Add CatBoost documentation and test coverage for Explainer

[aman-coder03]

Proposed Changes

this pr adds documentation and test coverage for using CatBoostRegressor as the model_tau estimator in the Explainer class when method="auto"

what changed

• updated the model_tau docstring to mention catboost support
• added a regression test using CatBoostRegressor, guarded with pytest.importorskip("catboost"), to verify that Explainer(method="auto") works correctly and returns feature importances with the expected shape

why

while investigating issue #826, i verified that current versions of catboost already expose the feature_importances_ attribute after fitting, so Explainer(method="auto") works without any implementation changes
this pr adds documentation and a regression test to ensure catboost support remains covered and continues to work as expected

closes #826

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.

[jeongyoonlee]

Could you reframe this PR as test + docs only?

The underlying bug doesn't reproduce on current CatBoost. CatBoostRegressor.feature_importances_ has been a class-level property since ~catboost 0.15 (2019), and check_conditions() fits the dummy model before the hasattr assertion (explainer.py:97-103) — so the original assertion already passes for CatBoost and default_importance() reads .feature_importances_ fine. Running the PR's own scenario on master (without this PR's code):

exp = Explainer(method="auto", model_tau=CatBoostRegressor(iterations=10, verbose=0), ...)
exp.get_importance()   # passes: pd.Series, len == n_features, normalized to 1

It passes, so test_explainer_auto_importance_catboost is green with and without the change, and the get_feature_importance() fallback is never reached for any of sklearn/lightgbm/xgboost/catboost (all satisfy feature_importances_ first) — it's dead code.

Please drop the _get_feature_importances helper and its fallback, keeping just the (genuinely additive) CatBoost-as-model_tau test and the docstring update. Also update the title/description away from "Bugfix" so the history doesn't record a fix for a non-bug.