Fix Filter F doesn't work with latest statsmodels' F test fvalue format

[paullo0106]

Proposed changes

This PR fixes #503.

In previous versions of statsmodels, f_test() of OLS model had fvalue in 2D (1x1) numpy array format, but it now becomes a single float value in the recent versions (please see the change description and the respective PR on statsmodels repo).

Similar to the diff in statsmodels repo, by applying float() to F_test.fvalue, we can safely convert the returned value to a single float number for both scenarios in our feature selection F filter, regardless of the version of statsmodels.

>>> fvalue = array([[194.9527]])
>>> fvalue.shape
(1, 1)
>>> float(fvalue)
194.9527

In addition, added test cases for Feature selection functions

Types of changes

What types of changes does your code introduce to CausalML?
Put an x in the boxes that apply

• Bugfix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Documentation Update (if none of the other choices apply)

Checklist

Put an x in the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your code.

• I have read the CONTRIBUTING doc
• I have signed the CLA
• Lint and unit tests pass locally with my changes
• I have added tests that prove my fix is effective or that my feature works
• I have added necessary documentation (if appropriate)
• Any dependent changes have been merged and published in downstream modules

Further comments

N/A

[paullo0106]

note: I use black to reformat optimize/__init__.py and optimize/pns.py along with my tests/test_feature_selection.py to pass Lint, for the most part, the previous failures was due to the use of single quote rather than double quotes

[jeongyoonlee]

LGTM. Thanks!