risk.partition.ITR: Determines optimal partition.

In kdoub5ha/rcITR: Risk Controlled ITR Discovery

Description

Determines optimal partition for an input node in an rcDT model.

Usage

risk.partition.ITR(dat, split.var, test = NULL, risk.threshold = NA,
  min.ndsz = 20, n0 = 5, lambda = 0, name = "0", ctg = ctg,
  max.depth = 15, mtry = length(split.var), dat.rest = NULL,
  max.score = NULL, AIPWE = AIPWE, use.other.nodes = TRUE,
  extremeRandomized = FALSE)

Arguments

dat	data.frame. Data used to identify split.
split.var	numeric vector. Columns of spliting variables.
test	data.frame of testing observations. Should be formatted the same as 'data'.
risk.threshold	numeric. Desired level of risk control.
min.ndsz	numeric specifying minimum number of observations required to call a node terminal. Defaults to 20.
n0	numeric specifying minimum number of treatment/control observations needed in a split to declare a node terminal. Defaults to 5.
lambda	numeric. Penalty parameter for risk scores. Defaults to 0, i.e. no constraint.
name	char. Name of internal node, used for ordering splits.
ctg	numeric vector corresponding to the categorical input columns. Defaults to NULL. Not available yet.
max.depth	numeric specifying maximum depth of the tree. Defaults to 15 levels.
mtry	numeric specifying the number of randomly selected splitting variables to be included. Defaults to number of splitting variables.
dat.rest	dataframe. Data outside current splitting node.
max.score	numeric. Current score for the tree.
AIPWE	logical. Should AIPWE (TRUE) or IPWE (FALSE) be used. Not available yet.
use.other.nodes	logical. Should global estimator of objective function be used. Defaults to TRUE.
extremeRandomized	logical. Experimental for randomly selecting cutpoints in a random forest model. Defaults to FALSE

Value

summary of the best split for a given data frame.

kdoub5ha/rcITR documentation built on Aug. 5, 2020, 9:05 p.m.