This is essentially a wrapper for the 'split' function,
- the important difference being that variables to order by
can be given by a model formula.
Usage
splitBy(formula, data = parent.frame(), drop=TRUE, return.matrix=FALSE)
## S3 method for class 'splitByData':
print(x, ...)
Arguments
formula
The right hand side of a formula
data
A data frame
drop
Logical indicating if levels that do not occur should be
dropped
return.matrix
Should the returned list consist of dataframs or
matrices, see 'details' below
x
A splitByData object (basically a list).
...
Additional arguments, currently not used.
Value
A list of dataframes of matrices
Details
The funcion transform the dataframe 'data' into a numerical matrix
(using the 'asNumericMatrix' function from the Hmisc package) and
makes the splitting operation on this. If return.matrix is TRUE, then
these matrices are returned, otherwise the matrices are turned into
dataframes and then these are returned.