funGp (version 0.2.2)

plotSims,fgpm-method: Plot for simulations from a funGp model

Description

This method displays the simulated output values delivered by a funGp Gaussian process model.

This method provides two plots for assessing the quality of the output delivered by the model selection algorithm in the fgpm_factory function. The first one is a calibration plot similar to the one offered for '>fgpm objects by the plotLOO function. This plot allows to validate the absolute quality of the selected model. The second one displays the performance statistic of all the models successfully evaluated by the model selection algorithm. This provides a notion of the relative quality of the selected model with respect to the other models that can be made using the same data.

Usage

# S4 method for fgpm
plotSims(model, sims, detail = "full", ...)
# S4 method for Xfgpm
plotX(x.model, calib = TRUE, fitp = TRUE, ...)

Arguments

model

a '>fgpm object for which the plot is to be made.

sims

a list containing the simulated output values. In funGp, this argument is just the data structure delivered by the simulate method.

detail

an optional character string specifying the data elements that should be included in the plot, to be chosen between "light" and "full". A light plot will include only include the simulated values, while a a full plot will also include the predicted mean and confidence bands at the simulation points. This argument will only be used if full simulations (including the mean and confidence bands) are provided, otherwise it will be dropped. See simulate for more details on the generation of light and full simulations.

...

additional arguments affecting the display. Since this method allows to generate two plots from a single function call, the extra arguments for each plot should be included in a list. For the calibration plot, the list should be called calib.gpars. For the plot of the fitness of explored models, the list should be called fitp.gpars. The following typical graphics parameters are valid entries of both lists: xlim, ylim, xlab, ylab, main. The boolean argument legends can also be included in any of the two lists in order to control the display of legends in the corresponding plot.

x.model

an object of class '>Xfgpm containing the output of the model selection algorithm in fgpm_factory.

calib

a boolean indicating whether the calibration plot of the selected model should be included in the display. Default is TRUE.

fitp

a boolean indicating whether scatter plot of the quality of all explored models should be included in the display. Default is TRUE.

Value

None.

None.

References

Betancourt, J., Bachoc, F., Klein, T., and Gamboa, F. (2020), Technical Report: "Ant Colony Based Model Selection for Functional-Input Gaussian Process Regression. Ref. B3D-WP3.2". RISCOPE project. [HAL]

Betancourt, J., Bachoc, F., and Klein, T. (2020), R Package Manual: "Gaussian Process Regression for Scalar and Functional Inputs with funGp - The in-depth tour". RISCOPE project. [HAL]

See Also

* fgpm for the construction of funGp models;

* plotLOO for model diagnostic plots;

* predict for predictions based on a funGp model;

* plotPreds for prediction plots.

* fgpm_factory for structural optimization of funGp models;

* plotEvol for a plot on the evolution of the model selection algorithm in fgpm_factory.

Examples

# NOT RUN {
# plotting light simulations_______________________________________________________________
# building the model
set.seed(100)
n.tr <- 25
sIn <- expand.grid(x1 = seq(0,1,length = sqrt(n.tr)), x2 = seq(0,1,length = sqrt(n.tr)))
fIn <- list(f1 = matrix(runif(n.tr*10), ncol = 10), f2 = matrix(runif(n.tr*22), ncol = 22))
sOut <- fgp_BB3(sIn, fIn, n.tr)
m1 <- fgpm(sIn = sIn, fIn = fIn, sOut = sOut)

# making light simulations
n.sm <- 100
sIn.sm <- as.matrix(expand.grid(x1 = seq(0,1,length = sqrt(n.sm)),
                                x2 = seq(0,1,length = sqrt(n.sm))))
fIn.sm <- list(f1 = matrix(runif(n.sm*10), ncol = 10), matrix(runif(n.sm*22), ncol = 22))
m1.sims <- simulate(m1, nsim = 10, sIn.sm = sIn.sm, fIn.sm = fIn.sm)

# plotting light simulations
plotSims(m1, m1.sims)


# plotting full simulations________________________________________________________________
# building the model
set.seed(100)
n.tr <- 25
sIn <- expand.grid(x1 = seq(0,1,length = sqrt(n.tr)), x2 = seq(0,1,length = sqrt(n.tr)))
fIn <- list(f1 = matrix(runif(n.tr*10), ncol = 10), f2 = matrix(runif(n.tr*22), ncol = 22))
sOut <- fgp_BB3(sIn, fIn, n.tr)
m1 <- fgpm(sIn = sIn, fIn = fIn, sOut = sOut)

# making full simulations
n.sm <- 100
sIn.sm <- as.matrix(expand.grid(x1 = seq(0,1,length = sqrt(n.sm)),
                                x2 = seq(0,1,length = sqrt(n.sm))))
fIn.sm <- list(f1 = matrix(runif(n.sm*10), ncol = 10), matrix(runif(n.sm*22), ncol = 22))
m1.sims <- simulate(m1, nsim = 10, sIn.sm = sIn.sm, fIn.sm = fIn.sm, detail = "full")

# plotting full simulations in full mode
plotSims(m1, m1.sims)

# plotting full simulations in light mode
plotSims(m1, m1.sims, detail = "light")

# generating input and output data
set.seed(100)
n.tr <- 2^5
sIn <- expand.grid(x1 = seq(0,1,length = n.tr^(1/5)), x2 = seq(0,1,length = n.tr^(1/5)),
                   x3 = seq(0,1,length = n.tr^(1/5)), x4 = seq(0,1,length = n.tr^(1/5)),
                   x5 = seq(0,1,length = n.tr^(1/5)))
fIn <- list(f1 = matrix(runif(n.tr*10), ncol = 10), f2 = matrix(runif(n.tr*22), ncol = 22))
sOut <- fgp_BB7(sIn, fIn, n.tr)
# }
# NOT RUN {
# optimizing the model structure with fgpm_factory (~5 seconds)
xm <- fgpm_factory(sIn = sIn, fIn = fIn, sOut = sOut)

# assessing the quality of the model - absolute and w.r.t. the other explored models
plotX(xm)

# customizing some graphical parameters
plotX(xm, calib.gpars = list(xlim = c(800,1000), ylim = c(600,1200)),
          fitp.gpars = list(main = "Relative quality", legends = FALSE))
# }
# NOT RUN {
# }