Scipy：使用optimize.leastsq时拟合参数的界限

Question

I am using optimize.leastsq to fit data. I would like to constrain the fitting parameter(s) to a certain range. Is it possible to define bounds when using optimize.leastsq? Bounds are implemented in optimize.fmin_slsqp, but I'd prefer to use optimize.leastsq.

Answer 1

I think the standard way of handling bounds is by making the function to be minimized (the residuals) very large whenever the parameters exceed the bounds.

import scipy.optimize as optimize
def residuals(p,x,y):
    if within_bounds(p):
        return y - model(p,x)
    else:
        return 1e6

p,cov,infodict,mesg,ier = optimize.leastsq(
    residuals,p_guess,args=(x,y),full_output=True,warning=True)

Answer 2

I just found this a short time ago

http://code.google.com/p/nmrglue/source/browse/trunk/nmrglue/analysis/leastsqbound.py

It uses parameter transformation to impose box constraints. It also calculates the adjusted covariance matrix for the parameter estimates.

BSD licensed, but I haven't tried it out yet.

Answer 3

You might find
https://lmfit.github.io/lmfit-py/ useful for this. It allows upper / lower bounds for each variable, and allows algebraic constraints between parameters.