apply.gdsn: Apply functions over margins

In zhengxwen/gdsfmt: R Interface to CoreArray Genomic Data Structure (GDS) Files

Apply functions over margins

Description

Return a vector or list of values obtained by applying a function to margins of a GDS matrix or array.

Usage

apply.gdsn(node, margin, FUN, selection=NULL,
    as.is=c("list", "none", "integer", "double", "character", "logical",
    "raw", "gdsnode"), var.index=c("none", "relative", "absolute"),
    target.node=NULL, .useraw=FALSE, .value=NULL, .substitute=NULL, ...)

Arguments

node	an object of class gdsn.class, or a list of objects of class gdsn.class
margin	an integer giving the subscripts which the function will be applied over. E.g., for a matrix 1 indicates rows, 2 indicates columns
FUN	the function to be applied
selection	a list or NULL; if a list, it is a list of logical vectors according to dimensions indicating selection; if NULL, uses all data
as.is	returned value: a list, an integer vector, etc; "gdsnode" – the returned value from the user-defined function will be appended to target.node.
var.index	if "none", call FUN(x, ...) without an index; if "relative" or "absolute", add an argument to the user-defined function FUN like FUN(index, x, ...) where index in the function is an index starting from 1: "relative" for indexing in the selection defined by selection, "absolute" for indexing with respect to all data
target.node	NULL, an object of class gdsn.class or a list of gdsn.class: output to the target GDS node(s) when as.is="gdsnode". See details
.useraw	use R RAW storage mode if integers can be stored in a byte, to reduce memory usage
.value	a vector of values to be replaced in the original data array, or NULL for nothing
.substitute	a vector of values after replacing, or NULL for nothing; length(.substitute) should be one or length(.value); if length(.substitute) = length(.value), it is a mapping from .value to .substitute
...	optional arguments to FUN

Details

The algorithm is optimized by blocking the computations to exploit the high-speed memory instead of disk.

When as.is="gdsnode" and there are more than one gdsn.class object in target.node, the user-defined function should return a list with elements corresponding to target.node, or NULL indicating no appending.

Value

A vector or list of values.

Author(s)

Xiuwen Zheng

See Also

read.gdsn, readex.gdsn, clusterApply.gdsn

Examples

# cteate a GDS file
f <- createfn.gds("test.gds")

(n1 <- add.gdsn(f, "matrix", val=matrix(1:(10*6), nrow=10)))
read.gdsn(index.gdsn(f, "matrix"))

(n2 <- add.gdsn(f, "string",
    val=matrix(paste("L", 1:(10*6), sep=","), nrow=10)))
read.gdsn(index.gdsn(f, "string"))

# Apply functions over rows of matrix
apply.gdsn(n1, margin=1, FUN=function(x) print(x), as.is="none")
apply.gdsn(n1, margin=1,
    selection = list(rep(c(TRUE, FALSE), 5), rep(c(TRUE, FALSE), 3)),
    FUN=function(x) print(x), as.is="none")
apply.gdsn(n1, margin=1, var.index="relative",
    selection = list(rep(c(TRUE, FALSE), 5), rep(c(TRUE, FALSE), 3)),
    FUN=function(i, x) { cat("index: ", i, ", ", sep=""); print(x) },
    as.is="none")
apply.gdsn(n1, margin=1, var.index="absolute",
    selection = list(rep(c(TRUE, FALSE), 5), rep(c(TRUE, FALSE), 3)),
    FUN=function(i, x) { cat("index: ", i, ", ", sep=""); print(x) },
    as.is="none")
apply.gdsn(n2, margin=1, FUN=function(x) print(x), as.is="none")


# Apply functions over columns of matrix
apply.gdsn(n1, margin=2, FUN=function(x) print(x), as.is="none")
apply.gdsn(n1, margin=2,
    selection = list(rep(c(TRUE, FALSE), 5), rep(c(TRUE, FALSE), 3)),
    FUN=function(x) print(x), as.is="none")
apply.gdsn(n2, margin=2,
    selection = list(rep(c(TRUE, FALSE), 5), rep(c(TRUE, FALSE), 3)),
    FUN=function(x) print(x), as.is="none")


apply.gdsn(n1, margin=1, FUN=function(x) print(x), as.is="none",
    .value=16:40, .substitute=NA)
apply.gdsn(n1, margin=2, FUN=function(x) print(x), as.is="none",
    .value=16:40, .substitute=NA)


# close
closefn.gds(f)



########################################################
#
# Append to a target GDS node
#

# cteate a GDS file
f <- createfn.gds("test.gds")

(n2 <- add.gdsn(f, "matrix", val=matrix(1:(10*6), nrow=10)))

(n2 <- add.gdsn(f, "string",
    val=matrix(paste("L", 1:(10*6), sep=","), nrow=10)))
read.gdsn(index.gdsn(f, "string"))

n2.1 <- add.gdsn(f, "transpose.matrix", storage="int", valdim=c(6,0))
n2.1 <- add.gdsn(f, "transpose.string", storage="string", valdim=c(6,0))

# Apply functions over rows of matrix
apply.gdsn(n2, margin=1, FUN=`c`, as.is="gdsnode", target.node=n2.1)

# matrix transpose
read.gdsn(n2)
read.gdsn(n2.1)


# Apply functions over rows of matrix
apply.gdsn(n2, margin=1, FUN=`c`, as.is="gdsnode", target.node=n2.1)

# matrix transpose
read.gdsn(n2)
read.gdsn(n2.1)

# close
closefn.gds(f)



########################################################
#
# Append to multiple target GDS node
#

# cteate a GDS file
f <- createfn.gds("test.gds")

(n2 <- add.gdsn(f, "matrix", val=matrix(1:(10*6), nrow=10)))

n2.1 <- add.gdsn(f, "transpose.matrix", storage="int", valdim=c(6,0))
n2.2 <- add.gdsn(f, "n.matrix", storage="int", valdim=c(0))

# Apply functions over rows of matrix
apply.gdsn(n2, margin=1, FUN=function(x) list(x, x[1]),
    as.is="gdsnode", target.node=list(n2.1, n2.2))

# matrix transpose
read.gdsn(n2)
read.gdsn(n2.1)
read.gdsn(n2.2)

# close
closefn.gds(f)




########################################################
#
# Multiple variables
#

# cteate a GDS file
f <- createfn.gds("test.gds")

X <- matrix(1:50, nrow=10)
Y <- matrix((1:50)/100, nrow=10)
Z1 <- factor(c(rep(c("ABC", "DEF", "ETD"), 3), "TTT"))
Z2 <- c(TRUE, FALSE, TRUE, FALSE, TRUE)

node.X <- add.gdsn(f, "X", X)
node.Y <- add.gdsn(f, "Y", Y)
node.Z1 <- add.gdsn(f, "Z1", Z1)
node.Z2 <- add.gdsn(f, "Z2", Z2)

v <- apply.gdsn(list(X=node.X, Y=node.Y, Z=node.Z1), margin=c(1, 1, 1),
    FUN=print, as.is="none")

v <- apply.gdsn(list(X=node.X, Y=node.Y, Z=node.Z2), margin=c(2, 2, 1),
    FUN=print)

v <- apply.gdsn(list(X=node.X, Y=node.Y, Z=node.Z2), margin=c(2, 2, 1),
    FUN=print, .value=35:45, .substitute=NA)

v <- apply.gdsn(list(X=node.X, Y=node.Y, Z=node.Z2), margin=c(2, 2, 1),
    FUN=print, .value=35:45, .substitute=NA)



# with selection

s1 <- rep(c(FALSE, TRUE), 5)
s2 <- c(TRUE, FALSE, TRUE, FALSE, TRUE)

v <- apply.gdsn(list(X=node.X, Y=node.Y, Z=node.Z1), margin=c(1, 1, 1),
    selection = list(list(s1, s2), list(s1, s2), list(s1)),
    FUN=function(x) print(x))

v <- apply.gdsn(list(X=node.X, Y=node.Y, Z=node.Z2), margin=c(2, 2, 1),
    selection = list(list(s1, s2), list(s1, s2), list(s2)),
    FUN=function(x) print(x))


# close the GDS file
closefn.gds(f)


# delete the temporary file
unlink("test.gds", force=TRUE)

zhengxwen/gdsfmt documentation built on Sept. 27, 2024, 10:08 a.m.