On Nov 4, 2008, at 8:02 AM, Luca Mortarini wrote:
I am dealing with a 2d vector field on a
regular grid. The field has sparse NA values
(t near the domain borders and not isolated),
which I am trying to substitute with
interpolated values of the nearest point.
What I am looking for is to replace the
values with a weighted mean, where the
weights are function of the distance from the
regular values.
I wonder if R as an implemented function for this I have looked the
zoo,
the akima and the fileds packages but I have not found it.
Thanks in advance,
Luca
I have not figured out what you mean by "substitut[ing] with
interpolated values of the nearest point". Would have seemed that
interpolation would require at a minimum two interior points. If these
are "not isolated" and at or near borders, it would also appear that
extrapolation might be a more appropriate term.
Quibbles aside .... Have you looked at the locfit package? Regarding
the vector-valued aspect of this field, perhaps you could approach it
by analyzing the projections on single dimensions at a time.
--
David Winsemius
Heritage Labs
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
