Hi Mohit.
Generally all algorithms in sklearn assume that all features are continuous.
Does discrete in your case mean categorial ('0'=blue, '1'=red,
'2'=green)? Then you should probably
recode these features using a one-hot encoding as interpreting them as
continuous will be meaningless.
I am not sure in what state the functionality for this in sklearn is,
maybe someone else can comment on that.
If they are discrete but still have an ordering, KMeans might work.
In these cases I found normalizing them with ``Scaler`` helpful.
Cheers,
Andy
On 03/28/2012 08:14 PM, Mohit Singh wrote:
Hi,
Does the knn library of scikits deal with features which are both
continous and discrete?
I have a feature as numpy array.. some of which are real-valued and
some are disrete but I havent mentioned anything explicitly??
I am not sure whether it will work or not or how will the algorithm
know that these are discrete and continous features?
Thanks
--
Mohit
"When you want success as badly as you want the air, then you will get
it. There is no other secret of success."
-Socrates
------------------------------------------------------------------------------
This SF email is sponsosred by:
Try Windows Azure free for 90 days Click Here
http://p.sf.net/sfu/sfd2d-msazure
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
------------------------------------------------------------------------------
This SF email is sponsosred by:
Try Windows Azure free for 90 days Click Here
http://p.sf.net/sfu/sfd2d-msazure
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
