`GroupedPredictor` patch

[FBruzzesi]

Description

As discussed in #616, shrinkage was intended for regression problems and even if in some cases it doesn't raise errors, it would yield incorrect results for classification or outlier detection tasks.

This PR:

• Early raises an error for shrinkage in non-regression tasks
• Expands on GroupedPredictor docstring
• Adds two classes, GroupedRegressor and GroupedClassifier - the latter doesn't allow for shrinkage in __init__
• Fixes image rendering in docs
• Removed GroupedEstimator as we passes 0.7.0

Fixes #616

Type of change

• [X] Bug fix (non-breaking change which fixes an issue)
• [ ] New feature (non-breaking change which adds functionality)
• [X] Breaking change (fix or feature that would cause existing functionality to not work as expected)

Checklist:

• [X] My code follows the style guidelines (flake8)
• [X] I have commented my code, particularly in hard-to-understand areas
• [X] I have made corresponding changes to the documentation (also to the readme.md)
• [ ] I have added tests that prove my fix is effective or that my feature works
• [ ] I have added tests to check whether the new feature adheres to the sklearn convention
• [X] New and existing unit tests pass locally with my changes

[koaning]

@FBruzzesi Any concerns about releasing this right away?

[FBruzzesi]

@FBruzzesi Any concerns about releasing this right away?

Not sure if it's better to go 0.7.5 (as in the info admonitions) or to 0.8.0 as it has breaking changes (no more shrinkage for classification).

If you want to wait for the HierarchicalPredictors, I may need a few more days just to open the PR