Generic handling of sklearn distance metric

This PR fixes #1296 which reported that Yellowbrick was being too restrictive of what distance metrics were allowed to be used with the KElbow visualizer and did not generalize to all scikit-learn distance metrics.

I have made the following changes:

Removed the DISTANCE_METRICS string constants
Ensured that callables were eligible to be distance metrics
Used sklearn.metrics.DistanceMetric.get_metric to validate if the metric was good or not.

There was already a test in place for testing that a YellowbrickValueError is raised if a bad metric is passed into the visualizer, and this test is still passing.

Sample Code and Plot

Previously we were unable to run the following code, it should now be possible:

viz = KElbowVisualizer(distance_metric="chebyshev") 
viz.fit(X_train, y_train)
viz.show()

CHECKLIST

[x] Is the commit message formatted correctly?
[ ] Have you noted the new functionality/bugfix in the release notes of the next release?

[ ] Included a sample plot to visually illustrate your changes?
[x] Do all of your functions and methods have docstrings?
[x] Have you added/updated unit tests where appropriate?
[ ] Have you updated the baseline images if necessary?
[x] Have you run the unit tests using pytest?
[x] Is your code style correct (are you using PEP8, pyflakes)?
[ ] Have you documented your new feature/functionality in the docs?

[ ] Have you built the docs using make html (must be run from docs/)?

DistrictDataLabs / yellowbrick

Generic handling of sklearn distance metric #1300

Sample Code and Plot

CHECKLIST

Codecov Report