Renaming levels

library(caret)

## Loading required package: lattice

## Loading required package: ggplot2

data("iris")
summary(iris)

##   Sepal.Length    Sepal.Width     Petal.Length    Petal.Width   
##  Min.   :4.300   Min.   :2.000   Min.   :1.000   Min.   :0.100  
##  1st Qu.:5.100   1st Qu.:2.800   1st Qu.:1.600   1st Qu.:0.300  
##  Median :5.800   Median :3.000   Median :4.350   Median :1.300  
##  Mean   :5.843   Mean   :3.057   Mean   :3.758   Mean   :1.199  
##  3rd Qu.:6.400   3rd Qu.:3.300   3rd Qu.:5.100   3rd Qu.:1.800  
##  Max.   :7.900   Max.   :4.400   Max.   :6.900   Max.   :2.500  
##        Species  
##  setosa    :50  
##  versicolor:50  
##  virginica :50  
##                 
##                 
## 

head(iris,10)

##    Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1           5.1         3.5          1.4         0.2  setosa
## 2           4.9         3.0          1.4         0.2  setosa
## 3           4.7         3.2          1.3         0.2  setosa
## 4           4.6         3.1          1.5         0.2  setosa
## 5           5.0         3.6          1.4         0.2  setosa
## 6           5.4         3.9          1.7         0.4  setosa
## 7           4.6         3.4          1.4         0.3  setosa
## 8           5.0         3.4          1.5         0.2  setosa
## 9           4.4         2.9          1.4         0.2  setosa
## 10          4.9         3.1          1.5         0.1  setosa

factor() function for nominal data

using factor function to recode values of variable Species.

attach(iris)
iris$Species <- factor(iris$Species,
levels = c("setosa","versicolor","virginica"),
labels = c(1,2,3)) 
levels(iris$Species)

## [1] "1" "2" "3"

Recoding a continuous variable

mean_val<-mean(Sepal.Width)
mean_val

## [1] 3.057333

iris$category[iris$Sepal.Width< mean_val] <- "low"
iris$category[iris$Sepal.Width>=mean_val] <- "high"
# Convert the column to a factor
iris$category <- factor(iris$category)
levels(iris$category)

## [1] "high" "low"

the ordered() function for ordinal data

iris$category <- ordered(iris$category,
levels = c("Low", "High"),
labels =c(1,2)) 
levels(iris$category)

## [1] "1" "2"

using match()

oldvalues <- c(1,2)
newvalues <- factor(c("v1","v2"))  #converting to factor

iris$category <- newvalues[ match(iris$category, oldvalues) ]
levels(iris$category)

## [1] "v1" "v2"

Recoding a categorical variable

The easiest way is to use revalue() or mapvalues() from the plyr package

library(plyr)
iris$Species <- revalue(iris$Species, c("setosa"="1", "versicolor"="2", "virginica"="3"))

## The following `from` values were not present in `x`: setosa, versicolor, virginica

iris$Species <- mapvalues(iris$Species, from = c("setosa","versicolor","virginica"), to = c("1", "2","3"))

## The following `from` values were not present in `x`: setosa, versicolor, virginica

levels(iris$Species)

## [1] "1" "2" "3"