search

elki-project / elki

ELKI Data Mining Toolkit
https://elki-project.github.io/
GNU Affero General Public License v3.0
785 stars 323 forks source link

Source code of DBSCAN Outlier Detection algorithm #96

Closed BraulioSanchez closed 3 years ago

codecov[bot] commented 3 years ago

Codecov Report

Merging #96 (50249cb) into master (20b92c4) will increase coverage by 0.04%. The diff coverage is 100.00%.

Impacted file tree graph

@@             Coverage Diff              @@
##             master      #96      +/-   ##
============================================
+ Coverage     50.86%   50.91%   +0.04%     
- Complexity    12103    12122      +19     
============================================
  Files          1726     1727       +1     
  Lines         86191    86225      +34     
  Branches      15865    15872       +7     
============================================
+ Hits          43842    43899      +57     
+ Misses        38226    38207      -19     
+ Partials       4123     4119       -4
Impacted Files Coverage Δ
...lki/outlier/clustering/DBSCANOutlierDetection.java 100.00% <100.00%> (ø)
...i-core-api/src/main/java/elki/result/Metadata.java 63.75% <0.00%> (-0.68%) :arrow_down:
...rc/main/java/elki/database/query/QueryBuilder.java 50.61% <0.00%> (+0.61%) :arrow_up:
...a/elki/database/query/EmpiricalQueryOptimizer.java 49.71% <0.00%> (+2.31%) :arrow_up:
...clustering/src/main/java/elki/data/Clustering.java 100.00% <0.00%> (+3.84%) :arrow_up:
...ng/dbscan/predicates/EpsilonNeighborPredicate.java 100.00% <0.00%> (+3.84%) :arrow_up:
...java/elki/clustering/dbscan/GeneralizedDBSCAN.java 89.42% <0.00%> (+6.73%) :arrow_up:
...i/utilities/optionhandling/ParameterException.java 73.68% <0.00%> (+10.52%) :arrow_up:
...ionhandling/parameterization/Parameterization.java 91.66% <0.00%> (+33.33%) :arrow_up:
... and 1 more

Continue to review full report at Codecov.

Legend - Click here to learn more Δ = absolute <relative> (impact), ø = not affected, ? = missing data Powered by Codecov. Last update 20b92c4...50249cb. Read the comment docs.

kno10 commented 3 years ago

Merged with trivial changes

To get the evaluation working short term, use -algorithm clustering.trivial.ByLabelClustering,outlier.clustering.DBSCANOutlierDetection for now, so that the automatic evaluation procedure uses the labels as reference, not the DBSCAN clustering.