CR_FunctionCombiner: Competing Risk Function Combiner
In jatherrien/largeRCRF: Large Random Competing Risks Forests

Description Usage Arguments Details Examples

Creates a CompetingRiskFunctionCombiner rJava object, which is used internally for constructing a forest. The forest uses it when creating predictions to average the cumulative incidence curves, cause-specific cumulative hazard functions, and Kaplan-Meier curves generated by each tree into individual functions.

1	CR_FunctionCombiner(events, times = NULL)

`events`	A vector of integers specifying which competing risks event functions should be processed. This should correspond to all of the competing risk events that can occur, from 1 to the largest number.
`times`	An optional numeric vector that forces the output functions to only update at these time points. Pre-specifying the values can result in faster performance when predicting, however if the times are not exhaustive then the resulting curves will not update at that point (they'll be flat). If left blank, the package will default to using all of the time points.

The user only needs to pass this object into train as the forestResponseCombiner parameter.

T1 <- rexp(1000)
T2 <- rweibull(1000, 1, 2)
C <- rexp(1000)

u <- round(pmin(T1, T2, C))
# ...

forestCombiner <- CR_FunctionCombiner(1:2) # there are two possible events
# or, since we know that u is always an integer
forestCombiner <- CR_FunctionCombiner(1:2, 0:max(u))