splitBy
builds a training set and validation set by placing
all samples that have the include
annotation in the specified
colBy
column in the training set. The remaining samples get
placed in the validation set. This split
is not random.
splitBy(object, colBy, include)
An ExprsArray
object to split.
A character string. Specifies the column used to split the data.
A character vector. Specifies which annotations in colBy
to include in the training set.
Returns a list of two ExprsArray
objects.