nm(x, ...)
"nm"(x, grouping, gamma = 0, ...)
"nm"(x, ...)
"nm"(x, grouping, ..., subset, na.action = na.fail)
"nm"(formula, data = NULL, ..., subset, na.action = na.fail)
formula
is not given)formula
is not given)groups ~ x1 + x2 + ...
.
That is, the response is the grouping factor and the right hand side specifies the (non-factor) discriminatorsformula
are preferentially to be takengamma=0
the posterior is 1 for the
nearest class (mean) and 0 else.NA
s are
found. The default action is for the procedure to fail. An
alternative is na.omit
, which leads to rejection of cases with
missing values on any required variable. (Note: If given, this
argument must be named.) sknn
functionlearn
)).
nm
is calling sknn
with the class means as observations.
If gamma>0
a gaussian like density is used to weight the distance to the class means
weight=exp(-gamma*distance)
. This is similar to an rbf kernel.
If the distances are large it may be useful to scale
the data first.
sknn
, rda
, knn
data(B3)
x <- nm(PHASEN ~ ., data = B3)
x$learn
x <- nm(PHASEN ~ ., data = B3, gamma = 0.1)
predict(x)$post
Run the code above in your browser using DataLab