Type the following line so git remembers your credential and you don't have to enter your token 6 times per day:
Get a notification on your phone/mail when a run is done
We use for notification. Install ntfy on your Iphone or Android device. Then subscribe to the channel ntfy.sh/flepimop_alerts where you'll receive notifications when runs are done.
End of job notifications goes as urgent priority.
Install slack integration
Within included example postprocessing scripts, we include a helper script that sends a slack message with some output snapshots of our model output. So our 🤖-friend can send us some notifications once a run is done.
Delphi Epidata API
If you are using the Delph Epidata API, first . Once you have a key, add that below where you see [YOUR API KEY]. Alternatively, you can put that key in your config file in the inference section as gt_api_key: "YOUR API KEY".
🚀 Run inference using slurm (do everytime)
TODO: add how to run test, and everything
Don't paste them if you don't know what they do
Filepaths structure
in configs with a setup name: USA
where, eg:
the index is 1
the run_id is 2021.12.14.23:56:12.CET
the prefix is USA/inference/med/2021.12.14.23:56:12.CET/global/intermediate/000000001.
Steps to first local run
where:
is slots
is core
is iteration per slot
Launch the docker locally
Pipeline git-fu (dealing with the commute_data)
because a big file get changed and added automatically. Since Git 2.13 (Q2 2017), you can stash individual files, with . One of these should work.
git config --global credential.helper store
git config --global user.name "{NAME SURNAME}"
git config --global user.email YOUREMAIL@EMAIL.COM
git config --global pull.rebase false # so you use merge as the default reconciliation method
cd /scratch4/struelo1/flepimop-code/
nano slack_credentials.sh
# and fill the file:
export SLACK_WEBHOOK="{THE SLACK WEBHOOK FOR CSP_PRODUCTION}"
export SLACK_TOKEN="{THE SLACK TOKEN}"