Collection of code from the HABs Proxies group to forecast chl-a for Ecological Forecasting Challenge 2022.
NOTE: A lot of the details on standardized environment and automation come from https://github.com/eco4cast/neon4cast-example
- Run
install.packages("renv")
in R. https://rstudio.github.io/renv/index.html - After the installation of
renv
finishes, runrenv::activate()
andrenv::restore()
.renv
uses therenv.lock
file committed to this repository to download and install the necessary packages to run this pipeline.renv
installs the packages to a project-specific location (i.e. it doesn't update R packages installed elsewhere on your machine). NOTE: this might take a while to install all the necessary packages for this project. We also userenv
in GitHub to automatically run the pipeline using GitHub actions. - If you make changes to the pipeline, especially if you're using a new package not already in use (or updating an existing package to a new version), run
renv::snapshot()
to update therenv.lock
file with any new packages that you have added. - Commit and push any changes to your forked version of the repository and open a pull request.
- Uncomment the
p6_submit
target. - Uncomment the
schedule:
and- cron: "0 20 * * *"
lines in the.github/workflows/do_prediction.yml
file. This cron job will run the forecast in this repository daily at 20:00 UTC, and the execution of the forecast occurs on GitHub's servers, so your local computer does not need to be turned on. You can update this to run on a different schedule based on timing codes found in https://crontab.guru - Commit and push the changes to Github.
- Under the actions tab, click on ".github/workflows/do_prediction.yml" on the left side.
- Click
Run workflow
, and then the greenRun workflow
button.
This software is preliminary or provisional and is subject to revision. It is being provided to meet the need for timely best science. The software has not received final approval by the U.S. Geological Survey (USGS). No warranty, expressed or implied, is made by the USGS or the U.S. Government as to the functionality of the software and related material nor shall the fact of release constitute any such warranty. The software is provided on the condition that neither the USGS nor the U.S. Government shall be held liable for any damages resulting from the authorized or unauthorized use of the software.