crossval
Cross-validate regression ensemble model
Description
returns a cross-validated (partitioned) regression ensemble model
(cvens
= crossval(ens
)cvens
) from a trained regression ensemble model
(ens
). By default, crossval
uses 10-fold
cross-validation on the training data to create cvens
, a RegressionPartitionedEnsemble
model.
specifies additional options using one or more name-value arguments. For example, you
can specify the cross-validation partition, the fraction of data for holdout validation,
and the number of folds to use.cvens
= crossval(ens
,Name=Value
)
Input Arguments
Examples
Alternatives
You can create a cross-validation ensemble directly from the data, instead of creating
an ensemble followed by a cross-validation ensemble. To do so, include one of these five
options in fitrensemble
: CrossVal
,
CVPartition
, Holdout
, Leaveout
,
or KFold
.
Extended Capabilities
Version History
Introduced in R2011a
See Also
cvpartition
| kfoldLoss
| RegressionPartitionedEnsemble
| RegressionEnsemble
| fitrensemble