Train additional trees and add to ensemble
Syntax
B = growTrees(B,ntrees)
B = growTrees(B,ntrees,'param1',val1,'param2',val2,...)
Description
B = growTrees(B,ntrees) grows ntrees new
trees and appends them to those trees already stored in the ensemble B.
B = growTrees(B,ntrees,'param1',val1,'param2',val2,...) pecifies
optional parameter name/value pairs:
| 'nprint' | Specifies that a diagnostic message showing training progress should
display after every value training cycles (grown
trees). Default is no diagnostic messages. |
| 'options' | A struct that specifies options that govern computation when
growing the ensemble of decision trees. One option requests that the
computation of decision trees on multiple bootstrap replicates uses
multiple processors, if the Parallel Computing Toolbox is available.
Two options specify the random number streams to use in selecting
bootstrap replicates. You can create this argument with a call to statset.
You can retrieve values of the individual fields with a call to statget. Applicable statset parameters
are:'UseParallel' — If 'always' and
if a matlabpool of the Parallel Computing Toolbox is
open, compute decision trees drawn on separate boostrap replicates
in parallel. If the Parallel Computing Toolbox is not installed,
or a matlabpool is not open, computation occurs
in serial mode. Default is 'never', or serial computation. 'UseSubstreams' — If 'always' select
each bootstrap replicate using a separate Substream of the random
number generator (aka Stream). This option is available only with RandStream types
that support Substreams. Default is 'never', do
not use a different Substream to compute each bootstrap replicate. 'Streams' — An object of
the RandStream class, or a cell array of RandStream objects.
Default is an empty cell array. If you do not supply a value
for this parameter, TreeBagger uses the default RandStream on
each MATLAB executable in selecting bootstrap replicates. Otherwise, TreeBagger selects
bootstrap replicates using the supplied RandStream object(s).
If you select 'UseSubstreams', the Streams parameter, if
present, must be a scalar RandStream object. If
you do not select 'UseSubstreams', then the Streams parameter,
if present, must match the number of processors used for the computation.
For serial computation, the Streams parameter must
be a scalar. If computation is distributed ('UseParallel' is 'always' and
a matlabpool is open), then the Streams parameter
must be a cell array of the same length as the matlabpool size.
In this case, each element of the cell array supplies the random number
generator for bootstrap sampling on one of the parallel workers.
|
See Also
classregtree
 | gpstat | | grp2idx |  |
Includes the most popular MATLAB recorded presentations with Q&A sessions led by MATLAB experts.
Get the Interactive Kit
Store 
