In this package vignette, we introduce how to use the C++ header-only
library that **splines2** contains with the
**Rcpp** package (Eddelbuettel
2013) for constructing spline basis functions. The introduction
is intended for package developers who would like to use
**splines2** package at C++ level by adding
**splines2** to the `LinkingTo`

field of package
`DESCRIPTION`

file.

Different with the procedure-based functions in the R interface, the
C++ interface follows the commonly-used object-oriented design in C++
for ease of usage and maintenance. The implementations use the
**Armadillo** (Sanderson
2016) library with help of **RcppArmadillo** (Eddelbuettel and Sanderson 2014) and require
C++11. We assume that is enabled for compilation henceforth. We may
include the header file named `splines2Armadillo.h`

to get
the access to all the classes and implementations in the name space
`splines2`

.

```
#include <RcppArmadillo.h>
// include header file from splines2 package
#include <splines2Armadillo.h>
// [[Rcpp::plugins(cpp11)]]
```

To use `Rcpp::sourceCpp()`

, one may need to add
`[[Rcpp::depends()]]`

as follows:

```
// [[Rcpp::depends(RcppArmadillo)]]
// [[Rcpp::depends(splines2)]]
```

For ease of demonstration, we assume the following
*using-directives*:

```
using namespace arma
using namespace splines2
```

The `BernsteinPoly`

class is implemented for the
generalized Bernstein polynomials.

The main non-default constructor is as follows:

```
(const vec& x,
BernsteinPolyconst unsigned int degree,
const vec& boundary_knots = vec());
```

In addition, two explicit constructors are provided for
`BernsteinPoly*`

and `SplineBase*`

, which set
`x`

, `degree`

, and `boundary_knots`

from the objects that the pointers point to.

The main methods are

`basis()`

for basis matrix`derivative()`

for derivatives of basis functions`integral()`

for integrals of basis functions

The specific function signatures are as follows:

```
(const bool complete_basis = true);
mat basis(const unsigned int derivs = 1,
mat derivativeconst bool complete_basis = true);
(const bool complete_basis = true); mat integral
```

In addition, we may *set* and *get* the specifications
through the following *setter* and *getter* functions,
respectively.

```
// setter functions
* set_x(const vec&);
BernsteinPoly* set_x(const double);
BernsteinPoly* set_degree(const unsigned int);
BernsteinPoly* set_order(const unsigned int);
BernsteinPoly* set_internal_knots(const vec&); // placeholder, does nothing
BernsteinPoly* set_boundary_knots(const vec&);
BernsteinPoly
// getter functions
();
vec get_xunsigned int get_degree();
unsigned int get_order();
(); vec get_boundary_knots
```

The *setter* function returns a pointer to the current
object.

A virtual base class named `SplineBase`

is implemented to
support a variety of classes for spline basis functions including

`BSpline`

for B-splines;`MSpline`

for M-splines;`ISpline`

for I-splines;`CSpline`

for C-splines;`NaturalSpline`

for natural cubic splines;`PeriodicMSpline`

for periodic M-splines;`BernsteinPoly`

for Bernstein polynomials.

`BSpline`

, `MSpline`

,
`ISpline`

, and `CSpline`

The `BSpline`

, `MSpline`

, `ISpline`

,
and `CSpline`

classes share the same constructors inherited
from the `SplineBase`

class. There are four constructors in
addition to the default constructor.

The first non-default constructor is invoked when internal knots are
explicitly specified as the second argument. Taking B-splines as an
example, the first non-default constructor of a `BSpline`

object is

```
// 1. specified internal_knots
(const vec& x,
BSplineconst vec& internal_knots,
const unsigned int degree = 3,
const vec& boundary_knots = vec());
```

The second non-default constructor is called when an unsigned integer
is specified as the second argument, which represents the degree of
freedom of the *complete spline basis functions* (different with
`df`

in the R interface) is specified. Then the number of
internal knots is computed as `spline_df - degree - 1`

and
the placement of internal knots uses quantiles of specified
`x`

within boundary.

```
// 2. specified spline degree of freedom (df)
(const vec& x,
BSplineconst unsigned int spline_df,
const unsigned int degree = 3,
const vec& boundary_knots = vec());
```

The third non-default constructor is intended for basis functions with an extended knot sequence, where the multiplicities of the knots can be more than one.

```
// 3. specified degree and (extended) knot sequence
(const vec& x,
BSplineconst unsigned int degree,
const vec& knot_sequence);
```

The fourth non-default constructor is explicit and takes a pointer to
a base class object, which can be useful when we want to create a new
object using the same specification (`x`

,
`degree`

, `internal_knots`

, and
`boundary_knots`

) of an existing object (not necessarily a
`BSpline`

object).

```
// 4. create a new object from a base class pointer
(const SplineBase* pSplineBase); BSpline
```

This constructor also allows us to easily switch between different
types of splines. For example, we create a `BSpline`

object
`bsp_obj`

form an existing `MSpline`

object
`msp_obj`

with the same specification as follows:

`{ &msp_obj }; BSpline bsp_obj `

`NaturalSpline`

The `NaturalSpline`

represents the class for natural cubic
splines. Thus, its constructors do not allow specification of
`degree`

. The first non-default constructor is called when
internal knots are explicitly specified.

```
// 1. specified internal_knots
(const vec& x,
NaturalSplineconst vec& internal_knots,
const vec& boundary_knots = vec());
```

The second non-default constructor is called when an unsigned integer
representing the degree of freedom of the *complete spline basis
functions* (different with `df`

in the R interface) is
specified. Then the number of internal knots is computed as
`spline_df - 2`

and the placement of internal knots uses
quantiles of specified `x`

.

```
// 2. specified spline degree of freedom (df)
(const vec& x,
NaturalSplineconst unsigned int spline_df,
const vec& boundary_knots = vec());
```

The third non-default constructor is explicit and takes a pointer to
a base class object. It can be useful when we want to create a new
object using the same specification (`x`

,
`internal_knots`

, `boundary_knots`

, etc.) of an
existing object.

```
// 3. create a new object from a base class pointer
(const SplineBase* pSplineBase); NaturalSpline
```

`PeriodicMSpline`

The `PeriodicMSpline`

class is for constructing the
periodic M-splines, which provides the same set of non-default
constructors with `BSpline`

except the constructor for
directly specifying the knot sequence.

The main methods are

`basis()`

for spline basis matrix`derivative()`

for derivatives of spline basis`integral()`

for integrals of spline basis (except for the`CSpline`

class)

The specific function signatures are as follows:

```
(const bool complete_basis = true);
mat basis(const unsigned int derivs = 1,
mat derivativeconst bool complete_basis = true);
(const bool complete_basis = true); mat integral
```

Similarly, we may set and get the spline specifications through the
following *setter* and *getter* functions,
respectively.

```
// setter functions
* set_x(const vec&);
SplineBase* set_x(const double);
SplineBase* set_internal_knots(const vec&);
SplineBase* set_boundary_knots(const vec&);
SplineBase* set_knot_sequence(const vec&);
SplineBase* set_degree(const unsigned int);
SplineBase* set_order(const unsigned int);
SplineBase
// getter functions
();
vec get_x();
vec get_internal_knots();
vec get_boundary_knots();
vec get_knot_sequenceunsigned int get_degree();
unsigned int get_order();
unsigned int get_spline_df();
```

The *setter* function returns a pointer to the current object
so that the specification can be chained for convenience. For
example,

```
{ arma::regspace(0, 0.1, 1) }; // 0, 0.1, ..., 1
vec x { x, 5 }; // df = 5 (and degree = 3, by default)
BSpline obj // change degree to 2 and get basis
{ obj.set_degree(2)->basis() }; mat basis_mat
```

The corresponding first derivatives and integrals of the basis functions can be obtained as follows:

```
{ bs.derivative() };
mat derivative_mat { bs.integral() }; mat integral_mat
```

Notice that there is no available `integral()`

method for
`CSpline`

and no meaningful `degree`

related
methods for `NaturalSpline`

.

Eddelbuettel, Dirk. 2013. *Seamless R and
C++ Integration with Rcpp*. Springer.

Eddelbuettel, Dirk, and Conrad Sanderson. 2014.
“RcppArmadillo: Accelerating
R with High-Performance C++ Linear
Algebra.” *Computational Statistics and Data Analysis* 71:
1054–63. http://dx.doi.org/10.1016/j.csda.2013.02.005.

Sanderson, Conrad. 2016. “Armadillo: An
Open Source C++ Linear Algebra Library for Fast Prototyping
and Computationally Intensive Experiments.” *Journal of Open
Source Software* 1: 26.