n_dup_max: The function to calculate the maximum round each sampling is...

In smotefamily: A Collection of Oversampling Techniques for Class Imbalance Problem Based on SMOTE

The function to calculate the maximum round each sampling is repeated

Description

The function to calculate the maximum round each sampling is repeated, if dup_size is given as 0 then, it calculates the maximum round the number of positive instances to be duplicated to nearly match the number of negative instances

Usage

n_dup_max(size_input, size_P, size_N, dup_size = 0)

Arguments

size_input	The size of overall dataset
size_P	The number of positive instances
size_N	The number of negative instances
dup_size	A number or vector of the number of times to be duplicated. The default is zero which means duplicating until nearly balanced.

Value

If dup_size is zero or contains zero, the number of rounds to duplicate positive to nearly equal to the number of negative instances If dup_size is not zero or contains no zero, the maximum value in dup_size

Author(s)

Wacharasak Siriseriwan <[e-mail]>

Examples

	data_example = sample_generator(10000,ratio = 0.80)
	P = data_example[data_example[,3]=="p",-3]
	N = data_example[data_example[,3]=="n",-3]
	D = rbind(P,N)
	max_round =n_dup_max(nrow(D),nrow(P),nrow(N),dup_size= 0)

smotefamily documentation built on May 29, 2024, 7:54 a.m.