Sourced from linfa-datasets's releases.

Release 0.8.0

What's Changed

Besides Bernouilli naive bayes classifier and bootstrap aggregation ensemble method, most notably Linfa's 0.8.0 release brings support for ndarray 0.16.

• [linfa-bayes] Add bernoulli naive bayes implementation by @​wildart, @​relf in rust-ml/linfa#388
• [linfa-ensemble] Add new ensemble methods crate: linfa-ensemble by @​jk1015, @​relf in rust-ml/linfa#392
• [linfa-clustering] Add predict_proba() to Gaussian mixture model by @​techyorzl in rust-ml/linfa#381
• [linfa-preprocessing] Add max_features and tokenizer to CountVectorizer by @​marco-cloudflare in rust-ml/linfa#376
• [linfa-svm] Fix SVR nu parameter passing and rework SVR parameterization API by @​relf in rust-ml/linfa#370
• [linfa-pls] Fix serde support for linfa-pls algorithms by @​relf in rust-ml/linfa#380
• [linfa-nn] Bump kdtree to 0.7.0 by @​acgessler in rust-ml/linfa#391
• [linfa-trees] Replace Vec with VecDeque for proper BFT queue behavior in NodeIter by @​WilsonKuo in rust-ml/linfa#384
• [linfa]:
  • Upgrade to ndarray 0.16 by @​relf in rust-ml/linfa#371
  • Add target names to Dataset by @​oojo12, @​relf in rust-ml/linfa#373
  • Fix confusion matrix by @​levkk, @​relf in rust-ml/linfa#374
  • Fix original feature and target names after shuffling by @​Plutone11011 in rust-ml/linfa#377
  • Bump MSRV to 1.87.0 by @​relf in rust-ml/linfa#371

New Contributors

• @​Plutone11011 made their first contribution in rust-ml/linfa#377
• @​techyorzl made their first contribution in rust-ml/linfa#381
• @​marco-cloudflare made their first contribution in rust-ml/linfa#376
• @​WilsonKuo made their first contribution in rust-ml/linfa#384
• @​acgessler made their first contribution in rust-ml/linfa#391

(I tried to track all contributors. Please get in touch if anybody is missing, I will update the release notes accordingly)

Full Changelog: rust-ml/linfa@0.7.1...0.8.0

Sourced from linfa-datasets's changelog.

Version 0.8.0 - 2025-09-30

New Algorithms

• Bernouilli naive bayes in [linfa-bayes] by [@​wildart]
• Bootstrap aggregation (aka Bagging) in new ensemble methods crate [linfa-ensemble] by [@​jk1015]

Changes

• add max_features and tokenizer_function to CountVectorizer in linfa-preprocessing
• add predict_proba() to Gaussian mixture model in linfa-clustering
• add predict_proba() and predict_log_proba() to algorithms in linfa-bayes
• add target names to dataset
• fix SVR parameterization in linfa-svm
• fix serde support for algorithms in linfa-pls
• fix confusion matrix: use predicted and ground thruth labels, make it reproducible
• fix dataset names after shuffling
• bump ndarray to 0.16, argmin to 0.11.0, kdtree to 0.7.0, statrs to 0.18, sprs to 0.11
• bump MSRV to 1.87.0

Version 0.7.1 - 2025-01-14

New Algorithms

• Random Projection added to linfa-reduction by [@​GBathie]

Changes

• add serde support to linfa-clustering
• add accessors for classes in linfa-logistics
• add accessors for Pca attributes in linfa-reduction
• add wasm-bindgenfeature to use linfa in the browser
• fix covariance update for GaussianMixtureModel in linfa-clustering
• bump ndarray-linalg to 0.16 and argmin to 0.9.0
• bump MSRV to 1.71.1

Version 0.7.0 - 2023-10-15

Changes

• add array_from_gz_csv and array_from_csv in linfa-datasets
• make Serde support in linfa-linear, linfa-logistic, and linfa-ftrl optional
• bump argmin to 0.8.1
• add Serde support to linfa-preprocessing and linfa-bayes
• make licenses follow SPDX 2.1 license expression standard

Removals

• Removed Approximate DBSCAN from linfa-clustering due to performance issues. It's now an alias to regular DBSCAN.
• Removed partitions dependency, which breaks in current versions of Rust.

... (truncated)

• 06eb432 Release version 0.8.0 (#398)
• e3f082b Upgrade to ndarray 0.16 (#371)
• 77457b2 Prepare release linfa-nn 0.7.2 (#395)
• 20b1dd2 Add new ensemble methods crate: linfa-ensemble (#392)
• 335924e linfa-nn: bump kdtree to 0.7.0 (#391)
• 11ea07a Add bernoulli naive bayes implementation (#388)
• 5272ad1 Replace Vec with VecDeque for performance in decision_tree node iterations ...
• fd4a214 Add max_features and tokenizer to CountVectorizer (#376)
• 6ab89bf Add predict_proba() to Gaussian mixture model (#381)
• 1e29cb4 Bump MSRV to 1.81.0 (#382)
• Additional commits viewable in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore <dependency name> major version will close this group update PR and stop Dependabot creating any more for the specific dependency's major version (unless you unignore this specific dependency's major version or upgrade to it yourself)
• @dependabot ignore <dependency name> minor version will close this group update PR and stop Dependabot creating any more for the specific dependency's minor version (unless you unignore this specific dependency's minor version or upgrade to it yourself)
• @dependabot ignore <dependency name> will close this group update PR and stop Dependabot creating any more for the specific dependency (unless you unignore this specific dependency or upgrade to it yourself)
• @dependabot unignore <dependency name> will remove all of the ignore conditions of the specified dependency
• @dependabot unignore <dependency name> <ignore condition> will remove the ignore condition of the specified dependency and ignore conditions