Combines several function tables (objects of class "fv")
into a single function table, merging columns that are identical
and relabelling columns that are different.
# S3 method for fv
collapse(object, ..., same = NULL, different = NULL)# S3 method for anylist
collapse(object, ..., same = NULL, different = NULL)
Object of class "fv".
An object of class "fv", or a list of such objects.
Additional objects of class "fv".
Character string or character vector specifying a column or columns
of function values that are identical in different "fv"
objects. These columns will be included only once in the result.
Character string or character vector specifying a column or columns
of function values, that are different in different "fv" objects.
Each of these columns of data will be included, with
labels that distinguish them from each other.
Adrian Baddeley Adrian.Baddeley@curtin.edu.au and Rolf Turner r.turner@auckland.ac.nz
This is a method for the generic function
collapse.
It combines the data in several function tables
(objects of class "fv", see fv.object)
to make a single function table.
It is essentially a smart wrapper for
cbind.fv.
A typical application is to calculate the same summary statistic
(such as the \(K\) function) for different point patterns,
and then to use collapse.fv to combine the results into a
single object that can easily be plotted. See the Examples.
The arguments object and ... should be function tables
(objects of class "fv", see fv.object)
that are compatible in the sense that they
have the same values of the function argument.
(This can be ensured by applying harmonise.fv to them.)
The argument same identifies any columns that are present
in some or all of the function tables, and
which are known to contain exactly the same values in each table
that includes them. This column or columns will be
included only once in the result.
The argument different identifies any columns that are present
in some or all of the function tables, and which may contain
different numerical values in different tables.
Each of these columns will be included, with labels
to distinguish them.
Columns that are not named in same or different will not
be included.
The function argument is always included and does not need to be specified.
The arguments same and different can be NULL,
or they can be character vectors containing the names
of columns of object. The argument different can be
one of the abbreviations recognised by fvnames.
fv.object,
cbind.fv
# generate simulated data
X <- replicate(3, rpoispp(100), simplify=FALSE)
names(X) <- paste("Simulation", 1:3)
# compute K function estimates
Klist <- anylapply(X, Kest)
# collapse
K <- collapse(Klist, same="theo", different="iso")
K
Run the code above in your browser using DataLab