Why caret preProcess impute method scales data automatically

Question

I want to deal with NA values in my data but do not want to scale and center it so I simply do this:

preProcess(data, method = "knnImpute", k=10)

or this:

preProcess(data, method = "bagImpute")

However it automatically scales and centers data which seems intentional (states that in documentation). How do I avoid that and simply do imputation?

Answer 1

You can't avoid scaling and centering your data when using method = "knnImpute", presumably because it does not usually make sense to use knn without doing so.

However, method = "bagImpute" or method = "medianImpute" will not scale and center the data unless you ask it to. For example:

mtcars[1, 1] <- NA
pc <- preProcess(data, method = "bagImpute")
head(predict(pc, mtcars))

                   mpg cyl disp  hp drat    wt  qsec vs am gear carb
Mazda RX4         21.0   6  160 110 3.90 2.620 16.46  0  1    4    4
Mazda RX4 Wag     21.0   6  160 110 3.90 2.875 17.02  0  1    4    4
Datsun 710        22.8   4  108  93 3.85 2.320 18.61  1  1    4    1
Hornet 4 Drive    21.4   6  258 110 3.08 3.215 19.44  1  0    3    1
Hornet Sportabout 18.7   8  360 175 3.15 3.440 17.02  0  0    3    2
Valiant           18.1   6  225 105 2.76 3.460 20.22  1  0    3    1