[ENH] Add a bad channel detection method using LOF algorithm

vpKumaravel commented 1 year ago

Reference issue NA

What does this implement/fix? This PR contains a new feature for bad channel detection using Local Outlier Factor (LOF) algorithm. File name: lof.py To be compliant, I also added the test_lof.py file along with the test data lofdata.mat

Additional information The proposed algorithm is used in Newborns EEG Artifact Removal (NEAR) pipeline published earlier this year. Recently, we analyzed data from adult subjects and the algorithm is adaptable to different populations.

Best regards, Velu

nbara commented 1 year ago

Hey @vpKumaravel, thanks! Will have a look as soon as possible. In the meantime, I activated the CI which where disabled for some reason. Best, Nicolas

codecov[bot] commented 1 year ago

Codecov Report

Merging #66 (3e53949) into master (5e95ee5) will increase coverage by 0.03%. The diff coverage is 84.00%.

:exclamation: Current head 3e53949 differs from pull request most recent head c7a89eb. Consider uploading reports for the commit c7a89eb to get more accurate results

@@            Coverage Diff             @@
##           master      #66      +/-   ##
==========================================
+ Coverage   78.74%   78.78%   +0.03%     
==========================================
  Files          21       22       +1     
  Lines        2315     2338      +23     
==========================================
+ Hits         1823     1842      +19     
- Misses        492      496       +4

Impacted Files	Coverage Δ
meegkit/lof.py	`82.60% <82.60%> (ø)`
meegkit/__init__.py	`100.00% <100.00%> (ø)`

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

nbara / python-meegkit

[ENH] Add a bad channel detection method using LOF algorithm #66

Codecov Report