Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.lang.python > #86527 > unrolled thread

Gaussian process regression

Back to article view | Back to comp.lang.python

Contents

  Gaussian process regression jaykim.huijae@gmail.com - 2015-02-26 09:59 -0800
    Re: Gaussian process regression Peter Pearson <pkpearson@nowhere.invalid> - 2015-02-27 17:55 +0000
      Re: Gaussian process regression Fabien <fabien.maussion@gmail.com> - 2015-02-27 19:33 +0100

#86527 — Gaussian process regression

Hi,

I am trying to use Gaussian process regression for Near Infrared spectra. I have reference data(spectra), concentrations of reference data and sample data, and I am trying to predict concentrations of sample data. Here is my code.

from sklearn.gaussian_process import GaussianProcess

gp = GaussianProcess()

gp.fit(reference, concentration)

concentration_pred = gp.predict(sample)


The results always gave me the same concentration even though I used different sample data. When I used some parts of reference data as sample data, it predicted concentration well. But whenever I use different data than reference data, it always gave me the same concentration. 
Can I get some help with this problem? What am I doing wrong?
I would appreciate any help.

Thanks,
Jay

[toc] | [next] | [standalone]

#86581

On Thu, 26 Feb 2015 09:59:45 -0800 (PST), jaykim.huijae@gmail.com wrote:
>
> I am trying to use Gaussian process regression for Near Infrared
> spectra. I have reference data(spectra), concentrations of reference
> data and sample data, and I am trying to predict concentrations of
> sample data. Here is my code.

>
> from sklearn.gaussian_process import GaussianProcess
> gp = GaussianProcess()
> gp.fit(reference, concentration)
> concentration_pred = gp.predict(sample)
[snip]

I'm sorry you're not getting help from this normally very helpful group.
I'd guess that's because nobody here uses sklearn.  Where did you get
sklearn?  Is it possible that there's an sklearn forum somewhere?

I've seen many of this group's regular participants go to great lengths
to help people with specialized problems, but for one of those people
to help with your problem, he or she would have to find and install
sklearn and learn enough about it to generate data sets on which
to exercise the code you've provided.  That's a lot to ask.  Can
you lower the activation barrier?

-- 
To email me, substitute nowhere->runbox, invalid->com.

[toc] | [prev] | [next] | [standalone]

#86582

On 27.02.2015 18:55, Peter Pearson wrote:
> On Thu, 26 Feb 2015 09:59:45 -0800 (PST),jaykim.huijae@gmail.com  wrote:
>> >
>> >I am trying to use Gaussian process regression for Near Infrared
>> >spectra. I have reference data(spectra), concentrations of reference
>> >data and sample data, and I am trying to predict concentrations of
>> >sample data. Here is my code.
>> >
>> >from sklearn.gaussian_process import GaussianProcess
>> >gp = GaussianProcess()
>> >gp.fit(reference, concentration)
>> >concentration_pred = gp.predict(sample)
> [snip]
>
> I'm sorry you're not getting help from this normally very helpful group.
> I'd guess that's because nobody here uses sklearn.  Where did you get
> sklearn?  Is it possible that there's an sklearn forum somewhere?

http://blog.gmane.org/gmane.comp.python.scikit-learn

Cheers,

Fabien

[toc] | [prev] | [standalone]

Back to top | Article view | comp.lang.python

csiph-web