README.md

In ncsa/DataHarmonizationPipeline: An automated statistical analysis pipeline in R for use on public health datasets

Data Harmonization Pipeline

An automated statistical analysis pipeline in R for use on public health datasets, developed at NCSA.

Description

• An open-source software package easily usable by scientists to identify combinations of factors responsible for healthy disparities.
• A computationally efficient statistical package that makes use of the host computer’s architecture and resources.
• A modularized, flexible, portable and easily-depolyable implementation of a statistical pipeline for data analysis on health datasets.

Authors

Sijia Huo, Dipro Ray, Liudmila Mainzer, Zeynep Madak-Erdogan

Installation

The entire package is written in R, using the RStudio IDE. The following instructions are to set up the package to be run in RStudio.

• git clone the repository into your workspace directory, and open the .Rproj file with RStudio.
• Run .R/DataPipelineDriver_New.R, and it will automatically download any package dependencies. To view a list of dependencies, view the DESCRIPTION file.

Further Information

Additional information regarding code design, implementation and documentation can be found in more_info.md.

ncsa/DataHarmonizationPipeline documentation built on May 30, 2019, 2:05 p.m.