Added class_weight parameter to sparse_categorical_focal_loss

[artemmavrin]

Similar to the pos_weight parameter of binary_focal_loss, class_weight allows the user to specify the relative weight of each class.

[codecov-io]

Codecov Report

Merging #11 into master will decrease coverage by 2.12%.
The diff coverage is 95.57%.

@@             Coverage Diff             @@
##            master      #11      +/-   ##
===========================================
- Coverage   100.00%   97.87%   -2.13%     
===========================================
  Files            8        8              
  Lines          513      612      +99     
  Branches        60       69       +9     
===========================================
+ Hits           513      599      +86     
- Misses           0       10      +10     
- Partials         0        3       +3     

Impacted Files	Coverage Δ
src/focal_loss/_categorical_focal_loss.py	89.65% <87.17%> (-10.35%)	⬇️
src/focal_loss/__init__.py	100.00% <100.00%> (ø)
...l_loss/tests/test_sparse_categorical_focal_loss.py	100.00% <100.00%> (ø)
src/focal_loss/_binary_focal_loss.py	91.66% <0.00%> (-8.34%)	⬇️

---

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 9e023de...c03f719. Read the comment docs.