Active Learning With Rich feedabck
Sample code in
pip install active_learning
python setup.py sdist
python setup.py install
- Make sure that conda is installed.
- Run the following command in the root directory to build the conda
conda env create -f environment.yml
source activate trewsbefore executing the Jupyter notebook.
- "trews" has a package nb_conda which allows you to specify the conda env you want as a Jupyter kernel. You must have "trews" activated for the Jupyter notebook server to manage conda environments
- Provide justification for custom sepsis definition generated from soliciting rich feedback from physicians.
- Create an AL implementation that incorporates rich feedback from physicians to improve the TREWS tool.
- Long-term goal: Create a library of active learning tools for any CDSS we design for new clinical problems.
- General functions should be written in .py files under folder 'python_scripts'
- Experiments should load these python files into iPython notebooks
for visualization/output neatness and reproducibility.
- Large experimental datasets should be stored locally and tracked using plaintext files or logs.
- Datasets used for testing implementation should be kept under repository 'dev_data'
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
|Filename, size||File type||Python version||Upload date||Hashes|
|Filename, size active_learning-0.3.0.tar.gz (14.3 kB)||File type Source||Python version None||Upload date||Hashes View|