[SciPy-user] leastsq information message

Tommy Grav tgrav@mac....
Thu Apr 19 08:05:40 CDT 2007


I am using the scipy.optimize.leastsq to find best solution to a
Fourier Analysis of the rotational lightcurve of asteroids. The
function works well and finds good solutions but I keep getting
an information message:

Both actual and predicted relative reductions in the sum of squares
   are at most 0.000000

I am calling the method with

     res = leastsq(diffunc,x0,args= 
(period,atime,amag,amerr,ahindex,norder),full_output=1,col_deriv=0,epsfc 
n=0.01)

so I am asking the function do estimate the derivatives. Can
anyone enlighten me as to what the information message is
caused by and if there is some way of improving my fit to
avoid it.

Cheers
   Tommy



More information about the SciPy-user mailing list