agtboost (version 0.9.3)

predict.Rcpp_GBT_COUNT_AUTO: aGTBoost Count-Regression Auto Prediction

Description

predict is an interface for predicting from a agtboost model.

Usage

# S3 method for Rcpp_GBT_COUNT_AUTO
predict(object, newdata, ...)

Arguments

object

Object or pointer to object of class GBT_ZI_MIX

newdata

Design matrix of data to be predicted. Type matrix

...

additional parameters passed. Currently not in use.

Value

For regression or binary classification, it returns a vector of length nrows(newdata).

Details

The prediction function for agtboost. Using the generic predict function in R is also possible, using the same arguments.

References

Berent <U+00C5>nund Str<U+00F8>mnes Lunde, Tore Selland Kleppe and Hans Julius Skaug, "An Information Criterion for Automatic Gradient Tree Boosting", 2020, https://arxiv.org/abs/2008.05926

See Also

gbt.train

Examples

# NOT RUN {
## A simple gtb.train example with linear regression:
## Random generation of zero-inflated poisson
2+2

# }