CODEWITHSUNDEEP
r
Yoshi Jhoncon
Yoshi Jhoncon

Reputation: 11

Removing a N.A value in a data frame

i am a begginer in R, im working with a csv archive named rere.csv so trying to get the mean of quality column with this code:

x<-read.csv("rere.csv", header = TRUE, sep = ";")

mean(x$quality)

But i get this:

Warning message: In mean.default(x$quality) : argument is not numeric or logical: returning NA

quality
5
6
2
2
4
9
41
1
5
N.A
2
23
2
9
5
62
2

Upvotes: 1

Views: 66

Answers (2)

Gregor Thomas
Gregor Thomas

Reputation: 145965

It looks like your data has N.A entries for missing values. By default, R expects NA, but you can tell read.csv that N.A is missing data

x <- read.csv("rere.csv", header = TRUE, sep = ";", na.strings = "N.A")

This will allow R to read the column in as a numeric with missing values rather than a factor (categorical) variable. To get a mean of the non-missing values only, you'll have to tell mean to leave out the NA's.

mean(x$quality, na.rm = TRUE)

Upvotes: 1

talat
talat

Reputation: 70296

Try this:

x<-read.csv("rere.csv", header = TRUE, sep = ";", na.strings = "N.A")

mean(x$quality, na.rm = TRUE)

You can read the help page ?read.csv for more info on the arguments, including na.strings.

Upvotes: 3

Related Questions