怎么设置smooth.spline的参数

 smoothing parameter value too small
Calls: predict -> smooth.spline
Execution halted

下面的y绝对值过小时「太接近0时」，出现上方error

Usage

smooth.spline(x, y = NULL, w = NULL, df, spar = NULL, lambda = NULL, cv = FALSE,
              all.knots = FALSE, nknots = .nknots.smspl,
              keep.data = TRUE, df.offset = 0, penalty = 1,
              control.spar = list(), tol = 1e-6 * IQR(x), keep.stuff = FALSE)

Arguments

x

a vector giving the values of the predictor variable, or a list or a two-column matrix specifying x and y.

y

responses. If y is missing or NULL, the responses are assumed to be specified by x, with x the index vector.

w

optional vector of weights of the same length as x; defaults to all 1.<