gridscore: Tuning of predictive models on a validation dataset

In mlesnoff/rchemo: Dimension reduction, Regression and Discrimination for Chemometrics

Tuning of predictive models on a validation dataset

Description

Functions for tuning predictive models on a validation set.

The functions return "scores" (average error rates) of predictions for a given model and a grid of parameter values, calculated on a validation dataset.

- gridscore: Can be used for any model.

- gridscorelv: Specific to models using regularization by latent variables (LVs) (e.g. PLSR). Much faster than gridscore.

- gridscorelb: Specific to models using ridge regularization (e.g. RR). Much faster than gridscore.

Argument pars (the grid) must be a list of named vectors, each vector corresponding to an argument of the model function and giving the parameter values to consider for this argument. This list can eventually be built with function mpars, which returns all the combinations of the input parameters, see the examples.

For gridscorelv, pars must not contain nlv (nb. LVs), and for gridscorelb, lb (regularization parameter lambda).

Usage

gridscore(Xtrain, Ytrain, X, Y, score, fun, pars, verb = FALSE)

gridscorelv(Xtrain, Ytrain, X, Y, score, fun, nlv, pars = NULL, verb = FALSE)

gridscorelb(Xtrain, Ytrain, X, Y, score, fun, lb, pars = NULL, verb = FALSE)

Arguments

Xtrain	Training X-data (n, p).
Ytrain	Training Y-data (n, q).
X	Validation X-data (n, p).
Y	Validation Y-data (n, q).
score	A function calculating a prediction score (e.g. msep).
fun	A function corresponding to the predictive model.
nlv	For gridscorelv. A vector of numbers of LVs.
lb	For gridscorelb. A vector of ridge regulariation parameters.
pars	A list of named vectors. Each vector must correspond to an argument of the model function and gives the parameter values to consider for this argument.
verb	Logical. If TRUE, fitting information are printed.

Value

A dataframe with the prediction scores for the grid.

Examples

######################## EXAMPLES WITH PLSR

n <- 50 ; p <- 8
Xtrain <- matrix(rnorm(n * p), ncol = p, byrow = TRUE)
ytrain <- rnorm(n)
Ytrain <- cbind(ytrain, 10 * rnorm(n))
m <- 3
Xtest <- Xtrain[1:m, ] 
Ytest <- Ytrain[1:m, ] ; ytest <- Ytest[, 1]

## Using gridscore
nlv <- 5
pars <- mpars(nlv = 1:nlv)
pars
gridscore(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = plskern, 
    pars = pars, verb = TRUE
    )

## Using gridscorelv (much faster) 
gridscorelv(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = plskern, 
    nlv = 0:nlv, verb = TRUE
    )

fm <- plskern(Xtrain, Ytrain, nlv = nlv)
pred <- predict(fm, Xtest)$pred
msep(pred, Ytest)

######################## EXAMPLES WITH PLSLDA

n <- 50 ; p <- 8
X <- matrix(rnorm(n * p), ncol = p, byrow = TRUE)
y <- sample(c(1, 4, 10), size = n, replace = TRUE)
#y <- sample(c("a", "10", "d"), size = n, replace = TRUE)
#y <- as.factor(sample(c(1, 4, 10), size = n, replace = TRUE))
#y <- as.factor(sample(c("a", "10", "d"), size = n, replace = TRUE))
Xtrain <- X ; ytrain <- y
m <- 5
Xtest <- X[1:m, ] ; ytest <- y[1:m]

## Using gridscore
nlv <- 5
pars <- mpars(nlv = 1:nlv, prior = c("unif", "prop"))
pars
gridscore(
    Xtrain, ytrain, Xtest, ytest, 
    score = err, 
    fun = plslda,
    pars = pars, verb = TRUE
    )

fm <- plslda(Xtrain, ytrain, nlv = nlv)
pred <- predict(fm, Xtest)$pred
err(pred, ytest)

## Using gridscorelv (much faster) 
pars <- mpars(prior = c("unif", "prop"))
pars
gridscorelv(
    Xtrain, ytrain, Xtest, ytest, 
    score = err, 
    fun = plslda,
    nlv = 1:nlv, pars = pars, verb = TRUE
    )

######################## EXAMPLES WITH RR

n <- 50 ; p <- 8
Xtrain <- matrix(rnorm(n * p), ncol = p, byrow = TRUE)
ytrain <- rnorm(n)
Ytrain <- cbind(ytrain, 10 * rnorm(n))
m <- 3
Xtest <- Xtrain[1:m, ] 
Ytest <- Ytrain[1:m, ] ; ytest <- Ytest[, 1]

## Using gridscore
lb <- c(.1, 1)
pars <- mpars(lb = lb)
pars
gridscore(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = rr, 
    pars = pars, verb = TRUE
    )

## Using gridscorelb (much faster) 
gridscorelb(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = rr, 
    lb = lb, verb = TRUE
    )

######################## EXAMPLES WITH KRR

n <- 50 ; p <- 8
Xtrain <- matrix(rnorm(n * p), ncol = p, byrow = TRUE)
ytrain <- rnorm(n)
Ytrain <- cbind(ytrain, 10 * rnorm(n))
m <- 3
Xtest <- Xtrain[1:m, ] 
Ytest <- Ytrain[1:m, ] ; ytest <- Ytest[, 1]

## Using gridscore
lb <- c(.1, 1)
gamma <- 10^(-1:1)
pars <- mpars(lb = lb, gamma = gamma)
pars
gridscore(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = krr, 
    pars = pars, verb = TRUE
    )

## Using gridscorelb (much faster) 
pars <- mpars(gamma = gamma)
gridscorelb(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = krr, 
    lb = lb, pars = pars, verb = TRUE
    )

######################## EXAMPLES WITH LWPLSR

n <- 50 ; p <- 8
Xtrain <- matrix(rnorm(n * p), ncol = p, byrow = TRUE)
ytrain <- rnorm(n)
Ytrain <- cbind(ytrain, 10 * rnorm(n))
m <- 3
Xtest <- Xtrain[1:m, ] 
Ytest <- Ytrain[1:m, ] ; ytest <- Ytest[, 1]

nlvdis <- 5
h <- c(1, Inf)
k <- c(10, 20)
nlv <- 5
pars <- mpars(nlvdis = nlvdis, diss = "mahal",
    h = h, k = k)
pars
res <- gridscorelv(
    Xtrain, Ytrain, Xtest, Ytest, 
    score = msep, 
    fun = lwplsr, 
    nlv = 0:nlv, pars = pars, verb = TRUE
    )
res

mlesnoff/rchemo documentation built on April 15, 2023, 1:25 p.m.