sampling_sequence: Chain sampling algorithms together.

In RomeroBarata/bimba: Sampling Algorithms for Two-Class Imbalanced Data Sets

Description

sampling_sequence applies a sequence of sampling algorithms to an input data set.

Usage

sampling_sequence(data, algorithms, parameters = NULL, classes = NULL)

Arguments

data	A data frame containing the predictors and the outcome. Restrictions about the input data depend on the individual sampling algorithms being used. In any case, the outcome must be both a binary valued factor and the last column of data.
algorithms	A vector containing the names of the sampling algorithms to be chained either as strings or the functions' objects themselves.
parameters	A list of lists where each individual list contains the parameters to be used by the respective sampling algorithm in algorithms.
classes	A named vector identifying the majority and the minority classes. The names must be "Majority" and "Minority". This argument is only useful if the function is called inside another sampling function.

Details

sampling_sequence has two main arguments: algorithms and parameters. algorithms is a vector containing the names of the sampling functions to be applied in sequence (either as strings or the functions' objects themselves). parameters is a list of lists, where each individual list contains the parameters to be used by the respective sampling function in algorithms.

Value

A data frame containing the result of a chain of sampling algorithms applied to the input data set.

RomeroBarata/bimba documentation built on May 17, 2019, 8:03 a.m.