search

analyticalmindsltd / smote_variants

A collection of 85 minority oversampling techniques (SMOTE) for imbalanced learning with multi-class oversampling and model selection features
http://smote-variants.readthedocs.io
MIT License
631 stars 137 forks source link

fix TODOs and revise some problems #67

Closed hykun1989 closed 1 year ago

hykun1989 commented 1 year ago

SMOTE_AMSR: combing the attention mechanism of sparse regions and the interpolation technique of geometric topology to Generate New Minority Data. In this method, we first introduced the sparsity evaluation function to score each instance of the minority class. Sparser instances will have larger weights and then the new data will be created more around them. And then, we used the geometric topology-based interpolation method to expand the diversity of the minority class.

codecov[bot] commented 1 year ago

Codecov Report

Merging #67 (f22d6e4) into master (fd25602) will not change coverage. The diff coverage is 100.00%.

@@           Coverage Diff           @@
##           master      #67   +/-   ##
=======================================
  Coverage   99.88%   99.88%           
=======================================
  Files         128      128           
  Lines        9574     9574           
=======================================
  Hits         9563     9563           
  Misses         11       11
Flag Coverage Δ
unittests ?

Flags with carried forward coverage won't be shown. Click here to find out more.

Impacted Files Coverage Δ
smote_variants/oversampling/_smote_amsr.py 100.00% <100.00%> (ø)

:mega: We’re building smart automated test selection to slash your CI/CD build times. Learn more

gykovacs commented 1 year ago

Great, thank you!