[pymvpa] regression analysis to predict subject-specific score
Yaroslav Halchenko
debian at onerussian.com
Mon Mar 12 17:00:43 UTC 2012
ah -- I should have thought about that...:
In [27]: print ds.targets
['-0.060484' '0.125' '-0.096774' '0' '0.065524' '0.13206' '0' '-0.0098118' ... ]
i.e. they are strings, whenever you want them to be numeric
so just do smth like
ds.targets = ds.targets.astype(float)
On Mon, 12 Mar 2012, David V. Smith wrote:
> Thanks for the help. The code you sent works on the 'chirp_linear' dataset, but it fails with the FailedToPredictError on my data. Also, thanks for the point about the NFoldPartitioner. I'll switch over to the HalfPartitioner.
> I just sent you the data using the command you provided. Let me know if you don't get it.
> Cheers,
> David
--
=------------------------------------------------------------------=
Keep in touch www.onerussian.com
Yaroslav Halchenko www.ohloh.net/accounts/yarikoptic
More information about the Pkg-ExpPsy-PyMVPA
mailing list