These are objects representing fitted gbm
s.
the "intercept" term, the initial predicted value to which trees make adjustments
a vector containing the fitted values on the scale of regression function (e.g. log-odds scale for bernoulli, log scale for poisson)
a vector of length equal to the number of fitted trees containing the value of the loss function for each boosting iteration evaluated on the training data
a vector of length equal to the number of fitted trees containing the value of the loss function for each boosting iteration evaluated on the validation data
if cv.folds
<2 this component is NULL. Otherwise, this
component is a vector of length equal to the number of fitted trees
containing a cross-validated estimate of the loss function for each boosting
iteration
a vector of length equal to the number of fitted trees
containing an out-of-bag estimate of the marginal reduction in the expected
value of the loss function. The out-of-bag estimate uses only the training
data and is useful for estimating the optimal number of boosting iterations.
See gbm.perf
a list containing the tree structures. The components are best
viewed using pretty.gbm.tree
a list of all the categorical splits in the collection of
trees. If the trees[[i]]
component of a gbm
object describes a
categorical split then the splitting value will refer to a component of
c.splits
. That component of c.splits
will be a vector of length
equal to the number of levels in the categorical split variable. -1 indicates
left, +1 indicates right, and 0 indicates that the level was not present in the
training data
If cross-validation was performed, the cross-validation predicted values on the scale of the linear predictor. That is, the fitted values from the ith CV-fold, for the model having been trained on the data in all other folds.
The following components must be included in a legitimate gbm
object.