Resolved...
The following work around accomplishes what I'm trying to do.
library(raster)
t<-stack("ELEV.asc", "AACN.asc", "CNBL.asc")
predict(t, PGMRF, filename = "predicted_output.asc", fun = predict, se.fit =
TRUE)
The coded material types (C, F, G, L, M) appear as numbers (1,2,3,4,5) in
the
Thanks for your reply Alex.
I am applying randomForest as a classification problem.
and the outcome is a parent material class expressed as character (M,F,G,C
etc).
Here is the code I'm using for rf (reduced to 3 variables):
PGMRF<- randomForest(PGM_1 ~ ELEV+AACN+CNBL, data=PGM, importance=TRU
Hi Chuck,
the error message suggests that the function unsuccessfully tries to
write a character string into the output file. Are you applying
randomforest to a classification problem or a regression problem? If
classification, are you predicting probabilities of class membership, or
classes
Hi.
I am using RSAGA multi.local.function to apply random forest to a series of
grids containing 9 topographic derivatives that were calculated in SAGA.
(trying to produce a soil parent material map).
On one series of grids the calculation works fine, and an output ascii file
is produced.
