Predicts simulator output at new inputs from the smoothed coefficients
written by BS_bigdata_R(), streaming one block of data at a time. For
each block it computes the same mean as FFBS_predict_exact():
\(F_{new}\hat\Theta + J^\top V^{-1}(Y - F\hat\Theta)\), with the
exponential input kernel. Every block must contain all training runs
(bnrow = fnrow in FF_bigdata_R()), as in emulator_learn().
Usage
FFBS_predict_bigdata_R(
Y_ls,
F_ls,
F_new_ls,
input,
input_new,
bs_files,
nT,
fnrow,
fncol,
bncol,
phi_para,
gp_sigma2 = 1.1,
gp_tau2 = 1e-04,
path_out,
verbose = FALSE
)Arguments
- Y_ls, F_ls
The response and design file paths given to
FF_bigdata_R().- F_new_ls
Design file path(s) for the new inputs, laid out like
F_ls: one row per new input,fncollag-1 columns and, for AR(2) designs,fncollag-2 columns after them. One path or one per time step.- input
Matrix of training inputs, one row per run (
fnrowrows).- input_new
Matrix (or vector, for one input) of new inputs.
- bs_files
The list returned by
BS_bigdata_R().- nT, fnrow, fncol, bncol
As given to
FF_bigdata_R().- phi_para, gp_sigma2, gp_tau2
Range, amplitude and nugget of the exponential input kernel, as in
FFBS_predict_exact().- path_out
Directory where the prediction files are written.
- verbose
Logical. If
TRUE, reports progress.
Value
A character vector with one CSV path per time step; each file holds the predicted means, one row per new input and one column per site.
Examples
set.seed(1)
dir <- file.path(tempdir(), "pred_big")
dir.create(dir, showWarnings = FALSE)
csv <- function(x, name) {
path <- file.path(dir, name)
utils::write.csv(x, path, row.names = FALSE)
path
}
# 5 training runs and 2 new inputs; 4 sites in two blocks; 3 times
input <- matrix(runif(10), 5, 2)
input_new <- matrix(runif(4), 2, 2)
Y <- lapply(1:3, function(t) matrix(rnorm(20, t), 5, 4))
F <- c(list(matrix(1, 5, 4)), Y[1:2])
V <- 1.1 * exp(-2 * as.matrix(dist(input))) + diag(1e-4, 5)
ff <- FF_bigdata_R(Y_ls = mapply(csv, Y, paste0("Y", 1:3, ".csv")),
F_ls = mapply(csv, F, paste0("F", 1:3, ".csv")),
G_ls = csv(diag(2), "G.csv"), W_ls = csv(diag(2), "W.csv"),
V_ls = csv(V, "V.csv"), m0 = matrix(0, 2, 2), M0 = diag(2), n0 = 4,
D0 = diag(2), nT = 3, fnrow = 5, fncol = 4, bnrow = 5, bncol = 2,
path_out = dir)
bs <- BS_bigdata_R(ff, file.path(dir, "G.csv"), nT = 3, fnrow = 5,
fncol = 4, bnrow = 5, bncol = 2, path_out = dir)
# Designs for the new inputs, e.g. built from their own lagged outputs
F_new <- c(list(matrix(1, 2, 4)), lapply(1:2, function(t) matrix(t, 2, 4)))
pred <- FFBS_predict_bigdata_R(file.path(dir, paste0("Y", 1:3, ".csv")),
file.path(dir, paste0("F", 1:3, ".csv")),
mapply(csv, F_new, paste0("Fnew", 1:3, ".csv")), input, input_new, bs,
nT = 3, fnrow = 5, fncol = 4, bncol = 2, phi_para = 2, path_out = dir)
utils::read.csv(pred[3]) # predicted means at time 3
#> V1 V2 V3 V4
#> 1 3.992888 4.078902 2.134635 2.556459
#> 2 3.393615 3.673938 2.652602 1.888386
unlink(dir, recursive = TRUE)
