Introduce n_jobs to StackingCVRegressor

[qiagu]

Description

Use the sklearn born cross_val_predict to replace the explicit cv splitting loop.
Add arguments n_jobs and pre_dispatch to be able to take advantage of parallel computation.

Related issues or pull requests

Pull Request Checklist

• Added a note about the modification or contribution to the ./docs/sources/CHANGELOG.md file (if applicable)
• Added appropriate unit test functions in the ./mlxtend/*/tests directories (if applicable)
• Modify documentation in the corresponding Jupyter Notebook under mlxtend/docs/sources/ (if applicable)
• Ran nosetests ./mlxtend -sv and make sure that all unit tests pass (for small modifications, it might be sufficient to only run the specific test file, e.g., nosetests ./mlxtend/classifier/tests/test_stacking_cv_classifier.py -sv)
• Checked for style issues by running flake8 ./mlxtend

[coveralls]

Coverage decreased (-0.002%) to 91.615% when pulling 866aff3 on qiagu:stackingcv into 8536994 on rasbt:master.

[rasbt]

That's nice, thanks for this!

[qiagu]

@rasbt Thanks for merging. I am trying to make stacking ensemble machine learning available on Galaxy. Luckily, I found this great library.

[rasbt]

Nice, haven't heard of Galaxy before but looks cool! Glad to hear this implemenation turned out to be useful for incorporating there