DOC: fix cookbook groupby & transform example

[julianste]

In the example, all negative values of a group should be replaced by the mean of the rest of the group. The linked stackoverflow output has it right: https://stackoverflow.com/questions/14760757/replacing-values-with-groupby-means

We have to negate the first argument of DataFrame.where here, since this should be the condition when the value stays the same (and this should be the case for g>=0.)

pandas df.where behavior is pretty weird when coming from Spark world :)

• closes #xxxx (Replace xxxx with the Github issue number)
• Tests added and passed if fixing a bug or adding a new feature
• All code checks passed.
• Added an entry in the latest doc/source/whatsnew/vX.X.X.rst file if fixing a bug or adding a new feature.

[mroeschke]

Thanks @julianste