In AnderEhu/sme:

library(SME)
library(knitr)

df <- data.frame("V1" = 1:3, "V2" = 3:5, "V3" = 5:7)
v <- c(1, 3, 5)
m <- matrix(c(1,2,3,3,4,5,5,6,7), ncol = 3, byrow = FALSE)

normalize

The goal of normalization is to transform features to be on a similar scale, implemented method is max-min normalization:

$x_{normalize} = \frac{x - min(x)}{max(x)-min(x)}$

Currently implemented for numeric vectors, numeric matrices and data.frame normalization.

Usage

normalize(x, margin = 1L)

Arguments

• x numeric, matrix or dataframe input vector.
• sep Field separator. Default ;
• margin 1 - normalize by rows and 2 - normalize by columns. Default is 1.

Value

• A normalized numeric or data.frame.

Examples

s1 <- normalize(df, margin = 1L)
kable(s1)

s2 <- normalize(df, margin = 2L)
kable(s2)

s3 <- normalize(m, margin = 1L)
kable(s3)

s4 <- normalize(m, margin = 2L)
kable(s4)

s5 <- normalize(v)
kable(s5)

standardize

Standardization rescales data to have a mean (μ) of 0 and standard deviation (σ) of 1 (unit variance).

$x_{standardize} = \frac{x-mean(x)}{\sigma (x)}$

Currently implemented for numeric vectors, numeric matrices and data.frame standardization.

Usage

standardize(x, margin = 1L)

Arguments

• x numeric, matrix or dataframe input vector.
• margin 1 - standardize by rows and 2 - standardize by columns. Default is 1

Value

A standardize numeric or data.frame.

Examples

s1 <- standardize(df, margin = 1L)
kable(s1)

s2 <- standardize(df, margin = 2L)
kable(s2)

s3 <- standardize(m, margin = 1L)
kable(s3)

s4 <- standardize(m, margin = 2L)
kable(s4)

s5 <- standardize(v)
kable(s5)

AnderEhu/sme documentation built on Jan. 31, 2022, 12:01 a.m.