Error msg "x must be numeric"

[Amalie]

Hi can someone please help me with the following error msg - I think it's due to the colonne Fat_protein isn't nummeric and that's why I have tried to add the as.factor(Mouse$Fat_Protein) but i still get the same error.

Mouse <- read_excel('Mouse_diet_intervention.xlsx')
Mouse <- Mouse[c(1:40),]
Mouse$Fat_Protein <- as.factor(Mouse$Fat_Protein)
Mouse_m <- Mouse [,c(5,23:28)]
MousePCA <- prcomp(Mouse_m, center=TRUE, scale=TRUE)

Error msg:

Error in colMeans(x, na.rm = TRUE) : 'x' must be numeric

My data for Mouse_m:

[Amalie]

So I'm about to have a course in R after the summerbreak where we have recieved some tasks we could do before the course starts in order not to be totally lost. So this one it's says "Suggest two ways in which you can change the coding so that the qplot can be made" where I got the code from the task to begin with - so I just added the Mouse$Fat_Protein <- as.factor() because I thought the error showed due to that colonne since it wasn't numeric but it didn't solve the issue

Sorry about my english btw it's not my first language

[nirgrahamuk]

factors are not directly numeric; they are integers underneath yes, but you wont have access to that aspect of them without using as.integer()

[Amalie]

Thanks! I have tried to use as.integer(Mouse$Fat_Protein) but it still don't work Is there something else I could do?

[M_AcostaCH]

For make prcomp() you need all data like numeric or in specific case put the factor variables. But don't put character variables.

Send you a great guide for this:

Principal Component Analysis in R: prcomp vs princomp - Articles - STHDA

[nirgrahamuk]

we cant see your code to judge how you did it. but maybe this example will help you.

df_ <- data.frame(
  a=letters[1:2],
  b=1:2
)

prcomp(df_ )

df_$a <- as.integer(as.factor(df_$a))

prcomp(df_ )

[Amalie]

Thanks I have typed in the following code:

Mouse <- read_excel('Mouse_diet_intervention.xlsx')
Mouse <- Mouse[c(1:40),]
Mouse_m <- Mouse [,c(5,23:28)]
Mouse$Fat_Protein <- as.integer(as.factor(Mouse$Fat_Protein))
MousePCA <- prcomp(Mouse_m, center=TRUE, scale=TRUE)

But I still get the same error:

Error in colMeans(x, na.rm = TRUE) : 'x' must be numeric

Did I type it in wrong?

[M_AcostaCH]

For better help you all the community, put a reproducible example of data.

FAQ: How to do a minimal reproducible example ( reprex ) for beginners

A minimal reproducible example consists of the following items: A minimal dataset, necessary to reproduce the issue The minimal runnable code necessary to reproduce the issue, which can be run on the given dataset, and including the necessary information on the used packages. Let's quickly go over each one of these with examples: Minimal Dataset (Sample Data) You need to provide a data frame that is small enough to be (reasonably) pasted on a post, but big enough to reproduce your issue. Let's say, as an example, that you are working with the iris data frame head(iris) #> Sepal.Length Sepal.Width Petal.Length Petal.Width Species #> 1 5.1 3.5 1.4 0.…

Like this:

dput(Mouse[1:30 , ]

copy and paste the result of this code.

[Amalie]

Thanks where in the code should i inset in?

[M_AcostaCH]

Yes, the result in the console. Copy an paste the result of dput(Mouse[1:30 , ].
Dont put the image, Im put only for explain you.

[nirgrahamuk]

@Amalie

Mouse_m <- Mouse [,c(5,23:28)]
Mouse$Fat_Protein <- as.integer(as.factor(Mouse$Fat_Protein))
MousePCA <- prcomp(Mouse_m, center=TRUE, scale=TRUE)

This shows you adjust Mouse, not Mouse_m to have the integer represntation of fat protein,
therefore it has no effect in the prcomp() that follows

[Amalie]

Oh thanks that worked!!!