[SciPy-user] NNLS in scipy

Graeme O'Keefe graeme.okeefe@petnm.unimelb.edu...
Sun Jun 15 17:56:37 CDT 2008


Here is an implementation I put together to solve for x non-negatively  
the system: y = X.x

-------------- next part --------------
A non-text attachment was scrubbed...
Name: fnnls.py
Type: text/x-python-script
Size: 4667 bytes
Desc: not available
Url : http://projects.scipy.org/pipermail/scipy-user/attachments/20080616/436558a4/attachment.bin 
-------------- next part --------------




regards,

Graeme


On 16/06/2008, at 5:07 AM, Christian Meesters wrote:

> Hi,
>
> I'd like to perform some "non-negatively constraint least squares"
> algorithm to fit my data, like this:
>
> Signal = SUM a_i C_i
>
> where C_i is some simulated signal and a_i the amplitude contributed  
> by
> that simulated signal. Or in terms of arrays, I will have one  
> reference
> array and several arrays of simulated signals. How can find the
> (non-negative) coefficients a_i for each simulated signal array? (All
> negative contributions should be discarded.)
>
> Is there anything like that in scipy (which I couldn't find)? Or any
> other code doing that?
>
> Else I could write it myself and contribute, but having some working
> code would be nice, of course.
>
> TIA
> Christian
>
> _______________________________________________
> SciPy-user mailing list
> SciPy-user@scipy.org
> http://projects.scipy.org/mailman/listinfo/scipy-user
>




More information about the SciPy-user mailing list