Use Random Forest (RF) classification trees to assign whale injuries as 'Serious' or 'Non-Serious', based on narratives. There are two RF models, one for vessel strikes (ModelVessel) and one for entanglements (ModelEntangle). Covariates are generated directly from narratives, by coding presence / absence of key words / phrases (i.e. 'healthy' vs 'emaciated') associated with known serious and non-serious injury cases. Models are based on 'known-outcome' cases, e.g. recoveries documented >=1 yr after a vessel strike or entanglement, observed health declines or serious injuries at any point after an incident, and deaths. Models are then applied to 'unknown outcome' cases, where injury severity and risk to whales are unknown due to a lack of details and/or brief observation periods.
|Maintainer||Jim Carretta <firstname.lastname@example.org>|
|License||GPL-3 plus file LICENSE|
|Package repository||View on GitHub|
Install the latest version of this package by entering the following in R:
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.