search

TutteInstitute / vectorizers

Vectorizers for a range of different data types
BSD 3-Clause "New" or "Revised" License
93 stars 23 forks source link

Change default normalization in TCV #63

Closed lmcinnes closed 3 years ago

lmcinnes commented 3 years ago

The default normalization was "Bayesian" which performed less well. This will change it to "frequentist" as well as changing the option "Bayesian" to "bayesian" to match the other string params which are all uncapitalised.

Finally a minor fix to the sphinx build stuff was added.

codecov-commenter commented 3 years ago

Codecov Report

Merging #63 (14537a0) into master (53f6e21) will decrease coverage by 0.23%. The diff coverage is 50.00%.

Impacted file tree graph

@@            Coverage Diff             @@
##           master      #63      +/-   ##
==========================================
- Coverage   64.27%   64.03%   -0.24%     
==========================================
  Files          19       19              
  Lines        2981     2981              
==========================================
- Hits         1916     1909       -7     
- Misses       1065     1072       +7
Impacted Files Coverage Δ
vectorizers/token_cooccurrence_vectorizer.py 56.10% <50.00%> (-0.22%) :arrow_down:
vectorizers/utils.py 45.91% <0.00%> (-3.78%) :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 53f6e21...14537a0. Read the comment docs.