Add DecisionTreeClassifier and DecisionTreeRegressor to AutoML

[angela97lin]

Closes #1236

Quip doc here: https://alteryx.quip.com/u5KjAUW92aeS/Adding-DecisionTree-Estimators-in-EvalML

[codecov]

Codecov Report

Merging #1255 into main will not change coverage.
The diff coverage is 100.00%.

@@           Coverage Diff           @@
##             main    #1255   +/-   ##
=======================================
  Coverage   99.93%   99.93%           
=======================================
  Files         208      208           
  Lines       13211    13211           
=======================================
  Hits        13203    13203           
  Misses          8        8           

Impacted Files	Coverage Δ
evalml/utils/gen_utils.py	100.00% <ø> (ø)
evalml/tests/pipeline_tests/test_pipelines.py	100.00% <100.00%> (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 081806a...80efa3e. Read the comment docs.

[freddyaboulton]

@angela97lin I think this looks great! I left a comment on the performance tests explaining why I think it's ok to add these estimators to search.

[jeremyliweishih]

☘️

[bchen1116]

Looks great!

[dsherry]

@angela97lin awesome!!! Love the analysis here.

I'd like to understand a bit more about what those 4 outlier datasets were in the validation accuracy graph. That said, I'd be shocked if those had anything to do with decision trees -- I suspect a bug with looking glass, or possibly a bug with automl. So, no need to hold merge for that. But let's discuss.