8000 Add Release Highlights for several features in 0.22 · Issue #15152 · scikit-learn/scikit-learn · GitHub
[go: up one dir, main page]
Skip to content
8000

Add Release Highlights for several features in 0.22 #15152

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
10 of 13 tasks
jnothman opened this issue Oct 8, 2019 · 11 comments
Closed
10 of 13 tasks

Add Release Highlights for several features in 0.22 #15152

jnothman opened this issue Oct 8, 2019 · 11 comments
Labels
Blocker Documentation Easy Well-defined and straightforward way to resolve help wanted
Milestone
0.22

Comments

@jnothman
Copy link
Member
jnothman commented Oct 8, 2019 •
edited by NicolasHug
Loading

We recently merged https://github.com/NicolasHug/scikit-learn/blob/master/examples/release_highlights/plot_release_highlights_0_22_0.py to summarise the highlights of 0.22, to be released in early November.

More release highlights, briefly demonstrating the new thing in action, belong in that example doc:

  • Permutation based feature importance
  • HistGradientBoostingClassifier with missing data
  • Plotting API
  • Tree pruning
  • fetch_openml's as_frame
  • ? Changed behaviour in StratifiedKFold
  • precomputed sparse neighborhoods, e.g. for SpectralClustering or manifold learning, with KNeighborsTransformer
  • StackingClassifier or StackingRegressor
  • parametrize_with_checks
  • KNNImputer and nan_euclidean_distances
  • ?Multiclass roc_auc_score
  • ? Improved performance of multimetric scoring
  • ? CategoricalNB

Priority here should be given, IMO, to:

  • things that will be popular (i.e. much anticipated, or people have gone elsewhere for these features)
  • things that people will miss otherwise (hence the inclusion of parametrize_with_checks)
@jnothman jnothman added Documentation help wanted Easy Well-defined and straightforward way to resolve labels Oct 8, 2019
@jnothman
Copy link
Member Author
jnothman commented Oct 8, 2019

Contributors: please only add one at a time.

@thebooort
Copy link

Hey there!, stackingclassifier and stackingregression have some examples in their definition. May I edit them a little bit and add them ( in one or two PR's) to the file?

@TomDLT TomDLT mentioned this issue Oct 9, 2019
Merged
@TomDLT
Copy link
Member
TomDLT commented Oct 9, 2019

@thebooort Please do :). I think one short example is enough.

@qinhanmin2014
Copy link
Member

HistGradientBoostingClassifier with missing data

this is already included? (Native support for missing values for gradient boosting)

@thomasjpfan
Copy link
Member

this is already included? (Native support for missing values for gradient boosting)

Yup! #13911

@jnothman jnothman added this to the 0.22 milestone Oct 28, 2019
This was referenced Oct 31, 2019
Merged
Merged
@NicolasHug
Copy link
Member

Depending on the length of the final file, we might want to have a TOC at the top for a quick glance

This was referenced Oct 31, 2019
Merged
Merged
@NicolasHug
Copy link
Member

have a TOC at the top for a quick glance

Trying that but can't get to anything

@jnothman
Copy link
Member Author
jnothman commented Nov 5, 2019

Are we happy to close this?

@NicolasHug
Copy link
Member

Maybe we need to decide the order of the entries, but OK for another issue

@jnothman
Copy link
Member Author
jnothman commented Nov 6, 2019 via email

@NicolasHug
Copy link
Member

Opened #15552

@jnothman jnothman closed this as completed Nov 7, 2019
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Blocker Documentation Easy Well-defined and straightforward way to resolve help wanted
Projects
None yet
Milestone
0.22
Development

No branches or pull requests
6 participants
@jnothman @NicolasHug @thomasjpfan @TomDLT @qinhanmin2014 @thebooort
0