Support different inputs for ROC

[yafimvo]

Describe your changes

Added support for 3 different inputs for ROC curve: lables/classes array, onehot encoded array, and array of values.

array([0, 1, 2])

array([[0, 1, 0], 
        [1, 0, 0], 
        [0, 0, 1]])

array([[0.1, 0.8, 0.1], 
        [0.8, 0.1, 0.1], 
        [0.1, 0.1, 0.8]])

Issue ticket number and link

Closes #98

Checklist before requesting a review

• I have performed a self-review of my code
• I have added thorough tests (when necessary).
• I have added the right documentation (when needed). Product update? If yes, write one line about this update.

---

📚 Documentation preview 📚: https://sklearn-evaluation--221.org.readthedocs.build/en/221/

[coveralls]

Pull Request Test Coverage Report for Build 3951368466

Warning: This coverage report may be inaccurate.

This pull request's base commit is no longer the HEAD commit of its target branch. This means it includes changes from outside the original pull request, including, potentially, unrelated coverage changes.

• For more information on this, see Tracking coverage changes with pull request builds.
• To avoid this issue with future PRs, see these Recommended CI Configurations.
• For a quick fix, rebase this PR at GitHub. Your next report should be accurate.

Details

• 14 of 14 (100.0%) changed or added relevant lines in 1 file are covered.
• No unchanged relevant lines lost coverage.
• Overall coverage increased (+0.2%) to 94.641%

---

Totals
Change from base Build 3949074078:	0.2%
Covered Lines:	2649
Relevant Lines:	2799

---

💛 - Coveralls

[yafimvo]

@edublancas @idomic
I added an example to classifications.

I think it's not the best example for ROC since the accuracy is almost 100% and the curves are "too good"

[idomic]

Looking good, just rebase on main and let's merge this.

[edublancas]

let's move this to the docstring. and clarify that the first two formats are for the y_true argument and the second format is for y_score

[edublancas]

there's an error here, y_pred_dt is created with y_pred_dt = dt_model.predict(X_test)

but it should be y_pred_dt = dt_model.predict_proba(X_test)

note that some plots like confusion matrix need the output of predict, and others like roc need predict_proba

[edublancas]

found a minor issue

[yafimvo]

@edublancas @idomic
This PR should be closed since we took another approach where ROC inputs should be "scores" like for y_score and "classes"/"one hot" for y_test.