step_spline_b — step_spline

generates basis splines.

Usage

step_spline_b(
  .rec,
  terms,
  df = 0L,
  internal_knots = NULL,
  boundary_knots = NULL,
  intercept = FALSE,
  periodic = FALSE,
  degree = 3L,
  role = "predictor",
  ...
)

Arguments

.rec: the R6 recipe object.
terms: the unquoted names of the variables to use or a selector function. terms replaces the `...` of the recipes package but requires variables to be included within `c()`. For example to include variables x and y you would write `c(x,y)` in the hydrorecipes package.
df: Degree of freedom that equals to the column number of the returned matrix. One can specify df rather than knots, then the function chooses df - degree - as.integer(intercept) internal knots at suitable quantiles of x ignoring missing values and those x outside of the boundary. For periodic splines, df - as.integer(intercept) internal knots will be chosen at suitable quantiles of x relative to the beginning of the cyclic intervals they belong to (see Examples) and the number of internal knots must be greater or equal to the specified degree - 1. If internal knots are specified via knots, the specified df will be ignored.
internal_knots: equivalent to knots from `splines2::bSplines`
boundary_knots: equivalent to Boundary.knots from `splines2::bSplines`
intercept: If TRUE, the complete basis matrix will be returned. Otherwise, the first basis will be excluded from the output.
periodic: A logical value. If TRUE, the periodic splines will be returned. The default value is FALSE.
degree: A nonnegative integer specifying the degree of the piecewise polynomial. The default value is 3 for cubic splines. Zero degree is allowed for piecewise constant basis functions.
role: character - the name of the role
...: Optional arguments that are not used.

Value

an updated recipe

Examples

formula <- as.formula(x~y+z)
rows <- 1e5

dat <- data.frame(x = rnorm(rows),
                  y = 1:rows,
                  z = cumsum(rnorm(rows)))
ik <- collapse::fquantile(dat$x, probs = seq(0, 1, 0.1))
bk <- ik[c(1, length(ik))]
ik <- ik[-c(1, length(ik))]

frec = recipe(formula = formula, data = dat) |>
  step_spline_b(x, df = 11L, intercept = FALSE)  |>
 plate("tbl")