De-identification toolkit for clinical text in Hebrew
Project description
HebSafeHarbor
A de-identification toolkit for clinical text in Hebrew.
Installation
To install the package, clone the repo and install all dependencies, preferably in a virtual environment:
# Create conda env (optional)
conda create --name hebsafeharbor python=3.8
conda activate hebsafeharbor
# Install dependencies
pip install -r requirements.txt
# (Optional) Install package locally
pip install -e .
# Download the he_ner_news_trf model used by hebsafeharbor
pip install https://github.com/8400TheHealthNetwork/HebSpacy/releases/download/he_ner_news_trf-3.2.1/he_ner_news_trf-3.2.1-py3-none-any.whl
Getting started
Python
from hebsafeharbor import HebSafeHarbor
hsh = HebSafeHarbor()
text = """שרון לוי התאשפזה ב02.02.2012 וגרה בארלוזרוב 16 רמת גן"""
doc = {"text": text}
output = hsh([doc])
print(output)
Docker
- Run the following command to install and run the server and demo services:
docker-compose up -d --build
- Navigate in the browser http://localhost:8080/docs to test the Server swagger
- Navigate in the browser http://localhost:8501 to test the Demo app
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Close
Hashes for hebsafeharbor-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 586eb9923fd9b589e641cb6eb8337e11a7fdb23b73baa081bfb3f399848ca31c |
|
MD5 | f912e13d524edbc2b80b399a554a60af |
|
BLAKE2b-256 | d0b8f5d0d8958e0143217ad4ca264256cc267318f9f2f40e1b72eed547e4207e |