step_bs creates a specification of a recipe step
that will create new columns that are basis expansions of
variables using B-splines.
Arguments
- recipe
A recipe object. The step will be added to the sequence of operations for this recipe.
- ...
One or more selector functions to choose variables for this step. See
selections()for more details.- role
For model terms created by this step, what analysis role should they be assigned? By default, the new columns created by this step from the original variables will be used as predictors in a model.
- trained
A logical to indicate if the quantities for preprocessing have been estimated.
- deg_free
The degrees of freedom for the spline. As the degrees of freedom for a spline increase, more flexible and complex curves can be generated. When a single degree of freedom is used, the result is a rescaled version of the original data.
- degree
Degree of polynomial spline (integer).
- objects
A list of
splines::bs()objects created once the step has been trained.- options
A list of options for
splines::bs()which should not includex,degree, ordf.- skip
A logical. Should the step be skipped when the recipe is baked by
bake()? While all operations are baked whenprep()is run, some operations may not be able to be conducted on new data (e.g. processing the outcome variable(s)). Care should be taken when usingskip = TRUEas it may affect the computations for subsequent operations.- id
A character string that is unique to this step to identify it.
Value
An updated version of recipe with the new step added to the
sequence of any existing operations.
Details
step_bs can create new features from a single variable
that enable fitting routines to model this variable in a
nonlinear manner. The extent of the possible nonlinearity is
determined by the df, degree, or knot arguments of
splines::bs(). The original variables are removed
from the data and new columns are added. The naming convention
for the new variables is varname_bs_1 and so on.
Tidying
When you tidy() this step, a tibble with column
terms (the columns that will be affected) is returned.
See also
Other individual transformation steps:
step_BoxCox(),
step_YeoJohnson(),
step_harmonic(),
step_hyperbolic(),
step_inverse(),
step_invlogit(),
step_logit(),
step_log(),
step_mutate(),
step_ns(),
step_percentile(),
step_poly(),
step_relu(),
step_sqrt()
Examples
data(biomass, package = "modeldata")
biomass_tr <- biomass[biomass$dataset == "Training", ]
biomass_te <- biomass[biomass$dataset == "Testing", ]
rec <- recipe(
HHV ~ carbon + hydrogen + oxygen + nitrogen + sulfur,
data = biomass_tr
)
with_splines <- rec %>%
step_bs(carbon, hydrogen)
with_splines <- prep(with_splines, training = biomass_tr)
expanded <- bake(with_splines, biomass_te)
expanded
#> # A tibble: 80 × 10
#> oxygen nitrogen sulfur HHV carbon_b…¹ carbo…² carbo…³ hydro…⁴ hydro…⁵
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 47.2 0.3 0.22 18.3 0.437 0.273 0.0568 0.383 0.367
#> 2 48.1 2.85 0.34 17.6 0.444 0.236 0.0417 0.393 0.355
#> 3 49.1 2.4 0.3 17.2 0.444 0.229 0.0394 0.393 0.355
#> 4 37.3 1.8 0.5 18.9 0.437 0.273 0.0571 0.354 0.394
#> 5 42.8 0.2 0 20.5 0.427 0.301 0.0707 0.338 0.406
#> 6 41.7 0.7 0.2 18.5 0.442 0.248 0.0465 0.393 0.355
#> 7 54.1 1.19 0.51 15.1 0.440 0.184 0.0256 0.408 0.335
#> 8 33.8 0.95 0.2 16.2 0.444 0.222 0.0369 0.431 0.290
#> 9 31.1 0.14 4.9 11.1 0.359 0.0771 0.00552 0.438 0.268
#> 10 23.7 4.63 1.05 10.8 0.338 0.0643 0.00408 0.444 0.214
#> # … with 70 more rows, 1 more variable: hydrogen_bs_3 <dbl>, and
#> # abbreviated variable names ¹carbon_bs_1, ²carbon_bs_2, ³carbon_bs_3,
#> # ⁴hydrogen_bs_1, ⁵hydrogen_bs_2