mets (version 1.3.4)

dby: Calculate summary statistics grouped by

Description

Calculate summary statistics grouped by variable

Usage

dby(
  data,
  INPUT,
  ...,
  ID = NULL,
  ORDER = NULL,
  SUBSET = NULL,
  SORT = 0,
  COMBINE = !REDUCE,
  NOCHECK = FALSE,
  ARGS = NULL,
  NAMES,
  COLUMN = FALSE,
  REDUCE = FALSE,
  REGEX = mets.options()$regex,
  ALL = TRUE
)

Arguments

data

Data.frame

INPUT

Input variables (character or formula)

...

functions

ID

id variable

ORDER

(optional) order variable

SUBSET

(optional) subset expression

SORT

sort order (id+order variable)

COMBINE

If TRUE result is appended to data

NOCHECK

No sorting or check for missing data

ARGS

Optional list of arguments to functions (...)

NAMES

Optional vector of column names

COLUMN

If TRUE do the calculations for each column

REDUCE

Reduce number of redundant rows

REGEX

Allow regular expressions

ALL

if FALSE only the subset will be returned

Author

Klaus K. Holst and Thomas Scheike

Details

Calculate summary statistics grouped by

dby2 for column-wise calculations

Examples

n <- 4
k <- c(3,rbinom(n-1,3,0.5)+1)
N <- sum(k)
d <- data.frame(y=rnorm(N),x=rnorm(N),id=rep(seq(n),k),num=unlist(sapply(k,seq)))
d2 <- d[sample(nrow(d)),]

dby(d2, y~id, mean)
dby(d2, y~id + order(num), cumsum)

dby(d,y ~ id + order(num), dlag)
dby(d,y ~ id + order(num), dlag, ARGS=list(k=1:2))
dby(d,y ~ id + order(num), dlag, ARGS=list(k=1:2), NAMES=c("l1","l2"))

dby(d, y~id + order(num), mean=mean, csum=cumsum, n=length)
dby(d2, y~id + order(num), a=cumsum, b=mean, N=length, l1=function(x) c(NA,x)[-length(x)])

dby(d, y~id + order(num), nn=seq_along, n=length)
dby(d, y~id + order(num), nn=seq_along, n=length)

d <- d[,1:4]
dby(d, x<0) <- list(z=mean)
d <- dby(d, is.na(z), z=1)

f <- function(x) apply(x,1,min)
dby(d, y+x~id, min=f)

dby(d,y+x~id+order(num), function(x) x)

f <- function(x) { cbind(cumsum(x[,1]),cumsum(x[,2]))/sum(x)}
dby(d, y+x~id, f)

## column-wise
a <- d
dby2(a, mean, median, REGEX=TRUE) <- '^[y|x]'~id
a
## wildcards 
dby2(a,'y*'+'x*'~id,mean) 


## subset
dby(d, x<0) <- list(z=NA)
d
dby(d, y~id|x>-1, v=mean,z=1)
dby(d, y+x~id|x>-1, mean, median, COLUMN=TRUE)

dby2(d, y+x~id|x>0, mean, REDUCE=TRUE)

dby(d,y~id|x<0,mean,ALL=FALSE)

a <- iris
a <- dby(a,y=1)
dby(a,Species=="versicolor") <- list(y=2)