for 'other workflows' datalab tutorial, need to show how to detect all issue types and use a custom regression model for detecting label errors

[jwmueller]

ideal code would be (this is just pseudocode):

issue_types = get_default_issue_types(problem_type='regression')  # contains many Nones / missing keys (that are left at defaults used internally)
issue_types['label']['cleanlearning_kwargs']['model'] = MySklearnRegressor(...)

datalab.find_issues(features, ..., issue_types=issue_types) 
# will find label errors using my regression model, and simultanoeusly detect many other issue types

[jwmueller]

first need to address this:
#920

so we have a place to store the new code