Return data derived from the data. For each type of stype vector, a reasonable set of default summary statistics will be provided based on the data type that is provided as an input. For example, if the data is continuous then statistics like the mean, variance, and various quantiles will be provided, whereas for a nominal variable the counts of the various levels are provided (among other information). Custom summary statistics can be appended to the base statistics by providing a list of additional functions as an input.
describe(x, g = NULL, w = NULL, .descriptors, ...)
# S4 method for describable,maybeGroup,maybeWeight,maybeDescriptor
describe(x, g = NULL, w = NULL, .descriptors, ...)
# S4 method for simpleStype,maybeGroup,maybeWeight,maybeDescriptor
describe(x, g = NULL, w = NULL, .descriptors, ...)
# S4 method for tbl_df,missing,missing,maybeDescriptor
describe(x, g = NULL, w = NULL, .descriptors, ...)
# S4 method for v_rcensored,maybeGroup,maybeWeight,maybeDescriptor
describe(x, g = NULL, w = NULL, .descriptors, ...)a vector a values
a vector a groupings (optional)
a vector of weights (optional)
an optional list of functions. Each function should have
a signature of the form function(v, ...), and where v is expected to be
of the result of calling as_canonical(x) on the x input to describe,
and ... is expected to be the unchanged value of the input to ... in
describe. If the input list is named then elements in the return object
corresponding to the result of evaluating the supplied functions will have
the corresponding names.
additional arguments passed on to the functions in the list
provided by .descriptors.