search

byu-dml / metalearn

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

Perceptron metafeatures #190

Open emrysshevek opened 5 years ago

emrysshevek commented 5 years ago

Add the following metafeatures (for a perceptron induced on the full dataset, 1/10 of the data, 1/2 of the data, and sqrt(n) of the data):

bjschoenfeld commented 5 years ago

Is there a test we should add?

emrysshevek commented 5 years ago

Is there a test we should add?

We should probably add a correctness check for a synthetic dataset with only one class, to make sure that the values we assign in that case are correct.

codecov-io commented 4 years ago

Codecov Report

Merging #190 into develop will increase coverage by 0.91%. The diff coverage is 100%.

Impacted file tree graph

@@             Coverage Diff             @@
##           develop     #190      +/-   ##
===========================================
+ Coverage    92.36%   93.28%   +0.91%     
===========================================
  Files           13       14       +1     
  Lines          760      819      +59     
===========================================
+ Hits           702      764      +62     
+ Misses          58       55       -3
Impacted Files Coverage Δ
metalearn/metafeatures/metafeatures.py 96.34% <100%> (+0.51%) :arrow_up:
metalearn/metafeatures/perceptron_metafeatures.py 100% <100%> (ø)
...metafeatures/information_theoretic_metafeatures.py 100% <0%> (+4.65%) :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 92e8a0d...b89291f. Read the comment docs.