Feature range parameter support

[namanmistry]

Description

As described in the issue Replace min_features and max_features in ExhaustiveFeatureSelector by feature_range and recipe #260 I have added support for new parameter feature_range in class ExhaustiveFeatureSelector. The priority of the parameters is still the same so it does not break the code base.

Related issues or pull requests

Fixes ``Replace min_features and max_features in ExhaustiveFeatureSelector by feature_range and recipe#260 partially. stillrecipe` parameter is remaining.

Pull Request Checklist

• [x] Added a note about the modification or contribution to the ./docs/sources/CHANGELOG.md file (if applicable)
• [x] Added appropriate unit test functions in the ./mlxtend/*/tests directories (if applicable)
• [x] Ran PYTHONPATH='.' pytest ./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., PYTHONPATH='.' pytest ./mlxtend/classifier/tests/test_stacking_cv_classifier.py -sv)
• [x] Checked for style issues by running flake8 ./mlxtend

[codecov[bot]]

Codecov Report

Patch coverage: 20.00% and project coverage change: -0.08 :warning:

Comparison is base (8ae4570) 77.27% compared to head (7d1a00c) 77.19%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #1044      +/-   ##
==========================================
- Coverage   77.27%   77.19%   -0.08%     
==========================================
  Files         200      200              
  Lines       11308    11321      +13     
  Branches     1484     1487       +3     
==========================================
+ Hits         8738     8739       +1     
- Misses       2351     2362      +11     
- Partials      219      220       +1     

Impacted Files	Coverage Δ
...d/feature_selection/exhaustive_feature_selector.py	70.58% <20.00%> (-4.70%)	:arrow_down:

:umbrella: View full report in Codecov by Sentry.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[rasbt]

Thanks a lot for the PR! If you have time, could you add a few unit tests to make sure it works as intended?

[namanmistry]

Hello @rasbt, Actually I am very new to open source and this is the first repo that I am contributing to. So could you please elaborate on how to add unit tests and possibly share some resources? Thank you.

[NimaSarajpoor]

Hello @rasbt, Actually I am very new to open source and this is the first repo that I am contributing to. So could you please elaborate on how to add unit tests and possibly share some resources? Thank you.

I was just wandering and noticed your comment. You should add a test function in https://github.com/rasbt/mlxtend/blob/master/mlxtend/feature_selection/tests/test_exhaustive_feature_selector.py to test whether the new changes work properly or not. I suggest that you go and checkout some of the existing test functions in the provided link to get some idea. Then, you should start write a test function. It is not always straightforward and you need to think how to assert the outcome of the function when user provides input considering the changes you applied.

I think @rasbt can definitely explain better when he gets a chance to get back to you. In the meantime, you may just go through the test functions in the provided link to better understand how tests are written.