Fix the bug of incorrent result in qini for multiple models

[enzoliao]

Proposed changes

Similar to #273 , the get_qini function re-uses the same df during evaluation for multiple models.
Therefore, result of the second model could be influenced by the first model.

This PR will fix the issue #519 by copying a new sorted_df in evaluation for each model.

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

If this is a relatively large or complex change, kick off the discussion by explaining why you chose the solution you did and what alternatives you considered, etc. This PR template is adopted from appium.

[CLAassistant]

All committers have signed the CLA.

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

enzoliao seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[ppstacy]

Hi @enzoliao thanks for submitting the PR! LGTM, wondering do you think if you can add the test code for this or we could open an issue to address it separately as well? T

[jeongyoonlee]

LGTM. Thanks for catching this.

[enzoliao]

Hi @enzoliao thanks for submitting the PR! LGTM, wondering do you think if you can add the test code for this or we could open an issue to address it separately as well? T

Hi @ppstacy . Thank you for your reviewing and it's okay for me to add some testing code. I'm wondering where should I put test code. Is it okay to add a new test_metrics.py in tests?

[enzoliao]

Just add a simple test here. It will make sure that qini_score won't give different scores when calling with other models.
Probably it's better for me to open a new PR for adding tests after this one is merged?

[ppstacy]

Hi @enzoliao thanks for preparing the test code. Yeah we can merge this one first.