OOBPredictorImportance How to interpret the values range?

2 visualizaciones (últimos 30 días)
Tiago Dias
Tiago Dias el 6 de En. de 2020
Comentada: Tiago Dias el 4 de Jun. de 2020
Hello,
To be able to calculate the importance of the predictors for TreeBagger it is needed to turn on the OOBPredictorImportance parameter
Mdl = TreeBagger(200,X,'MPG','Method','regression','Surrogate','on','PredictorSelection','curvature','OOBPredictorImportance','on');
I would like to know what is the range of the parameters, the results for my regression is beetween 0 and 1.5, is that good? bad? What more conclusions can I draw from that vector?
Thanks for your time!
Tiago

Respuestas (1)

Adrian Jacinto
Adrian Jacinto el 4 de Jun. de 2020
Hi, really this parameter have no range. This parameter only explain you how important is a band compared to other bands. When you a have a higuest values associated with a band, this indicates that this band is more important than the rest.
You can make the result more visual by applying the bar () function on the OOB vector to make a bar diagram.
  1 comentario
Tiago Dias
Tiago Dias el 4 de Jun. de 2020
Ok, thanks for you input.
I tought that perhaps it would be on percentage or something like that. IT is more quanlitative then quantitative.

Iniciar sesión para comentar.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by