gbm.step error: Error: Must subset columns with a valid subscript vector

Question

I am trying to do a boosted regression tree in R using gbm.step. I have 470 observations and I have 20 predictor variables. The full error I get is Error: Must subset columns with a valid subscript vector. i Logical subscripts must match the size of the indexed input. x Input has size 1 but subscript model.mask has size 470.

I try to run the following code:

parrotfish.tc5.lr01 <- gbm.step(data=fd, 
gbm.x = c(2:22),
gbm.y = 1,
family = "gaussian",
tree.complexity = 5,
learning.rate = 0.01,
bag.fraction = 0.5,
ZI= FALSE)

Answer 1

A sample dataframe would have helped a lot. With given code, you are passing a combine list of 1:22 which is a value list into the x for gbm. Change it to 2:22 which is the index of the input data frame. Try this

parrotfish.tc5.lr01 <- gbm.step(data=fd, 
gbm.x = c(2:22),
gbm.y = 1,
family = "gaussian",
tree.complexity = 5,
learning.rate = 0.01,
bag.fraction = 0.5,
ZI= FALSE)

Answer 2

I figure out my problem. The data (fd in my code) was in a tibble when it needed to be in a dataframe.