Update regression metrics to handle multiseries problems

[eccabay]

Closes #4231

Our anticipated input from users for multiseries problems has one column that contains all the series targets and one column that delineates the series_id of each row. However, our estimators expect one column per series, so we will be internally converting between these two forms.

Both scikit-learn and sktime already have implementations for multioutput problems expecting the "one column per series" data format, so this PR assumes that input format as well, and just adapts the few metrics that were not already set up to handle this.

[codecov]

Codecov Report

Merging #4233 (3a79e83) into main (aa17295) will increase coverage by 0.1%.
The diff coverage is 100.0%.

@@           Coverage Diff           @@
##            main   #4233     +/-   ##
=======================================
+ Coverage   99.7%   99.7%   +0.1%     
=======================================
  Files        349     349             
  Lines      38284   38314     +30     
=======================================
+ Hits       38165   38195     +30     
  Misses       119     119             

Impacted Files	Coverage Δ
evalml/objectives/objective_base.py	100.0% <100.0%> (ø)
evalml/objectives/standard_metrics.py	100.0% <100.0%> (ø)
...lml/tests/objective_tests/test_standard_metrics.py	100.0% <100.0%> (ø)

[jeremyliweishih]

LGTM good work!

[christopherbunn]

LGTM