[SciPy-User] fit with 3 parameters ok, fit with 4 is going wrong!

[Gabriele Brambilla]

Hi guys! now it works (not perfectly but there has been a lot of progress!)
first the expression I wrote was wrong for the reason outlined by Eric
Hermes, now I use: -(x0/c)**d.
Second I've tried a way to give to the fit a more precise start point.

thank you all

Gabriele



2014-02-06 Daπid <davidmenhur at gmail.com>:

> On 6 February 2014 18:55, Matt Newville <newville at cars.uchicago.edu>wrote:
>
>> I'm interested, but slightly confused.   Iminuit / probfit is described
>> as BSD, but depends on (and includes?) Minuit - isn't that GPL?
>
>
> The license says iminuit is MIT, but Minuit is GPLv2. So, the Python part,
> that wraps the C code is MIT. One could deattach it and use a different
> algorithm, or a Minuit implementation under another license.
>
> Probfit provides convenience functions to do regressions and plotting. For
> example, chi2 = Chi2Regression(fun, x, y) creates a callable object that
> calculates the chi2 for the function and the defined data, but has methods
> like chi2.draw to plot it, and it can obtain the plotting parameters from
> an iminuit object (the dictionary Minuit.values), but could work perfectly
> well with some other object presenting the same interface.
>
> I am currently using it to fit a lorentzian curve to a noisy profile. I
> have fairly nice approximations to the actual values (looking at the
> maximum, for example), and speed is critical, so I tried a few approaches
> and iminuit + probfit were the fastest, by 20 to 50%.
>
>
> _______________________________________________
> SciPy-User mailing list
> SciPy-User at scipy.org
> http://mail.scipy.org/mailman/listinfo/scipy-user
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mail.scipy.org/pipermail/scipy-user/attachments/20140206/7432ca9c/attachment.html>