Using fit 'exp2' an error with "weights"

Question

JJC 2013-4-12

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/71763-using-fit-exp2-an-error-with-weights

评论： Zahra Ali 2017-11-2

I've used the fit function a few times on creep data sets (i.e. time vs displacement) and have been using the 'exp2' fit type. On smaller data sets I've had no problem using this function. Now I'm looking at a 10 folder bigger data set and am getting an error.

I was previously running this and had no problem

[creep_data_fit, gof] = fit(creep_data(1:1800,1),creep_data(1:1800,2), 'exp2')

Now I'm running this and getting the following error

[creep_data_fit, gof] = fit(creep_data(1:10800,1),creep_data(1:10800,2), 'exp2')

Any ideas on why i'm getting this error?

Error using fit>iFit (line 235)
X, Y and WEIGHTS cannot have NaN values.
Error in fit (line 109)
[fitobj, goodness, output, convmsg] = iFit( xdatain, ydatain, fittypeobj, ...

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Tom Lane 2013-4-13

3
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/71763-using-fit-exp2-an-error-with-weights#answer_82080

在 MATLAB Online 中打开

Since you didn't specify weights, it seems like the NaN value must be in either x or y. You can find the usable values (using your own variable names) like this:

t = ~isnan(x) & ~isnan(y);

Then omit the NaN values from the fit:

fit(x(t),y(t),'poly1')