normalize

0th

Percentile

Normalize the ratings

Provides the generic for normalize/denormalize and a method to normalize/denormalize the ratings in a realRatingMatrix.

Keywords
Manipulation
Usage
normalize(x, ...) "normalize"(x, method="center", row=TRUE)
denormalize(x, ...) "denormalize"(x, method=NULL, row=NULL, factors=NULL)
Arguments
x
a realRatingMatrix.
method
normalization method. Currently "center" or "Z-score".
row
logical; normalize rows (or the columns)?
factors
a list with the factors to be used for denormalizing (elements are "mean" and "sds"). Usually these are not specified and the values stored in x are used.
...
further arguments (currently unused).
Details

Normalization tries to reduce the individual rating bias by row centering the data, i.e., by subtracting from each available rating the mean of the ratings of that user (row). Z-score in addition divides by the standard deviation of the row/column. Normalization can also be done on columns.

Denormalization reverses normalization. It uses the normalization information stored in x unless the user specifies method, row and factors.

Value

A normalized realRatingMatrix.

Aliases
  • normalize
  • denormalize
  • denormalize,realRatingMatrix-method
  • normalize,realRatingMatrix-method
Examples
## create a matrix with ratings
m <- matrix(sample(c(NA,0:5),50, replace=TRUE, prob=c(.5,rep(.5/6,6))), 
nrow=5, ncol=10, dimnames = list(users=paste('u', 1:5, sep=''),
items=paste('i', 1:10, sep='')))

## do normalization
r <- as(m, "realRatingMatrix")
r_n1 <- normalize(r) 
r_n2 <- normalize(r, method="Z-score")

r
r_n1
r_n2

## show normalized data
image(r, main="Raw Data")
image(r_n1, main="Centered")
image(r_n2, main="Z-Score Normalization")
Documentation reproduced from package recommenderlab, version 0.2-1, License: GPL-2

Community examples

Looks like there are no examples yet.