This project was created with the rrrpkg package and is intended to serve as a Research Compendium. The easiest way to get your hands dirty and explore data and run the analysis is to clone the HabMod github repository (instructions on how to clone and general github/Rstudio knowledge can be found at happygitwithr.com -- replace 'myrepo' with 'slarge/HabMod'). Once you have the project cloned, you will need to add a few functions necessary to load data. "Load all" using the keyboard shortcut ctrl+shift+L, which will load these functions into the current Global Environment.
Data is held in a private google drive folder. If you have access to the folder, open the analysis/data/raw_data/load_new_data.R script and follow the instructions to download the data. The intention, here, is to copy data from the google drive folder into the R package directory structure in a consistent way to facilitate batch processessing the data in subsequent analyses.
Once data are loaded using the analysis/data/raw_data/load_new_data.R script, you can get started with the analysis. Load the analysis/procedure/xgboost_habitat.R script. This script loads the raw data and adds a presence/absence vector for each species and then models presence/absence habitat and biomass habitat. Fitting with the xgboost algorithm requires a few steps. First, a few hyperparameters need to be tuned, which is done using a Bayesian optimization procedure. Next, the model is tuned.
Please cite this compendium as:
Large, S and Friedland, K (2017). NEUS Habitat Modeling. Accessed 14 Dec 2017. Online at https://doi.org/xxx/xxx
You can install habitatmodel from github with:
# install.packages("devtools")
devtools::install_github("slarge/HabMod")Text and figures: CC-BY-4.0
Code: See the DESCRIPTION file
Data: CC-0 attribution requested in reuse
We welcome contributions from everyone. Before you get started, please see our contributor guidelines. Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.