adjusted error message

[jamesjjcondon]

What does this PR do?

Includes example of common error source

Where should the reviewer start?

n/a

How should this PR be tested?

n/a

Any background context you want to provide?

I came across this when first using TPOT with binary classes, binary-only evaluation metrics and nans that were treated as a third class. This is likely a common use-case and error for beginners.
(my first contribution : )

What are the relevant issues?

[you can link directly to issues by entering # then the number of the issue, for example, #3 links to issue 3]

Screenshots (if appropriate)

Questions:

• Do the docs need to be updated? No
• Does this PR add new (Python) dependencies? No

[coveralls]

Coverage remained the same at 96.757% when pulling d0c590a on jamesjjcondon:jamesjjcondon into 09d7645 on EpistasisLab:development.

[weixuanfu]

Thank you for rewording!