## S3 method for class 'formula':
blackboost(formula, data = list(), weights = NULL, ...)
## S3 method for class 'matrix':
blackboost(x, y, weights = NULL, ...)
blackboost_fit(object, tree_controls =
ctree_control(teststat = "max",
testtype = "Teststatistic",
mincriterion = 0,
maxdepth = 2),
fitmem = ctree_memory(object, TRUE), family = GaussReg(),
control = boost_control(), weights = NULL)
boost_data
, see boost_dpp
.TreeControl
, which can be
obtained using ctree_control
.
Defines hyper parameters TreeFitMemory
.boost_family-class
,
implementing the negative gradient corresponding
to the loss function to be optimized, by default,
squared boost_control
which defines the hyper parameters of the
boosting algorithm.gbm
. The
main difference is that arbitrary loss functions to be optimized
can be specified via the family
argument to blackboost
whereas
gbm
uses hard-coded loss functions.
Moreover, the base learners (conditional
inference trees, see ctree
) are a little bit more flexible.The regression fit is a black box prediction machine and thus hardly interpretable.
Usually, the formula based interface blackboost
should be used,
the fitting procedure without data preprocessing is assessible
via blackboost_fit
, for example for cross-validation.
Greg Ridgeway (1999), The state of boosting. Computing Science and Statistics, 31, 172--181.
Peter Buhlmann and Torsten Hothorn (2006),
Boosting algorithms: regularization, prediction and model fitting.
Submitted manuscript.
### a simple two-dimensional example: cars data
cars.gb <- blackboost(dist ~ speed, data = cars,
control = boost_control(mstop = 50))
cars.gb
### plot fit
plot(dist ~ speed, data = cars)
lines(cars$speed, predict(cars.gb), col = "red")
Run the code above in your browser using DataLab