Replace Categorical Variables with Mode in R

In Data Science project, it is common to replace the missing values of the categorical variables with the mode. Let’s see the following example:

df<-data.frame(id=seq(1,10), ColumnA=c(10,9,8,7,NA,NA,20,15,12,NA), 
           ColumnB=c("A","B","A","A","","B","A","B","","A"),
           ColumnC=c("","BB","CC","BB","BB","CC","AA","BB","","AA"),
           ColumnD=c(NA,20,18,22,18,17,19,NA,17,23)
)

df

Note that the ColumnB and ColumnC are Character columns. Note also that there is no mode function in R. So let’s build it:

getmode <- function(v){
  v=v[nchar(as.character(v))>0]
  uniqv <- unique(v)
  uniqv[which.max(tabulate(match(v, uniqv)))]
}

Now let’s replace all the empty strings of the Character variables with their corresponding column mode. Finally, we should convert the character variables to factors.

df[sapply(df, is.character)] <- lapply(df[sapply(df, is.character)], function(x) ifelse(x=="", getmode(x), x))
df[sapply(df, is.character)] <- lapply(df[sapply(df, is.character)], as.factor)
df

As we can see, we replaced the empty strings with the corresponding mode.