Changelog¶
Version 0.3.0¶
Fix bug with random initialization of KMedoids [#129].
KMedoids supports array-like init method [#137].
- Add a stopping criterion and parameter tuning heuristic for Huber robust mean
estimator.
- Add CLARA (Clustering for Large Applications) which extends k-medoids to
be more scalable using a sampling approach. [#83].
Fix _estimator_type for
robust
estimators. Fix misbehavior of scikit-learn’scross_val_score
andGridSearchCV
forRobustWeightedClassifier
.
Version 0.2.0¶
April 14, 2021
Add
RobustWeightedClassifier
,RobustWeightedRegressor
andRobustWeightedKMeans
estimators that rely on iterative reweighting of samples to be robust to outliers. [#42].Added Common Nearest-Neighbors clustering estimator
CommonNNClustering
[#64]Added PAM algorithm to
KMedoids
withmethod="pam"
parameter which produces better solutions but at higher computational cost [#73]Binary wheels were uploaded to PyPi, making the installation possible without a C compiler [#66]
List of contributors (in alphabetical order)¶
Christos Aridas, Jan-Oliver Joswig, Timothée Mathieu, Roman Yurchak