There are some algorithms described in the wikipedia:
http://en.wikipedia.org/wiki/Ensemble_learning
One way for ensemble is to combine the predictions using the accuracy and
the training data size of each model, e.g., bayesian model averaging.
Much simpler to implement, but effective, method is voting. For this, count
the number of predictions for each label from each model, and then pick the
label who got the most vote. One issue with this simple voting is that each
model should be almost equally good. For example, if you have one good
model and two so-so model, then those two so-so results may prevail.
2013/11/26 Abhi <[email protected]>
> How can we combine probabilities from multiple classifiers in sklearn?
> [Classifiers are trained on similar type datasets, difference being their
> sizes and the way each result might be used]. I am using SGDClassifier to
> train the individual classifiers, and need to choose the best amongst them.
> But as I understand I would need to normalize first before comparing
> them and was not sure how to calibrate them as such. Any pointers
> to would be helpful.
>
>
>
> ------------------------------------------------------------------------------
> Shape the Mobile Experience: Free Subscription
> Software experts and developers: Be at the forefront of tech innovation.
> Intel(R) Software Adrenaline delivers strategic insight and game-changing
> conversations that shape the rapidly evolving mobile landscape. Sign up
> now.
> http://pubads.g.doubleclick.net/gampad/clk?id=63431311&iu=/4140/ostg.clktrk
> _______________________________________________
> Scikit-learn-general mailing list
> [email protected]
> https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
>
------------------------------------------------------------------------------
Rapidly troubleshoot problems before they affect your business. Most IT
organizations don't have a clear picture of how application performance
affects their revenue. With AppDynamics, you get 100% visibility into your
Java,.NET, & PHP application. Start your 15-day FREE TRIAL of AppDynamics Pro!
http://pubads.g.doubleclick.net/gampad/clk?id=84349351&iu=/4140/ostg.clktrk
_______________________________________________
Scikit-learn-general mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
