Compute ranks to select the copula.

[JDTheRipperPC]

Resolves #101

Compute ranks to select the copula.

Now return a copula, not a tuple with copula_type and theta. Bivariate.select_copula usage inside the project adapted.

Also, we still under discussion if there are a way to get the selected copula without computing the rank.

Important

A few tests are raising exceptions after changing the way the method return the selected copula.

tests/copulas/multivariate/test_tree.py

• TestCenterTree.test_first_tree_likelihood
• TestCenterTree.test_second_tree_likelihood
• TestRegularTree.test_first_tree_likelihood
• TestDirectTree.test_first_tree_likelihood
• TestDirectTree.test_second_tree_likelihood

This tests has been marked with @pytest.mark.xfail temporally.

[codecov-io]

Codecov Report

Merging #104 into master will increase coverage by 0.64%.
The diff coverage is 92.5%.

@@            Coverage Diff             @@
##           master     #104      +/-   ##
==========================================
+ Coverage    92.1%   92.74%   +0.64%     
==========================================
  Files          18       18              
  Lines        1305     1310       +5     
==========================================
+ Hits         1202     1215      +13     
+ Misses        103       95       -8

Impacted Files	Coverage Δ
copulas/multivariate/tree.py	95.33% <100%> (+0.05%)	⬆️
copulas/bivariate/gumbel.py	89.28% <50%> (-1.46%)	⬇️
copulas/bivariate/base.py	89.5% <93.33%> (+1.16%)	⬆️
copulas/bivariate/clayton.py	86.66% <0%> (+15.55%)	⬆️

---

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 16e49ba...164381d. Read the comment docs.

[csala]

Good work @JDTheRipperPC !!