Empirical Intensity of Line Segment Pattern
Computes the average total length of segments per unit area in a spatial pattern of line segments.
## S3 method for class 'psp' intensity(X, ..., weights=NULL)
X |
A line segment pattern (object of class |
weights |
Optional.
Numeric vector of weights attached to the segments of |
... |
Ignored. |
This is a method for the generic function intensity.
It computes the empirical intensity of a line segment pattern
(object of class "psp"),
i.e. the average total segment length per unit area.
If the segment pattern is multitype, the intensities of the different types are computed separately.
Note that the intensity will be computed as the length per area
in units per square unit, based on the unit of length for X,
given by unitname(X). If the unit of length is a strange multiple
of a standard unit, like 5.7 metres, then it can be converted
to the standard unit using rescale. See the Examples.
If weights are given, then the intensity is
computed as the total weight times length per square unit.
The argument weights should be a numeric vector
of weights for each point of X (weights may be negative or
zero).
Alternatively weights can be an expression
which will be evaluated for the dataset to yield a vector of weights.
The expression may involve the Cartesian coordinates x,y of the
points, and the marks of the points, if any. Variable names
permitted in the expression include x0, x1, y0,
y1 for the coordinates of the segment endpoint,
the name marks if X has a single column of marks,
the names of any columns of marks if X has a data frame of
marks, and the names of constants or functions that exist
in the global environment. See the Examples.
A numeric value (giving the intensity) or numeric vector (giving the intensity for each possible type).
Adrian Baddeley Adrian.Baddeley@curtin.edu.au, Rolf Turner r.turner@auckland.ac.nz and Ege Rubak rubak@math.aau.dk.
S <- edges(letterR) intensity(S) intensity(S, weights=runif(nsegments(S))) intensity(S, weights=expression((x0+x1)/2))
Please choose more modern alternatives, such as Google Chrome or Mozilla Firefox.