i using curve_fit
function find 2 coefficients , not result until altered called maxfev
larger value, since error 'maxfev=600 has been reached', took total guess , added maxfev=10000
curve_fit
function , seemed work. question is: maxfev
? do, how work, , how has affected data?
the function curve_fit
wrapper around leastsq
(both scipy.optimize library). parameter adjusting specifies how many times parameters model trying fit allowed altered, while program attempting find local minimum (see below example).
data = [(1,0),(2,1),(3,2),(4,3)...] model = a*x+b
let assume initialize a
, b
0
. program attempts once, gets given array of leastsquares back, program attempt alter either a
or b
, run again. repeats until optimal value a
, b
found (yielding lowest least squares, should a=1
, b=-1
).
the fact program can not find optimal value after 600 alterations of parameters clear indication fitting wrong model.
ps: problem has nothing ipython notebook
Comments
Post a Comment