This repo houses all the class notebooks and utilities that will be used during the UCSB spring 2018 quarter Health Data Science Module led by Evidation Health.
To get up and running with the required dependencies and data do:
git pull https://github.com/evidation-health/EvidationDataScienceModule.gitcd EvidationDataScienceModule./utils/pull_nhanes_data.sh./utils/setup_env.sh
The above will pull the processed NHANES data down from a public bucket in s3, and will setup a python virtual environment that pip installs the required dependencies. Note this has yet to be thoroughly tested, and will only be tested on OSX and Linux.
The module will be organized into four submodules that will all make use of the 2005 NHANES Dataset. The four modules are as follows:
- ETL, data munging, data QC, storage strategies
- Data visualization as a preparation strategy for inference and machine learning
- Inferential analysis
- Machine Learning for health data
Put resources here. . . .