Commit cd57ef1a authored by Mayur Mudigonda's avatar Mayur Mudigonda
Browse files

Update README.md

parent 9019caf1
Pipeline #291394 failed with stage
in 55 minutes and 20 seconds
......@@ -51,9 +51,6 @@ git remote add upstream https://renkulab.io/gitlab/aaron.spring/s2s-ai-challenge
git pull upstream master
```
### 2. Fill our [registration form](https://docs.google.com/forms/d/1KEnATjaLOtV-o4N8PLinPXYnpba7egKsCCH_efriCb4).
Registrations are not required before October 31st 2021, but highly [appreciated for the flow of information](https://renkulab.io/gitlab/aaron.spring/s2s-ai-challenge/-/issues/4).
### 3. Make the project private
......@@ -72,18 +69,12 @@ description of your method.
### 4. Add the `s2saichallengescorer` user to your repo with Reporter permissions
The scorer follows the code shown in the [verification notebook](https://renkulab.io/gitlab/aaron.spring/s2s-ai-challenge-template/-/blob/master/notebooks/verification_RPSS.ipynb). The scorer's username on gitlab is `s2saichallengescorer`. You should add it to your project with `Reporter` permissions. Under "Members" - "Invite Members" - "GitLab member or Email address", add `s2saichallengescorer`. The scorer will only ever clone your repository and evaluate your submission. It will never make any changes to your code.
### 5. Add the `s2s-ai-challenge` topic to your repository
To add the project topic navigate to `Settings` -> `General` and then fill in the word `s2s-ai-challenge` in the
`Topics` field near the top of the page. If you have multiple topics you can separate them by commas.
This is optional and not required for now :)
This allows your repository to be recognized as a participant of the competition. Without
this project topic or if you have not added the scorer as a member of your project
the automated scoring bot will not evaluate any of your submissions and none of your code
or results will be considered for the competition.
## Make Predictions
### 6. Start jupyter on renku or locally
### 4. Start jupyter on renku or locally
The simplest way to contribute is right from the Renku platform -
just click on the `Environments` tab in your renku project and start a new session.
This will start an interactive environment right in your browser.
......@@ -98,7 +89,7 @@ renku project URLs - use `renku clone` to clone the project on whichever machine
Install [renku first with `pipx`](https://renku-python.readthedocs.io/en/latest/installation.html),
and then `renku clone https://renkulab.io/gitlab/$YOURNAME/s2s-ai-challenge-$GROUPNAME.git`
### 7. Train your Machine Learning model
### 5. Train your Machine Learning model
Get training data via
- [climetlab](https://github.com/ecmwf-lab/climetlab-s2s-ai-challenge)
......@@ -108,12 +99,12 @@ Get corresponding observations/ground truth:
- [climetlab](https://github.com/ecmwf-lab/climetlab-s2s-ai-challenge)
- IRIDL: [temperature](http://iridl.ldeo.columbia.edu/SOURCES/.NOAA/.NCEP/.CPC/.temperature/.daily/) and accumulated [precipitation](http://iridl.ldeo.columbia.edu/SOURCES/.NOAA/.NCEP/.CPC/.UNIFIED_PRCP/.GAUGE_BASED/.GLOBAL/.v1p0/.extREALTIME/.rain)
### 8. Let the Machine Learning model perform subseasonal 2020 predictions
### 6. Let the Machine Learning model perform subseasonal 2020 predictions
and save them as `netcdf` files.
The submissions have to placed in the `submissions` folder with filename `ML_prediction_2020.nc`,
see [example](https://renkulab.io/gitlab/aaron.spring/s2s-ai-competition-bootstrap/-/blob/master/submissions/ML_prediction_2020.nc).
### 9. `git commit` training pipeline and netcdf submission
### 7. `git commit` training pipeline and netcdf submission
For later verification by the organizers, reproducibility and scoring of submissions,
commit all code, input and output data. For the data files please use `git lfs`.
If you are unfamiliar with `git lfs` a short introduction can be found
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment