Question: why maintaining this code aside sklearn mixture GMM ?

AlexanderFabisch / gmr

Gaussian Mixture Regression

https://alexanderfabisch.github.io/gmr/

BSD 3-Clause "New" or "Revised" License

168 stars 49 forks source link

Question: why maintaining this code aside sklearn mixture GMM ? #3

Closed show0k closed 8 years ago

show0k commented 9 years ago

Hi, The main part of this code is present or rewrited in GMM mixture in scikit-learn. Is there any reason to continue to develop it instead of modifying the sklearn version ?

AlexanderFabisch commented 9 years ago

Hi, some features of this library do not fit the sklearn API (conditioning, marginalization). There was a discussion on the sklearn mailing list some month ago.

show0k commented 9 years ago

ok, I think you should highlight differences between both implementations because this is not clear for lambda users :)

AlexanderFabisch commented 9 years ago

I had to google the term 'lambda user'. :) Can you make a suggestion where to put the explanation?

show0k commented 9 years ago

I had to google the term 'lambda user'.

Sorry, it must be used more often in French than in English/Germain!

Can you make a suggestion where to put the explanation?

A simple note in the README.rst file would be already great.

AlexanderFabisch commented 8 years ago

See c68a014