PartitionSample: Partition Sample

In citronmeliss/predictionpackr: Predictionpackr

Description

Partitions the sample using stratified random sampling of the outcome of interest. Attempts to maintain class distribution as observed in the study sample. Accepted number of partitions are 2 or 3. If n.partitions is 3, 1 - train.size) / 2 is partitioned into both the validation and test sets.

Usage

PartitionSample(study.sample, outcome.variable.name = "composite",
  n.partitions = 2, train.size = 0.6)

Arguments

study.sample	Data frame. The study sample. No default
outcome.variable.name	Character vector of length 1. The name of the outcome variable of interest. Defaults to "s30d"
n.partitions	Numeric vector of length 1. The number of partitions to create. Either 2 of 3. If Defaults to 2.
train.size	Numeric vector of length 1. The proportion of the sample that goes into training set. Defaults to 0.6

citronmeliss/predictionpackr documentation built on Feb. 10, 2020, 12:19 a.m.