get_best: Accessor function for the best learner estimates

In GenericML: Generic Machine Learning Inference

Accessor function for the best learner estimates

Description

The best learner is determined by maximizing the criteria Λ and \bar{Λ}, see Sections 5.2 and 5.3 of the paper. This function accesses the estimates of these two criteria,

Usage

get_best(x)

Arguments

x	An object of the class "GenericML", as returned by the function GenericML().

Value

An object of class "best", which consists of the following components:

BLP

A string holding the name of the best learner for a BLP analysis.

GATES

A string holding the name of the best learner for a GATES analysis.

CLAN

A string holding the name of the best learner for a CLAN analysis (same learner as in GATES).

overview

A numeric matrix of the estimates of the performance measures Λ and \bar{Λ} for each learner.

See Also

GenericML(), get_BLP(), get_GATES(), get_CLAN()

Examples

if(require("rpart") && require("ranger")){
## generate data
set.seed(1)
n  <- 150                                  # number of observations
p  <- 5                                    # number of covariates
D  <- rbinom(n, 1, 0.5)                    # random treatment assignment
Z  <- matrix(runif(n*p), n, p)             # design matrix
Y0 <- as.numeric(Z %*% rexp(p) + rnorm(n)) # potential outcome without treatment
Y1 <- 2 + Y0                               # potential outcome under treatment
Y  <- ifelse(D == 1, Y1, Y0)               # observed outcome

## column names of Z
colnames(Z) <- paste0("V", 1:p)

## specify learners
learners <- c("tree", "mlr3::lrn('ranger', num.trees = 10)")

## perform generic ML inference
# small number of splits to keep computation time low
x <- GenericML(Z, D, Y, learners, num_splits = 2,
               parallel = FALSE)

## access best learner
get_best(x)

## access BLP generic targets for best learner w/o plot
get_BLP(x, learner = "best", plot = FALSE)

## access BLP generic targets for ranger learner w/o plot
get_BLP(x, learner = "mlr3::lrn('ranger', num.trees = 10)", plot = FALSE)

## access GATES generic targets for best learner w/o plot
get_GATES(x, learner = "best", plot = FALSE)

## access GATES generic targets for ranger learner w/o plot
get_GATES(x, learner = "mlr3::lrn('ranger', num.trees = 10)", plot = FALSE)

## access CLAN generic targets for "V1" & best learner, w/o plot
get_CLAN(x, learner = "best", variable = "V1", plot = FALSE)

## access CLAN generic targets for "V1" & ranger learner, w/o plot
get_CLAN(x, learner = "mlr3::lrn('ranger', num.trees = 10)",
         variable = "V1", plot = FALSE)
}

GenericML documentation built on June 18, 2022, 9:09 a.m.