Update detect_problem_types implementation

[bchen1116]

fix #1469

Updated this implementation to catch Int64 dtypes. Previously, using analyze_metadata in looking_glass, if the target data was Int64, the problem_type would be classified as multiclass as long as there were >2 unique values.

After using is_numeric_dtype:

Since we drop NaN data, classifying Boolean (nullable) as a numeric dtype is ok, since we'll catch this binary case before determining if it is regression or multiclass.

[codecov]

Codecov Report

Merging #1476 (833b0f1) into main (94a816d) will increase coverage by 0.1%.
The diff coverage is 100.0%.

@@            Coverage Diff            @@
##             main    #1476     +/-   ##
=========================================
+ Coverage   100.0%   100.0%   +0.1%     
=========================================
  Files         223      223             
  Lines       15019    15024      +5     
=========================================
+ Hits        15012    15017      +5     
  Misses          7        7             

Impacted Files	Coverage Δ
evalml/problem_types/utils.py	100.0% <100.0%> (ø)
...lml/tests/problem_type_tests/test_problem_types.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 94a816d...833b0f1. Read the comment docs.

[jeremyliweishih]

good catch! LGTM

[freddyaboulton]

@bchen1116 This looks good to me!

[dsherry]

Got it, thanks @bchen1116 !

I think the ultimate goal is to update this (and all our utilities) to standardize to woodwork (#1229 ) and then check if the "numeric" semantic tag has been applied to the target. (@angela97lin FYI)