Collection of feedback
@stevehadd is already working on this.
Since Jul 13, 2022.
Assessment
This issue has not been assessed yet.
Description
I have now used this material twice, all parts for the GMED/RMED training, and the first half for the CEDS 2022 conference. I will gather feedback here:
Feedback from participants:
• Generally, people who had a bit of background on ML found the session very useful, for me it was exactly what I needed to get started.
• The very beginner people in ML struggled a bit and suggested a few changes:
o the part on "history of ML at the Met Office" (which I actually quite liked but may be less useful for beginners) could be replaced by a brief overview of the different types of algorithms and maybe an example. (I know it's the focus of the 2nd session, but some people were a bit lost on this)
o For the Jupyter notebooks: we didn't have time to go through them ourselves much during the session, so potentially you could have demonstrated only one of the examples and then let us play with it.
o Some people hadn't had time to set up the conda environment so potentially sending it one week in advance would have been good (that said, again I appreciate you've done this for the first time and it'll be easier to send this in advance next time you run it - so this comment is probably not very useful!).
My own reflections:
- I landed up using a lot of the time, especially notebooks 1-3, talking with less practical time than intended. Probably need at extra hour for each session. So probably 4.5 hours per session (e.g. 10-12h30, 13h30-15h30)
- Need to find out about level of participants beforehand, to decide about how much background/introductory material to rpesent (e.g. deefinition of machine learning, what is supervised vs unsupervised). Might require something preparatory for participants beforehand to have consitent level - e.g. those new to ML watch DS CoP session first
- Dominant language
- Jupyter Notebook
- Stars
- 4
- Forks
- 2
- PR merge metrics
- No merged PRs in 30d
Getting set up
We have not checked this project's setup files yet. Start from its README, and see our first-contribution guide for the general steps.
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from MetOffice/ml_weather_tutorial
-
Difficulty 1/5 Under an hour Newbie friendliness 55/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 35/100
-
Difficulty 3/5 1-2 days Newbie friendliness 35/100
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
create a similarity matrix for the clustering notebookMay be free again @stevehadd claimed this 1382 days ago, and no pull request is open. Open
MetOffice/ml_weather_tutorial#28 · 1 assignee ·