.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+rpds-py==0.19.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 sacremoses==0.0.53 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-safetensors==0.4.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-sentencepiece==0.1.99 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-setuptools==69.0.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+safetensors==0.4.3 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+sentencepiece==0.2.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+setuptools==70.3.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+shellingham==1.5.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 six==1.16.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-smart-open==6.4.0 ; python_full_version >= "3.8.0" and python_version < "3.12" and python_full_version != "3.9.7"
+smart-open==7.0.4 ; python_full_version >= "3.8.0" and python_version < "3.12" and python_full_version != "3.9.7"
 smmap==5.0.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
 spacy-legacy==3.0.12 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 spacy-loggers==1.0.5 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-spacy==3.7.2 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+spacy==3.7.5 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 srsly==2.4.8 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 stanza==1.1.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-streamlit==1.28.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-sympy==1.12 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-tenacity==8.2.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-thinc==8.2.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-tldextract==5.1.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-tokenizers==0.15.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+streamlit==1.36.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+sympy==1.13.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+tbb==2021.13.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12" and platform_system == "Windows"
+tenacity==8.5.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+thinc==8.2.5 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+tldextract==5.1.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+tokenizers==0.19.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
 toml==0.10.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-toolz==0.12.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-torch==2.1.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-tornado==6.3.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-tqdm==4.66.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-transformers==4.35.2 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-triton==2.1.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-typer==0.9.0 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-typing-extensions==4.8.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-tzdata==2023.3 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12" and platform_system == "Windows"
-tzlocal==5.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-unidecode==1.3.7 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-urllib3==2.1.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-validators==0.22.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
-wasabi==1.1.2 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-watchdog==3.0.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12" and platform_system != "Darwin"
-weasel==0.3.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
-zipp==3.17.0 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+toolz==0.12.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+torch==2.3.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+tornado==6.4.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+tqdm==4.66.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+transformers==4.42.4 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+triton==2.3.1 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version < "3.12" and python_full_version >= "3.8.0" and python_full_version != "3.9.7"
+typer==0.12.3 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+typing-extensions==4.12.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+unidecode==1.3.8 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+urllib3==2.2.2 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12"
+wasabi==1.1.3 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+watchdog==4.0.1 ; python_version >= "3.8" and python_full_version != "3.9.7" and python_version < "3.12" and platform_system != "Darwin"
+weasel==0.4.1 ; python_full_version >= "3.8.0" and python_full_version != "3.9.7" and python_version < "3.12"
+wrapt==1.16.0 ; python_full_version >= "3.8.0" and python_version < "3.12" and python_full_version != "3.9.7"
+zipp==3.19.2 ; python_version >= "3.8" and python_version < "3.9"