Our our research agendas involve improving the tools we use to study disease transmission and biosecurity. Below, you’ll find software for working with infectious diseases, machine learning and on-farm swine biosecurity.
The RABapp (Rapid Acess Biosecurity) provides rapid access to up-to-date, standardized on-farm biosecurity plans and animal movement data in a timely manner to enable business continuity within the swine industry, also:
- Expand SPS plan adoption throughout the swine industry and train stakeholders to use the app to help them refine and manage their site-specific plans
- Train stakeholders in how to use the app to prepare for large-scale disease emergencies
mrIML
We are developing the mrIML
R package for generating postestimation interpret multivariate machine learning models. The package contains functions for multi-response stacking algorithms and harnessing the tidyverse (tidy model syntax in
particular).
Installation
Install the stable version of the package:
#install.packages("devtools")
devtools::install_github('nfj1380/mrIML')
Quick start
mrIML is designed to be used with a single function call or to be
used in an ad-hoc fashion via individual function calls. In the
following section we give an overview of the simple use case. For more
on using each function see the function documentation. The core
functions for both regression and classification are:
mrIMLpredicts
, mrIMLperformance
, and
mrInteractions
,for plotting and visualization mrVip
,
mrFlashlight
, andplot_vi
. Estimating the interactions
alone can be substantially computationally demanding depending on the
number of outcomes you want to test. The first step to using the package
is to load it as follows.