Replace mean or mode for missing values in R

Question

I have a large database made up of mixed data types (numeric, character, factor, ordinal factor) with missing values, and I am trying to create a for loop to substitute the missing values using either the mean of the respective column if numerical or the mode if character/factor.

This is what I have until now:

#fake array:
age<- c(5,8,10,12,NA)
a <- factor(c("aa", "bb", NA, "cc", "cc"))
b <- c("banana", "apple", "pear", "grape", NA)
df_test <- data.frame(age=age, a=a, b=b)
df_test$b <- as.character(df_test$b)

for (var in 1:ncol(df_test)) {
    if (class(df_test[,var])=="numeric") {
        df_test[is.na(df_test[,var]) <- mean(df_test[,var], na.rm = TRUE)
} else if (class(df_test[,var]=="character") {
        Mode(df_test$var[is.na(df_test$var)], na.rm = TRUE)
} 
}

Where 'Mode' is the function:

Mode <- function (x, na.rm) {
    xtab <- table(x)
    xmode <- names(which(xtab == max(xtab)))
    if (length(xmode) > 1)
        xmode <- ">1 mode"
    return(xmode)
}

It seems as it is just ignoring the statements though, without giving any error… I have also tried to work the first part out with indexes:

## create an index of missing values
index <- which(is.na(df_test)[,1], arr.ind = TRUE)
## calculate the row means and "duplicate" them to assign to appropriate cells
df_test[index] <- colMeans(df_test, na.rm = TRUE) [index["column",]]

But I get this error: "Error in colMeans(df_test, na.rm = TRUE) : 'x' must be numeric"

Does anybody have any idea how to solve this?

Thank you very much for all the great help! -f

This code has several syntax errors rendering it un-runnable. — joran, Oct 11 '11 at 21:53

score 6 · Accepted Answer · answered Oct 11 '11 at 23:25

If you simply remove the obvious bugs then it works as intended:

Mode <- function (x, na.rm) {
    xtab <- table(x)
    xmode <- names(which(xtab == max(xtab)))
    if (length(xmode) > 1) xmode <- ">1 mode"
    return(xmode)
}

# fake array:
age <- c(5, 8, 10, 12, NA)
a <- factor(c("aa", "bb", NA, "cc", "cc"))
b <- c("banana", "apple", "pear", "grape", NA)
df_test <- data.frame(age=age, a=a, b=b)
df_test$b <- as.character(df_test$b)

print(df_test)

#   age    a      b
# 1   5   aa banana
# 2   8   bb  apple
# 3  10 <NA>   pear
# 4  12   cc  grape
# 5  NA   cc   <NA>

for (var in 1:ncol(df_test)) {
    if (class(df_test[,var])=="numeric") {
        df_test[is.na(df_test[,var]),var] <- mean(df_test[,var], na.rm = TRUE)
    } else if (class(df_test[,var]) %in% c("character", "factor")) {
        df_test[is.na(df_test[,var]),var] <- Mode(df_test[,var], na.rm = TRUE)
    }
}

print(df_test)

#     age  a       b
# 1  5.00 aa  banana
# 2  8.00 bb   apple
# 3 10.00 cc    pear
# 4 12.00 cc   grape
# 5  8.75 cc >1 mode

I recommend that you use an editor with syntax highlighting and bracket matching, which would make it easier to find these sorts of syntax errors.

Pete, Thank you very much!! I tried re-writing based on what you suggested using 'gedit', and it is much better indeed! I was going blind trying to follow the brackets…Also thank you for the corrections, there were loads of errors…lots to learn still. THANK YOU! — user971102, Oct 12 '11 at 09:08
Can you tell me when to use median , mean or mode for replacing NA's in dataSet? — Dashang G. Makwana, Aug 21 '18 at 16:12

score 0 · Answer 2 · answered Apr 18 '20 at 15:00

First, you need to write the mode function taking into consideration the missing values of the Categorical data, which are of length<1.
The mode function:

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

Then you can iterate of columns and if the column is numeric to fill the missing values with the mean otherwise with the mode.

The loop statement below:

for (cols in colnames(df)) {
  if (cols %in% names(df[,sapply(df, is.numeric)])) {
    df<-df%>%mutate(!!cols := replace(!!rlang::sym(cols), is.na(!!rlang::sym(cols)), mean(!!rlang::sym(cols), na.rm=TRUE)))

  }
  else {

    df<-df%>%mutate(!!cols := replace(!!rlang::sym(cols), !!rlang::sym(cols)=="", getmode(!!rlang::sym(cols))))

  }
}

Let's provide an example:

library(tidyverse)

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

df

The initial df with the missing values:

# A tibble: 10 x 5
      id ColumnA ColumnB ColumnC ColumnD
   <int>   <dbl> <fct>   <fct>     <dbl>
 1     1      10 "A"     ""           NA
 2     2       9 "B"     "BB"         20
 3     3       8 "A"     "CC"         18
 4     4       7 "A"     "BB"         22
 5     5      NA ""      "BB"         18
 6     6      NA "B"     "CC"         17
 7     7      20 "A"     "AA"         19
 8     8      15 "B"     "BB"         NA
 9     9      12 ""      ""           17
10    10      NA "A"     "AA"         23

By running the for loop above, we get:

# A tibble: 10 x 5
      id ColumnA ColumnB ColumnC ColumnD
   <dbl>   <dbl> <fct>   <fct>     <dbl>
 1     1    10   A       BB         19.2
 2     2     9   B       BB         20  
 3     3     8   A       CC         18  
 4     4     7   A       BB         22  
 5     5    11.6 A       BB         18  
 6     6    11.6 B       CC         17  
 7     7    20   A       AA         19  
 8     8    15   B       BB         19.2
 9     9    12   A       BB         17  
10    10    11.6 A       AA         23

As we can see, the missing values have been imputed. You can see an example here

Replace mean or mode for missing values in R

2 Answers2

Linked