Fill missing value with mean of another variable based on categories in R

Question

I want to replace NA values in val2 in each row with the mean of val corresponding to that ID column. Any easy (tidyverse) way to do this?

Also, I want to know how to replace it by mean(na.rm=TRUE) of val2 values itself by categories (For ex: for row 6 & 9 val2 will be replace by 4, mean(na.rm=TRUE) of val2 (for ID==c))

For the dataframe in this image :

R code:

df <- data.frame(ID=c("a","b","c","a","b","c","a","b","c"),
                 val=c(seq(1:9)), val2=c(1,2,4,NA,5,NA,7,NA,NA))

This is called **"target mean imputation"**. – smci Mar 10 '19 at 02:28 — smci, Mar 10 '19 at 02:28

score 1 · Accepted Answer · answered Mar 09 '19 at 05:52

1

Found the answer myself, incase any answer suggestions which is better than this then please share

df %>% 
group_by(ID) %>% 
mutate(val2 = ifelse(is.na (val2), mean(val), val2))

For Point

df %>% 
group_by(ID) %>% 
mutate(val2 = ifelse(is.na(val2), mean(val2,na.rm=TRUE), val2))

answered Mar 09 '19 at 05:52

Vaibhav Singh

1,159
1
10
25

@NelsonGon I have mentioned the R dataframe code in the question, not sure what else is required ? – Vaibhav Singh Mar 09 '19 at 06:02

Fill missing value with mean of another variable based on categories in R

1 Answers1