Related
I've followed the code provided in the vignette of crmPack (pages 16-17) to define the one-parameter power model. I would need to feed it some toxicity data using the update function, but the error I get is "no slot of name "call"". Here is the code below. I would be very grateful for any comments or ideas in order to "fix" this. Many thanks.
# package and options
library(crmPack)
options <- McmcOptions(burnin = 1000, step = 2, samples = 5000)
set.seed(1)
# extra functions to define the power model
.OneParExp <- setClass(Class = "OneParExp", contains = "Model",
representation(skeletonFun = "function",
skeletonProbs = "numeric",
lambda = "numeric"))
OneParExp <- function(skeletonProbs, doseGrid, lambda)
{
skeletonFun <- approxfun(x = doseGrid, y = skeletonProbs, rule = 2)
invSkeletonFun <- approxfun(x = skeletonProbs, y = doseGrid, rule = 1)
.OneParExp(
skeletonFun = skeletonFun, skeletonProbs = skeletonProbs,
lambda = lambda,
datamodel = function(){
for (i in 1:nObs)
{
y[i] ~ dbern(p[i])
p[i] <- skeletonProbs[xLevel[i]]^theta
}},
datanames = c("nObs", "y", "xLevel"),
prob = function(dose, theta){ skeletonFun(dose)^theta },
dose = function(prob, theta){ invSkeletonFun(prob^(1 / theta)) },
priormodel = function(){ theta ~ dexp(lambda) },
modelspecs = function(){ list(skeletonProbs = skeletonProbs,
lambda = lambda) },
init = function(){ list(theta = 1) }, sample = "theta")
}
# tox data and model fitting
data <- Data(x = c(1.2,1.2,1.8,2.4,3),
y = c(0, 0, 0, 1, 1),
cohort = c(1, 1, 2, 3, 4),
doseGrid = seq(1.2, 3, 0.6),
ID = 1:5,
placebo = FALSE)
(skeletonProbs <- round(data#doseGrid / max(data#doseGrid) / 4, 2))
newModel <- OneParExp(skeletonProbs = skeletonProbs,
doseGrid = data#doseGrid, lambda = 1)
newDLTmodel <- update(object=newModel, data=data)
You don't use the "update" function here to feed data to the model. ("update" methods are primarily internal methods to update "Data" objects in crmPack.) Instead, you use "mcmc" to estimate parameters given a model and data:
estimates <- mcmc(model=newModel, data=data, options=McmcOptions())
plot(estimates, newModel, data)
catTestfisher <-
function (tab)
{
st <- if (!is.matrix(tab) || nrow(tab) < 2 | ncol(tab) <
2)
list(p.value = NA, statistic = NA, parameter = NA)
else {
rowcounts <- tab %*% rep(1, ncol(tab))
tab <- tab[rowcounts > 0, ]
if (!is.matrix(tab))
list(p.value = NA, statistic = NA, parameter = NA)
else fisher.test(tab)
}
list(P = st$p.value, stat = "", df = "",
testname = "Fisher's Exact", statname = "", latexstat = "", namefun = "",
plotmathstat = "")
}
I wanted to use library(Hmisc)'s summaryM function but with Fisher's exact test, so I wrote a catTestfisher function and set catTest = catTestfisher in my own summaryM2 function, which is exactly the same as summaryM, except for catTest = catTestfisher
summaryM2 <-
function (formula, groups = NULL, data = NULL, subset, na.action = na.retain,
overall = FALSE, continuous = 10, na.include = FALSE, quant = c(0.025,
0.05, 0.125, 0.25, 0.375, 0.5, 0.625, 0.75, 0.875, 0.95,
0.975), nmin = 100, test = FALSE, conTest = conTestkw,
catTest = catTestfisher, ordTest = ordTestpo)
{
marg <- length(data) && ".marginal." %in% names(data)
if (marg)
formula <- update(formula, . ~ . + .marginal.)
formula <- Formula(formula)
Y <- if (!missing(subset) && length(subset))
model.frame(formula, data = data, subset = subset, na.action = na.action)
else model.frame(formula, data = data, na.action = na.action)
X <- model.part(formula, data = Y, rhs = 1)
Y <- model.part(formula, data = Y, lhs = 1)
getlab <- function(x, default) {
lab <- attr(x, "label")
if (!length(lab) || lab == "")
default
else lab
}
if (marg) {
xm <- X$.marginal.
X$.marginal. <- NULL
}
else xm <- rep("", nrow(X))
if (length(X)) {
xname <- names(X)
if (length(xname) == 1 && !length(groups))
groups <- xname
if (!length(groups) && length(xname) > 1) {
warnings("Must specify groups when > 1 right hand side variable is present.\ngroups taken as first right hand variable.")
groups <- xname[1]
}
svar <- if (length(xname) == 1)
factor(rep(".ALL.", nrow(X)))
else do.call("interaction", list(X[setdiff(xname, groups)],
sep = " "))
group <- X[[groups]]
glabel <- getlab(group, groups)
}
else {
svar <- factor(rep(".ALL.", nrow(Y)))
group <- rep("", nrow(Y))
groups <- group.freq <- NULL
glabel <- ""
}
quants <- unique(c(quant, 0.025, 0.05, 0.125, 0.25, 0.375,
0.5, 0.625, 0.75, 0.875, 0.95, 0.975))
nv <- ncol(Y)
nameY <- names(Y)
R <- list()
for (strat in levels(svar)) {
instrat <- svar == strat
n <- integer(nv)
type <- n
comp <- dat <- vector("list", nv)
names(comp) <- names(dat) <- nameY
labels <- Units <- vector("character", nv)
if (test) {
testresults <- vector("list", nv)
names(testresults) <- names(comp)
}
gr <- group[instrat]
xms <- xm[instrat]
if (all(xms != ""))
xms <- rep("", length(xms))
group.freq <- table(gr)
group.freq <- group.freq[group.freq > 0]
if (overall)
group.freq <- c(group.freq, Combined = sum(group.freq))
for (i in 1:nv) {
w <- Y[instrat, i]
if (length(attr(w, "label")))
labels[i] <- attr(w, "label")
if (length(attr(w, "units")))
Units[i] <- attr(w, "units")
if (!inherits(w, "mChoice")) {
if (!is.factor(w) && !is.logical(w) && length(unique(w[!is.na(w)])) <
continuous)
w <- as.factor(w)
s <- !is.na(w)
if (na.include && !all(s) && length(levels(w))) {
w <- na.include(w)
levels(w)[is.na(levels(w))] <- "NA"
s <- rep(TRUE, length(s))
}
n[i] <- sum(s & xms == "")
w <- w[s]
g <- gr[s, drop = TRUE]
if (is.factor(w) || is.logical(w)) {
tab <- table(w, g)
if (test) {
if (is.ordered(w))
testresults[[i]] <- ordTest(g, w)
else testresults[[i]] <- catTest(tab)
}
if (nrow(tab) == 1) {
b <- casefold(dimnames(tab)[[1]], upper = TRUE)
pres <- c("1", "Y", "YES", "PRESENT")
abse <- c("0", "N", "NO", "ABSENT")
jj <- match(b, pres, nomatch = 0)
if (jj > 0)
bc <- abse[jj]
else {
jj <- match(b, abse, nomatch = 0)
if (jj > 0)
bc <- pres[jj]
}
if (jj) {
tab <- rbind(tab, rep(0, ncol(tab)))
dimnames(tab)[[1]][2] <- bc
}
}
if (overall)
tab <- cbind(tab, Combined = apply(tab, 1,
sum))
comp[[i]] <- tab
type[i] <- 1
}
else {
sfn <- function(x, quant) {
o <- options(digits = 10)
on.exit(options(o))
c(quantile(x, quant), Mean = mean(x), SD = sqrt(var(x)),
N = sum(!is.na(x)))
}
qu <- tapply(w, g, sfn, simplify = TRUE, quants)
if (test)
testresults[[i]] <- conTest(g, w)
if (overall)
qu$Combined <- sfn(w, quants)
comp[[i]] <- matrix(unlist(qu), ncol = length(quants) +
3, byrow = TRUE, dimnames = list(names(qu),
c(format(quants), "Mean", "SD", "N")))
if (any(group.freq <= nmin))
dat[[i]] <- lapply(split(w, g), nmin = nmin,
function(x, nmin) if (length(x) <= nmin)
x
else NULL)
type[i] <- 2
}
}
else {
w <- as.numeric(w) == 1
n[i] <- sum(!is.na(apply(w, 1, sum)) & xms ==
"")
g <- as.factor(gr)
ncat <- ncol(w)
tab <- matrix(NA, nrow = ncat, ncol = length(levels(g)),
dimnames = list(dimnames(w)[[2]], levels(g)))
if (test) {
pval <- numeric(ncat)
names(pval) <- dimnames(w)[[2]]
d.f. <- stat <- pval
}
for (j in 1:ncat) {
tab[j, ] <- tapply(w[, j], g, sum, simplify = TRUE,
na.rm = TRUE)
if (test) {
tabj <- rbind(table(g) - tab[j, ], tab[j,
])
st <- catTest(tabj)
pval[j] <- st$P
stat[j] <- st$stat
d.f.[j] <- st$df
}
}
if (test)
testresults[[i]] <- list(P = pval, stat = stat,
df = d.f., testname = st$testname, statname = st$statname,
latexstat = st$latexstat, plotmathstat = st$plotmathstat)
if (overall)
tab <- cbind(tab, Combined = apply(tab, 1,
sum))
comp[[i]] <- tab
type[i] <- 3
}
}
labels <- ifelse(nchar(labels), labels, names(comp))
R[[strat]] <- list(stats = comp, type = type, group.freq = group.freq,
labels = labels, units = Units, quant = quant, data = dat,
N = sum(!is.na(gr) & xms == ""), n = n, testresults = if (test) testresults)
}
structure(list(results = R, group.name = groups, group.label = glabel,
call = call, formula = formula), class = "summaryM")
}
After trying to test it on the following data, I get a warning and an error:
library(Hmisc)
set.seed(173)
sex <- factor(sample(c("m","f"), 500, rep=TRUE))
treatment <- factor(sample(c("Drug","Placebo"), 500, rep=TRUE))
> summaryM2(sex ~ treatment, test=TRUE, overall = TRUE)
Error in round(teststat, 2) :
non-numeric argument to mathematical function
I tried stepping through the summaryM2 function line by line, but could not figure out what's causing the problem.
In your catTestfisher function, the output variables stat (test statistic) and df (degrees of freedom) should be numeric variables not empty strings. In the programming stat is coverted to teststat for rounding before being outputted (hence the error message for round("", 2) is non-numeric argument to mathematical function). See lines 1718 to 1721 in the summary.formula code) .
You can set df = NULL but a value is required for stat (not NA or NULL) otherwise no output is returned. You can get around the problem by setting stat = 0 (or any other number), and then only displaying the p value using prtest = "P".
catTestfisher2 <- function (tab)
{
st <- fisher.test(tab)
list(P = st$p.value, stat = 0, df = NULL,
testname = st$method, statname = "", latexstat = "", namefun = "",
plotmathstat = "")
}
output <- summaryM(sex ~ treatment, test=TRUE, overall = TRUE, catTest = catTestfisher2)
print(output, prtest = "P")
Descriptive Statistics (N=500)
+-------+-----------+-----------+-----------+-------+
| |Drug |Placebo |Combined |P-value|
| |(N=257) |(N=243) |(N=500) | |
+-------+-----------+-----------+-----------+-------+
|sex : m|0.52 (133)|0.52 (126)|0.52 (259)| 1 |
+-------+-----------+-----------+-----------+-------+
Note there is no need to define your own summaryM2 function. Just use catTest = to pass in your function.
I am applying spectral clustering to a dataset with 4200 rows and 2 columns.
spec <- specClust(df1, centers=7, nn = 7, method = "symmetric")
I have the below error.
n .Call("R_igraph_arpack", func, extra, options, env, sym, PACKAGE = "igraph") :
At arpack.c:944 : ARPACK error, Maximum number of iterations reached
In addition: Warning message:
In .Call("R_igraph_arpack", func, extra, options, env, sym, PACKAGE = "igraph") :
At arpack.c:776 :ARPACK solver failed to converge (1001 iterations, 0/7 eigenvectors converged)
How do i increase the iterations of arpack because this doesnt work:
spec <- specClust(df1, centers=7, nn = 7, method = "symmetric",iter.max=301000)
Digging into the specClust, the ... does not pass anything to the arpack call.
The simplest thing to do I think is to copy the specClust code add maxiter=10000 and source the function in your script.
specCLust2 <- function (data, centers = NULL, nn = 7, method = "symmetric",
gmax = NULL, max.iter = 10000, ...)
{
call = match.call()
if (is.data.frame(data))
data = as.matrix(data)
da = apply(data, 1, paste, collapse = "#")
indUnique = which(!duplicated(da))
indAll = match(da, da[indUnique])
data2 = data
data = data[indUnique, ]
n <- nrow(data)
data = scale(data, FALSE, TRUE)
if (is.null(gmax)) {
if (!is.null(centers))
gmax = centers - 1L
else gmax = 1L
}
test = TRUE
while (test) {
DC = mydist(data, nn)
sif <- rbind(1:n, as.vector(DC[[2]]))
g <- graph(sif, directed = FALSE)
g <- decompose(g, min.vertices = 4)
if (length(g) > 1) {
if (length(g) >= gmax)
nn = nn + 2
else test = FALSE
}
else test = FALSE
}
W <- DC[[1]]
n <- nrow(data)
wi <- W[, nn]
SC <- matrix(1, nrow(W), nn)
SC[] <- wi[DC[[2]]] * wi
W = W^2/SC
alpha = 1/(2 * (nn + 1))
qua = abs(qnorm(alpha))
W = W * qua
W = dnorm(W, sd = 1)
DC[[1]] = W
L = Laplacian(DC, nn, method)
f <- function(x, extra) as.vector(extra %*% x)
if (is.null(centers))
kmax = 25
else kmax = max(centers)
###
#add the maxiter parameter to the arpack call, below
###
U <- arpack(f, extra = L, options = list(n = n, which = "SM",
nev = kmax, ncv = 2 * kmax, mode = 1, maxiter=max.iter), sym = TRUE)
ind <- order(U[[1]])
U[[2]] = U[[2]][indAll, ind]
U[[1]] = U[[1]][ind]
if (is.null(centers)) {
tmp = which.max(diff(U[[1]])) + 1
centers = which.min(AUC(U[[1]][1:tmp]))
}
if (method == "symmetric") {
rs = sqrt(rowSums(U[[2]]^2))
U[[2]] = U[[2]]/rs
}
result = kmeans(U[[2]], centers = centers, nstart = 20, ...)
archeType = getClosest(U[[2]][indAll, ], result$centers)
result$eigenvalue = U[[1]]
result$eigenvector = U[[2]]
result$data = data2
result$indAll = indAll
result$indUnique = indUnique
result$L = L
result$archetype = archeType
result$call = call
class(result) = c("specClust", "kmeans")
result
}
I was wondering how one extracts the estimated parameters stored in an R object of class mle-class.
Here is an example:
x <- matrix(rnorm(300), ncol = 3)
x[x > 1] <- 1
require(tmvtnorm)
fit1 <- mle.tmvnorm(X = x, lower = rep(-Inf, 3), upper = rep(1, 3))
Now, fit1 is an object of class:
class(fit1)
[1] "mle"
attr(,"package")
[1] "stats4
"
fit1 itself gives me:
fit1
Call:
mle(minuslogl = function (mu_1 = 0, mu_2 = 0, mu_3 = 0, sigma_1.1 = 1,
sigma_1.2 = 0, sigma_1.3 = 0, sigma_2.2 = 1, sigma_2.3 = 0,
sigma_3.3 = 1)
{
nf <- names(formals())
theta <- sapply(nf, function(x) {
eval(parse(text = x))
})
mean <- theta[1:n]
if (cholesky) {
L <- inv_vech(theta[-(1:n)])
L[lower.tri(L, diag = FALSE)] <- 0
sigma <- t(L) %*% L
}
else {
sigma <- inv_vech(theta[-(1:n)])
}
if (det(sigma) <= 0 || any(diag(sigma) < 0)) {
return(.Machine$integer.max)
}
f <- -(sum(dmvnorm(X, mean, sigma, log = TRUE)) - nrow(X) *
log(pmvnorm(lower = lower, upper = upper, mean = mean,
sigma = sigma)))
if (is.infinite(f) || is.na(f)) {
return(.Machine$integer.max)
}
f
}, start = as.list(c(0, 0, 0, 1, 0, 0, 1, 0, 1)), method = "BFGS",
fixed = list())
Coefficients:
mu_1 mu_2 mu_3 sigma_1.1 sigma_1.2 sigma_1.3
0.64218198 1.51720543 0.97047201 1.73395947 -0.03889188 0.14627774
sigma_2.2 sigma_2.3 sigma_3.3
2.18020597 0.38822509 1.49854600
My question is: how do I extract these coefficients from the object fit1?
Thanks again for your time, and for your help in answering this question!
coef is a generic function which extracts model coefficients from objects returned by modeling functions. coefficients is an alias for it.
Usage
coef(object, ...)
coefficients(object, ...)
So, fit1#coef should work.
https://stat.ethz.ch/R-manual/R-devel/library/stats/html/coef.html
Sorry for this silly question: I will keep it just in case someone ends up looking.
fit1#coef
mu_1 mu_2 mu_3 sigma_1.1 sigma_1.2 sigma_1.3
0.64218198 1.51720543 0.97047201 1.73395947 -0.03889188 0.14627774
sigma_2.2 sigma_2.3 sigma_3.3
2.18020597 0.38822509 1.49854600
solves the query. Duh!
Say you have a model object of class 'varrest' returned from a VAR() regression operation.
I want to save the model to a file, but not all data which was used to estimate the coefficients.
How can one just save the model specification wihtout the training data?
Because when I save the model it has a file size of over 1GB and therefore loading does take its time.
Can one save objects without some attributes?
The predict.varest function starts out with this code:
K <- object$K
p <- object$p
obs <- object$obs
type <- object$type
data.all <- object$datamat
ynames <- colnames(object$y)
You can then investigate how much pruning you might achieve:
data(Canada)
tcan <-
VAR(Canada, p = 2, type = "trend")
names(tcan)
# [1] "varresult" "datamat" "y" "type" "p"
# [6] "K" "obs" "totobs" "restrictions" "call"
object.size(tcan[c("K","p", "obs", "type", "datamat", "y")] )
#15080 bytes
object.size(tcan)
#252032 bytes
So the difference is substantial, but just saving those items is not sufficient because the next line in predict.varest is:
B <- Bcoef(object)
You will need to add that object to the list above and then construct a new predict-function that accepts something less than the large 'varresult' node of the model object. Also turned out that there was a downstream call to an internal function that needs to be stored. (You will need to decide in advance what interval you need for prediction.)
tsmall <- c( tcan[c("K","p", "obs", "type", "datamat", "y", "call")] )
tsmall[["Bco"]] <- Bcoef(tcan)
tsmall$sig.y <- vars:::.fecov(x = tcan, n.ahead = 10)
And the modified predict function will be:
sm.predict <- function (object, ..., n.ahead = 10, ci = 0.95, dumvar = NULL)
{
K <- object$K
p <- object$p
obs <- object$obs
type <- object$type
data.all <- object$datamat
ynames <- colnames(object$y)
n.ahead <- as.integer(n.ahead)
Z <- object$datamat[, -c(1:K)]
# This used to be a call to Bcoef(object)
B <- object$Bco
if (type == "const") {
Zdet <- matrix(rep(1, n.ahead), nrow = n.ahead, ncol = 1)
colnames(Zdet) <- "const"
}
else if (type == "trend") {
trdstart <- nrow(Z) + 1 + p
Zdet <- matrix(seq(trdstart, length = n.ahead), nrow = n.ahead,
ncol = 1)
colnames(Zdet) <- "trend"
}
else if (type == "both") {
trdstart <- nrow(Z) + 1 + p
Zdet <- matrix(c(rep(1, n.ahead), seq(trdstart, length = n.ahead)),
nrow = n.ahead, ncol = 2)
colnames(Zdet) <- c("const", "trend")
}
else if (type == "none") {
Zdet <- NULL
}
if (!is.null(eval(object$call$season))) {
season <- eval(object$call$season)
seas.names <- paste("sd", 1:(season - 1), sep = "")
cycle <- tail(data.all[, seas.names], season)
seasonal <- as.matrix(cycle, nrow = season, ncol = season -
1)
if (nrow(seasonal) >= n.ahead) {
seasonal <- as.matrix(cycle[1:n.ahead, ], nrow = n.ahead,
ncol = season - 1)
}
else {
while (nrow(seasonal) < n.ahead) {
seasonal <- rbind(seasonal, cycle)
}
seasonal <- seasonal[1:n.ahead, ]
}
rownames(seasonal) <- seq(nrow(data.all) + 1, length = n.ahead)
if (!is.null(Zdet)) {
Zdet <- as.matrix(cbind(Zdet, seasonal))
}
else {
Zdet <- as.matrix(seasonal)
}
}
if (!is.null(eval(object$call$exogen))) {
if (is.null(dumvar)) {
stop("\nNo matrix for dumvar supplied, but object varest contains exogenous variables.\n")
}
if (!all(colnames(dumvar) %in% colnames(data.all))) {
stop("\nColumn names of dumvar do not coincide with exogen.\n")
}
if (!identical(nrow(dumvar), n.ahead)) {
stop("\nRow number of dumvar is unequal to n.ahead.\n")
}
if (!is.null(Zdet)) {
Zdet <- as.matrix(cbind(Zdet, dumvar))
}
else {
Zdet <- as.matrix(dumvar)
}
}
Zy <- as.matrix(object$datamat[, 1:(K * (p + 1))])
yse <- matrix(NA, nrow = n.ahead, ncol = K)
# This used to be a call to vars:::.fecov
sig.y <- object$sig.y
for (i in 1:n.ahead) {
yse[i, ] <- sqrt(diag(sig.y[, , i]))
}
yse <- -1 * qnorm((1 - ci)/2) * yse
colnames(yse) <- paste(ci, "of", ynames)
forecast <- matrix(NA, ncol = K, nrow = n.ahead)
lasty <- c(Zy[nrow(Zy), ])
for (i in 1:n.ahead) {
lasty <- lasty[1:(K * p)]; print(lasty); print(B)
Z <- c(lasty, Zdet[i, ]) ;print(Z)
forecast[i, ] <- B %*% Z
temp <- forecast[i, ]
lasty <- c(temp, lasty)
}
colnames(forecast) <- paste(ynames, ".fcst", sep = "")
lower <- forecast - yse
colnames(lower) <- paste(ynames, ".lower", sep = "")
upper <- forecast + yse
colnames(upper) <- paste(ynames, ".upper", sep = "")
forecasts <- list()
for (i in 1:K) {
forecasts[[i]] <- cbind(forecast[, i], lower[, i], upper[,
i], yse[, i])
colnames(forecasts[[i]]) <- c("fcst", "lower", "upper",
"CI")
}
names(forecasts) <- ynames
result <- list(fcst = forecasts, endog = object$y, model = object,
exo.fcst = dumvar)
class(result) <- "varprd"
return(result)
}
Either
set the attributes you do not want to NULL, or
copy the parts you want to a new object, or
call the save() function with proper indexing.