Bernoulli Naive Bayes

[wildart]

Following #183 tips. This is an implementation of Bernoulli Naive Bayes classifier derived from Multinomial NB.

[codecov-commenter]

Codecov Report

Merging #226 (2091be5) into master (6168a90) will decrease coverage by 2.45%. The diff coverage is 53.84%.

@@            Coverage Diff             @@
##           master     #226      +/-   ##
==========================================
- Coverage   57.87%   55.41%   -2.46%     
==========================================
  Files          96       96              
  Lines        8384     8860     +476     
==========================================
+ Hits         4852     4910      +58     
- Misses       3532     3950     +418     

Impacted Files	Coverage Δ
algorithms/linfa-bayes/src/multinomial_nb.rs	62.65% <ø> (ø)
algorithms/linfa-bayes/src/hyperparams.rs	14.28% <20.00%> (+3.75%)	:arrow_up:
algorithms/linfa-bayes/src/bernoulli_nb.rs	63.04% <63.04%> (ø)
algorithms/linfa-clustering/src/k_means/init.rs	56.20% <0.00%> (-30.66%)	:arrow_down:
algorithms/linfa-pls/src/utils.rs	63.15% <0.00%> (-24.94%)	:arrow_down:
algorithms/linfa-kernel/src/sparse.rs	74.19% <0.00%> (-21.64%)	:arrow_down:
src/composing/platt_scaling.rs	40.00% <0.00%> (-21.23%)	:arrow_down:
...fa-clustering/src/appx_dbscan/counting_tree/mod.rs	36.08% <0.00%> (-17.77%)	:arrow_down:
algorithms/linfa-svm/src/classification.rs	60.23% <0.00%> (-16.07%)	:arrow_down:
algorithms/linfa-nn/src/distance.rs	36.20% <0.00%> (-13.80%)	:arrow_down:
... and 47 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 6168a90...2091be5. Read the comment docs.

[bytesnake]

continued in #242