search

byu-dml / metalearn

BYU's python library of useable tools for metalearning
MIT License
22 stars 6 forks source link

Use metafeature groups for filtering #204

Closed JeremyRees closed 4 years ago

JeremyRees commented 4 years ago

Resolves #195. In PR #192 the enum MetafeatureGroup was introduced for tagging metafeatures. This PR tags target-dependent metafeatures as such and leverages the new groups for filtering in Metafeatures.list_metafeatures() and Metafeatures.compute(), with appropriate new unit tests included.

codecov-io commented 4 years ago

Codecov Report

Merging #204 into develop will increase coverage by 0.01%. The diff coverage is 93.75%.

Impacted file tree graph

@@             Coverage Diff             @@
##           develop     #204      +/-   ##
===========================================
+ Coverage    92.23%   92.24%   +0.01%     
===========================================
  Files           13       13              
  Lines          747      761      +14     
===========================================
+ Hits           689      702      +13     
- Misses          58       59       +1
Impacted Files Coverage Δ
metalearn/metafeatures/landmarking_metafeatures.py 100% <ø> (ø) :arrow_up:
metalearn/metafeatures/simple_metafeatures.py 100% <ø> (ø) :arrow_up:
...metafeatures/information_theoretic_metafeatures.py 95.34% <ø> (ø) :arrow_up:
...talearn/metafeatures/decision_tree_metafeatures.py 100% <ø> (ø) :arrow_up:
metalearn/metafeatures/base.py 93.61% <100%> (ø) :arrow_up:
metalearn/metafeatures/metafeatures.py 95.55% <93.1%> (-0.18%) :arrow_down:

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 55ca6bf...0ef67d7. Read the comment docs.