RegressionTree cannot use "predict" method?

Hello there,

I'm using Matlab R2013a and was able to train a regression tree using RegressionTree.fit(). However, when I used "predict(rtree, test_data)," I got the following error message:

Error using predict (line 85) Systems of classreg.learning.partition.RegressionPartitionedModel class cannot be used with the "predict" command. Convert the system to an identified model first, such as by using the "idss" command.

I believe using "predict" method confused a dynamic model estimation. Can you please tell me what was wrong?

Young

Answer 1

[Young]

As long as you're not using 'crossval' option, like

 rtree = RegressionTree( x, y, 'crossval', 'on' );

The following should work:

 [yfit, node] = predict( rtree, test_data );

So, just train a regression tree using "rtree = RegressionTree( train_data, train_label ); and then use it like, [yfit, node] = predict( rtree, test_data )

Young

[reem aldaihani]

What if we will use cross-validation? This is part of my code: cvmodel=fitcknn(training_Best,class1, 'Distance',@mindistnew, 'NumNeighbors',1, 'KFold',10); cvclass=predict(cvmodel, testing_Best);

and I received this error:

Systems of classreg.learning.partition.ClassificationPartitionedModel class cannot be used with the "predict" command. Convert the system to an identified model first, such as by using the "idss" command.

Could you please help me to fix this ASAP.

Answer 2

[Sincloe Brans]

Just do

Yfit = tree([Xnew]);

where tree is your regression or classreg tree and Xnew the new X's to be predicted.