DOC Adds note regarding plot partial dependence with the same axes

[thomasjpfan]

Reference Issues/PRs

Addresses #15581

What does this implement/fix? Explain your changes.

Adds note regarding using plot_partial_dependence with the same axes

Any other comments?

[adrinjalali]

Test failing

___ [doctest] sklearn.inspection._partial_dependence.plot_partial_dependence ___
[gw0] linux -- Python 3.7.5 /usr/share/miniconda/envs/testvenv/bin/python
427 
428     .. note::
429 
430         :func:`plot_partial_dependence` does not support using the same axes
431         with multiple calls. To plot the the partial dependence for multiple
432         estimators, please pass the axes created by the first call to the
433         second call::
434 
435           >>> from sklearn.inspection import plot_partial_dependence
436           >>> disp1 = plot_partial_dependence(...)
UNEXPECTED EXCEPTION: TypeError("plot_partial_dependence() missing 2 required positional arguments: 'X' and 'features'")
Traceback (most recent call last):

  File "/usr/share/miniconda/envs/testvenv/lib/python3.7/doctest.py", line 1329, in __run
    compileflags, 1), test.globs)

  File "<doctest sklearn.inspection._partial_dependence.plot_partial_dependence[1]>", line 1, in <module>

TypeError: plot_partial_dependence() missing 2 required positional arguments: 'X' and 'features'

/home/vsts/work/1/s/sklearn/inspection/_partial_dependence.py:436: UnexpectedException

[glemaitre]

Only a nitpicks, LGTM

[glemaitre]

Suggested change

	>>> disp1 = plot_partial_dependence(est, X) #doctest: +SKIP
	>>> disp1 = plot_partial_dependence(est, X) # doctest: +SKIP

[glemaitre]

Suggested change

	... ax=disp1.axes_) #doctest: +SKIP
	... ax=disp1.axes_) # doctest: +SKIP

[glemaitre]

@thomasjpfan Thanks