Unsupervised Filter Feature Selection - Rank by Correlation
5 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
I have a set of features which and I wish to rank according to their Correlation Coefficient with eachother, without accounting for the true label (that would by a Supervised feature selection, right?). My objective is selecting the first feature as the one more correlated with every other, take it out and so on.
The problem is how to test the correlation of a vector with a matrix (all the other vectors/features)? Is it possible to do this or am I doing this all right.
PS: I'm using MATLAB 2013b
Thank you all
1 comentario
Giorgio
el 21 de Ag. de 2016
Hi,
did you have a look at: http://it.mathworks.com/matlabcentral/fileexchange/56937-feature-selection-library
best wishes,
Respuestas (1)
Image Analyst
el 12 de Jul. de 2014
Yes. It is possible. Give it a shot and see what happens. Come back here with your attempt at coding if you need someone to help you.
0 comentarios
Ver también
Categorías
Más información sobre Design Condition Indicators Interactively en Help Center y File Exchange.
Productos
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!