curve fitting with python

Question

I'm trying to fit some data and stuff, I know there is a simple command to do this with python/numpy/matplotlib, but I can't find it. I think it is something like

popt,popc = numpy.curvefit(f,x)

where popt is the paramters of f, popc is the fit quality and f is a predefined function of f. Does any of you know it?

If this is a one-off, it's easier to just plug the values into the function finder at http://zunzun.com/ and let it find the best matching curve. Their Python code is available, too. — endolith, Dec 02 '11 at 14:57

score 29 · Accepted Answer · answered Nov 26 '11 at 19:14

29

Take a look at scipy.optimize.curve_fit:

scipy.optimize.curve_fit(f, xdata, ydata, p0=None, sigma=None, **kw)

Use non-linear least squares to fit a function, f, to data.

answered Nov 26 '11 at 19:14

ars

120,335
23
147
134

One question: is there an easy way to get R-squared value out of curve_fit, or get SSE so that I can calculate R-squared? I can do some work and get it done in scipy.optimize.leastsq, but the code will be much more verbose. – Yuxiang Wang Aug 20 '13 at 02:36

score -1 · Answer 2 · answered Nov 26 '11 at 19:17

-1

Found it. Curve_fit from optimize in scipy

answered Nov 26 '11 at 19:17

Yotam

10,295
30
88
128

Isn't this answer a duplicate of the accepted answer? – user May 20 '15 at 09:12

curve fitting with python

2 Answers2

Linked