Variable importance for predictive variables

Variable importance in subgroup identification for predictive variables.

MrSImp(
  dataframe,
  role,
  B = 100,
  bestK = 1,
  maxDepth = 5,
  minTrt = 5,
  minData = max(c(minTrt * maxDepth, NROW(Y)/20)),
  batchNum = 1L,
  faster = FALSE,
  display = FALSE,
  treeName = paste0("tree_", format(Sys.time(), "%m%d"), ".yaml"),
  nodeName = paste0("node_", format(Sys.time(), "%m%d"), ".txt"),
  impName = paste0("imp_", format(Sys.time(), "%m%d"), ".txt")
)

Arguments

dataframe	train data frame
role	role follows GUIDE role
B	bootstrap number default = 100
bestK	number of covariates in the regression model
maxDepth	maximum tree depth
minTrt	minimum treatment and placebo sample in each node
minData	minimum sample in each node
batchNum	related with exhaustive search for numerical split variable
faster	related with tree split searching
display	Whether display tree in the end
treeName	yaml file for save the tree
nodeName	file same for each node
impName	important variable file name

Value

A list contains importance score variable names and roles

imp

Importance score data frame

role

Role for each variable

Settings

Settings used to build the tree

Details

MrSGUIDE variable importance

Examples

library(MrSGUIDE)
set.seed(1234)

N = 200
np = 3

numX <- matrix(rnorm(N * np), N, np) ## numerical features
gender <- sample(c('Male', 'Female'), N, replace = TRUE)
country <- sample(c('US', 'UK', 'China', 'Japan'), N, replace = TRUE)

z <- sample(c(0, 1), N, replace = TRUE) # Binary treatment assignment

y1 <- numX[, 1] + 1 * z * (gender == 'Female') + rnorm(N)
y2 <- numX[, 2] + 2 * z * (gender == 'Female') + rnorm(N)

train <- data.frame(numX, gender, country, z, y1, y2)
role <- c(rep('n', 3), 'c', 'c', 'r', 'd', 'd')

mrsobj <- MrSImp(dataframe = train, role = role, B = 10)
mrsobj$imp
#>   Importance Feature
#> 1 0.0000e+00      X1
#> 3 0.0000e+00      X3
#> 5 0.0000e+00 country
#> 2 4.8052e+01      X2
#> 4 2.0000e+12  gender