Running Search with n_jobs>1 throws Deap Attribute Error. Official sklearn example

[luded]

code downloaded from sklearn for GridSearchCV
replaced by EvolutionaryAlgorithmSearchCV. Works only for n_jobs=1. Else throws a Deap exception.

python code attached for reproduction.

grid_search_text_feature_extraction.txt

[luded]

I have now seen your improvement with pmap. However passing n_jobs=pool.map yields exactly the same error. I could not find anywhere a single working example of how to use multi-thread in window. would be grateful if you could point me to one.
Thanks

[luded]

Tested on Linux. The error is gone, but there is no sign of genetic search running on multiple threads. Actually the sklearn GridSearchCV finishes faster than EvolutionaryAlgorithmSearchCV.

Also I consistently get (in Win and Linux) sligthly better results (fitness) on sklearn-deap than on sklearn, and that's impossible because sklearn performs an exhaustive search.

is this project still alive? is there anyone actually using it that can prove it works as it should?