Skip to main content

Active Learning With Rich feedabck

Project description

Example

Sample code in AL_Notebook.ipynb notebook

Install

  • pip install active_learning
  • OR
  • python setup.py sdist
  • python setup.py install

Environment Setup

  • Make sure that conda is installed.
  • Run the following command in the root directory to build the conda environment "trews": conda env create -f environment.yml
  • Run source activate trews before 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

Objective

  • 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.

Code Organization

  • 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'

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
active_learning-0.3.0.tar.gz (14.3 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page