If any edge are dropped, the MST are pruned. This generate a two subgraphs. So, it makes a tree graphs and tree dissimilarity values are computed, one for each graph. The dissimilarity is the sum over sqared differences between the observactions in the nodes and mean vector of observations in the graph. The dissimilarity of original graph and the sum of dissimilarity of subgraphs are returned.
prunecost(edges, data, method = c("euclidean", "maximum", "manhattan",
"canberra", "binary", "minkowski", "mahalanobis"),
p = 2, cov, inverted = FALSE)
A vector with the differences between the dissimilarity of all nodes and the dissimilarity sum of all subgraphs obtained by pruning one edge each time.
A matrix with 2 colums with each row is one edge
A data.frame with observations in the nodes.
Character or function to declare distance method.
If method
is character, method must be "mahalanobis" or
"euclidean", "maximum", "manhattan", "canberra", "binary"
or "minkowisk".
If method
is one of "euclidean", "maximum",
"manhattan", "canberra", "binary" or "minkowisk", see
dist
for details,
because this function as used to compute the distance.
If method="mahalanobis"
, the mahalanobis distance
is computed between neighbour areas.
If method
is a function
, this function is
used to compute the distance.
The power of the Minkowski distance.
The covariance matrix used to compute the mahalanobis distance.
logical. If 'TRUE', 'cov' is supposed to contain the inverse of the covariance matrix.
Elias T. Krainski and Renato M. Assuncao
See Also as prunemst
d <- data.frame(a=-2:2, b=runif(5))
e <- matrix(c(1,2, 2,3, 3,4, 4,5), ncol=2, byrow=TRUE)
sum(sweep(d, 2, colMeans(d))^2)
prunecost(e, d)
Run the code above in your browser using DataLab