ENH accept string labels in classifier

[glemaitre]

closes #709

Allow to pass the original y values without to encode the labels before hand.

[codecov]

Codecov Report

Merging #718 into master will increase coverage by 0.01%.
The diff coverage is 100.00%.

@@            Coverage Diff             @@
##           master     #718      +/-   ##
==========================================
+ Coverage   96.45%   96.47%   +0.01%     
==========================================
  Files          82       82              
  Lines        4999     5026      +27     
==========================================
+ Hits         4822     4849      +27     
  Misses        177      177              

Impacted Files	Coverage Δ
imblearn/ensemble/tests/test_forest.py	100.00% <ø> (ø)
imblearn/utils/_validation.py	100.00% <ø> (ø)
imblearn/ensemble/_bagging.py	97.72% <100.00%> (+0.35%)	⬆️
imblearn/ensemble/_easy_ensemble.py	100.00% <100.00%> (ø)
imblearn/ensemble/_forest.py	97.33% <100.00%> (+0.07%)	⬆️
imblearn/pipeline.py	97.91% <100.00%> (ø)
imblearn/tests/test_pipeline.py	97.68% <100.00%> (ø)
imblearn/utils/estimator_checks.py	95.60% <100.00%> (+0.24%)	⬆️

---

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 f21bdea...fe1b627. Read the comment docs.