Limit model usage for EN, XBG, CB for large multiclass problems

[bchen1116]

fix #2976

[codecov]

Codecov Report

Merging #2982 (caa7c2c) into main (981024f) will increase coverage by 0.1%.
The diff coverage is 100.0%.

@@           Coverage Diff           @@
##            main   #2982     +/-   ##
=======================================
+ Coverage   99.7%   99.7%   +0.1%     
=======================================
  Files        309     309             
  Lines      29312   29399     +87     
=======================================
+ Hits       29221   29308     +87     
  Misses        91      91             

Impacted Files	Coverage Δ
...lml/automl/automl_algorithm/iterative_algorithm.py	100.0% <100.0%> (ø)
evalml/automl/automl_search.py	99.9% <100.0%> (+0.1%)	⬆️
.../automl_tests/test_automl_search_classification.py	100.0% <100.0%> (ø)
...lml/tests/automl_tests/test_iterative_algorithm.py	100.0% <100.0%> (ø)

---

Continue to review full report at Codecov.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update 981024f...caa7c2c. Read the comment docs.

[chukarsten]

Thanks for knocking this one out!! A few things I'd like to see before we merge this: a little more documentation as noted in the review and a logger statement to appear in the verbose output of AutoML search. I think with that, in addition to all the good stuff you currently have, and this behavior is well documented and communicated clearly. Good call also making the filter_estimators function. We may need to conduct a similar test with the DefaultAlgorithm and move that function out of the IterativeAlgorithm to be used communally. An issue is filed for that : #2985 .

[freddyaboulton]

Thanks @bchen1116 ! Left some minor comments but otherwise looks great to me. I agree with the other threads on this pr as well.

[chukarsten]

Looks gucci! Thanks for addressing. Sorry for the long wait on re-review.