source code of Isolation Forest algorithm

[codecov[bot]]

Codecov Report

Merging #92 (cd020d6) into master (6fc5a6b) will increase coverage by 0.27%. The diff coverage is 92.79%.

@@             Coverage Diff              @@
##             master      #92      +/-   ##
============================================
+ Coverage     50.64%   50.91%   +0.27%     
- Complexity    12052    12112      +60     
============================================
  Files          1724     1727       +3     
  Lines         85673    86302     +629     
  Branches      15746    15885     +139     
============================================
+ Hits          43385    43940     +555     
- Misses        38213    38231      +18     
- Partials       4075     4131      +56     

Impacted Files	Coverage Δ
...ki-core-math/src/main/java/elki/math/MathUtil.java	96.20% <ø> (ø)
...n/java/elki/outlier/isolation/IsolationForest.java	92.79% <92.79%> (ø)
...rc/main/java/elki/clustering/kmedoids/FastPAM.java	87.61% <0.00%> (-2.86%)	:arrow_down:
...n/java/elki/index/tree/metrical/vptree/VPTree.java	83.39% <0.00%> (ø)
...ain/java/elki/index/tree/metrical/vptree/GNAT.java	90.04% <0.00%> (ø)
.../main/java/elki/database/ids/QuickSelectDBIDs.java	79.86% <0.00%> (+0.67%)	:arrow_up:
...data/synthetic/bymodel/GeneratorSingleCluster.java	51.13% <0.00%> (+2.27%)	:arrow_up:
...ava/elki/data/synthetic/bymodel/GeneratorMain.java	42.33% <0.00%> (+2.91%)	:arrow_up:

---

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 6fc5a6b...cd020d6. Read the comment docs.

[kno10]

I merged an own implementation of isolation forest (similar quality in the test, but more efficient implementation).

Note: located in density.IsolationForest instead of an isolation package. After all, isolation forests are an efficient approximate density measure.