Operate on grouped data in data frames and data sets
Groups.RdGroup creates a grouped variant of an object of
class "data.frame" or of class "data.set", for which methods for
with and within are defined, so that these well-known
functions can be applied "groupwise".
Usage
# Create an object of class "grouped.data" from a
# data frame or a data set.
Groups(data,by,...)
# S3 method for class 'data.frame'
Groups(data,by,...)
# S3 method for class 'data.set'
Groups(data,by,...)
# S3 method for class 'grouped.data'
Groups(data,by,...)
# Recombine grouped data into a data fame or a data set
recombine(x,...)
# S3 method for class 'grouped.data.frame'
recombine(x,...)
# S3 method for class 'grouped.data.set'
recombine(x,...)
# Recombine grouped data and coerce the result appropriately:
# S3 method for class 'grouped.data'
as.data.frame(x,...)
# S4 method for class 'grouped.data.frame'
as.data.set(x,row.names=NULL,...)
# S4 method for class 'grouped.data.set'
as.data.set(x,row.names=NULL,...)
# Methods of the generics "with" and "within" for grouped data
# S3 method for class 'grouped.data'
with(data,expr,...)
# S3 method for class 'grouped.data'
within(data,expr,recombine=FALSE,...)
# This is equivalent to with(Groups(data,by),expr,...)
withGroups(data,by,expr,...)
# This is equivalent to within(Groups(data,by),expr,recombine,...)
withinGroups(data,by,expr,recombine=TRUE,...)Arguments
- data
an object of the classes "data.frame", "data.set" if an argument to
Groups,withGroups,withinGroups,- by
a formula with the factors the levels of which define the groups.
- expr
an expression, or several expressions enclosed in curly braces.
- recombine
a logical vector; should the resulting grouped data be recombined?
- x
an object of class "grouped.data".
- row.names
an optional character vector with row names.
- ...
other arguments, ignored.
Details
When applied to a data frame Groups returns an object with class attributes
"grouped.data.frame", "grouped.data", and "data.frame", when applied do an object with class
"data.set", it returns an object with class attributes "grouped.data.set",
"grouped.data", and "data.set".
When applied to objects with class attributed
"grouped.data", both the functions with() amd within()
evaluate expr separately for each group defined by
Groups. with() returns an array composed of the results
of expr, while within() returns a modified copy of its
data argument, which will be a "grouped.data" object
("grouped.data.frame" or "grouped.data.set"), unless the argument
recombine=TRUE is set.
The expression expr may contain references to the variables
n_, N_, and i_. n_ is equal to the size of
the respective group (the number of rows belonging to it), while
N_ is equal to the total number of observations in all
groups. The variable i_ equals to the indices of the rows
belonging to the respective group of observations.
Examples
some.data <- data.frame(x=rnorm(n=100))
some.data <- within(some.data,{
f <- factor(rep(1:4,each=25),labels=letters[1:4])
g <- factor(rep(1:5,each=4,5),labels=LETTERS[1:5])
y <- x + rep(1:4,each=25) + 0.75*rep(1:5,each=4,5)
})
# For demonstration purposes, we create an
# 'empty' group:
some.data <- subset(some.data,
f!="a" | g!="C")
some.grouped.data <- Groups(some.data,
~f+g)
# Computing the means of y for each combination f and g
group.means <- with(some.grouped.data,
mean(y))
group.means
#> g
#> f A B C D E
#> a 1.910285 1.813113 NA 4.628047 4.765704
#> b 3.163240 3.794269 4.147919 4.571508 5.705042
#> c 3.497435 3.662945 5.201009 6.433493 7.067344
#> d 4.165605 6.739396 6.982883 7.306113 8.190686
# Obtaining a groupwise centered variant of y
some.grouped.data <- within(some.grouped.data,{
y.cent <- y - mean(y)
},recombine=FALSE)
# The groupwise centered variable should have zero mean
# whithin each group
group.means <- with(some.grouped.data,
round(mean(y.cent),15))
group.means
#> g
#> f A B C D E
#> a 0 0 NA 0 0
#> b 0 0 0 0 0
#> c 0 0 0 0 0
#> d 0 0 0 0 0
# The following demonstrates the use of n_, N_, and i_
# An external copy of y
y1 <- some.data$y
group.means.n <- with(some.grouped.data,
c(mean(y), # Group means for y
n_, # Group sizes
sum(y)/n_,# Group means for y
n_/N_, # Relative group sizes
sum(y1)/N_,# NOT the grand mean
sum(y1[i_])/n_)) # Group mean for y1
group.means.n
#> , , g = A
#>
#> f
#> a b c d
#> mean(y) 1.91028489 3.16323983 3.49743466 4.16560478
#> n_ 8.00000000 4.00000000 4.00000000 4.00000000
#> sum(y)/n_ 1.91028489 3.16323983 3.49743466 4.16560478
#> n_/N_ 0.08333333 0.04166667 0.04166667 0.04166667
#> sum(y1)/N_ 4.93633741 4.93633741 4.93633741 4.93633741
#> sum(y1[i_])/n_ 1.91028489 3.16323983 3.49743466 4.16560478
#>
#> , , g = B
#>
#> f
#> a b c d
#> mean(y) 1.81311307 3.79426884 3.66294505 6.73939584
#> n_ 5.00000000 7.00000000 4.00000000 4.00000000
#> sum(y)/n_ 1.81311307 3.79426884 3.66294505 6.73939584
#> n_/N_ 0.05208333 0.07291667 0.04166667 0.04166667
#> sum(y1)/N_ 4.93633741 4.93633741 4.93633741 4.93633741
#> sum(y1[i_])/n_ 1.81311307 3.79426884 3.66294505 6.73939584
#>
#> , , g = C
#>
#> f
#> a b c d
#> mean(y) NA 4.147919 5.201009 6.98288284
#> n_ NA 6.000000 6.000000 4.00000000
#> sum(y)/n_ NA 4.147919 5.201009 6.98288284
#> n_/N_ NA 0.062500 0.062500 0.04166667
#> sum(y1)/N_ NA 4.936337 4.936337 4.93633741
#> sum(y1[i_])/n_ NA 4.147919 5.201009 6.98288284
#>
#> , , g = D
#>
#> f
#> a b c d
#> mean(y) 4.62804704 4.57150804 6.43349330 7.30611330
#> n_ 4.00000000 4.00000000 7.00000000 5.00000000
#> sum(y)/n_ 4.62804704 4.57150804 6.43349330 7.30611330
#> n_/N_ 0.04166667 0.04166667 0.07291667 0.05208333
#> sum(y1)/N_ 4.93633741 4.93633741 4.93633741 4.93633741
#> sum(y1[i_])/n_ 4.62804704 4.57150804 6.43349330 7.30611330
#>
#> , , g = E
#>
#> f
#> a b c d
#> mean(y) 4.76570424 5.70504209 7.06734352 8.19068598
#> n_ 4.00000000 4.00000000 4.00000000 8.00000000
#> sum(y)/n_ 4.76570424 5.70504209 7.06734352 8.19068598
#> n_/N_ 0.04166667 0.04166667 0.04166667 0.08333333
#> sum(y1)/N_ 4.93633741 4.93633741 4.93633741 4.93633741
#> sum(y1[i_])/n_ 4.76570424 5.70504209 7.06734352 8.19068598
#>
# Names can be attached to the groupwise results
with(some.grouped.data,
c(Centered=round(mean(y.cent),15),
Uncentered=mean(y)))
#> , , g = A
#>
#> f
#> a b c d
#> Centered 0.000000 0.00000 0.000000 0.000000
#> Uncentered 1.910285 3.16324 3.497435 4.165605
#>
#> , , g = B
#>
#> f
#> a b c d
#> Centered 0.000000 0.000000 0.000000 0.000000
#> Uncentered 1.813113 3.794269 3.662945 6.739396
#>
#> , , g = C
#>
#> f
#> a b c d
#> Centered NA 0.000000 0.000000 0.000000
#> Uncentered NA 4.147919 5.201009 6.982883
#>
#> , , g = D
#>
#> f
#> a b c d
#> Centered 0.000000 0.000000 0.000000 0.000000
#> Uncentered 4.628047 4.571508 6.433493 7.306113
#>
#> , , g = E
#>
#> f
#> a b c d
#> Centered 0.000000 0.000000 0.000000 0.000000
#> Uncentered 4.765704 5.705042 7.067344 8.190686
#>
some.data.ungrouped <- recombine(some.grouped.data)
str(some.data.ungrouped)
#> 'data.frame': 96 obs. of 5 variables:
#> $ x : num -0.387 -0.785 -1.057 -0.796 -1.756 ...
#> $ y : num 1.363 0.965 0.693 0.954 0.744 ...
#> $ g : Factor w/ 5 levels "A","B","C","D",..: 1 1 1 1 2 2 2 2 4 4 ...
#> $ f : Factor w/ 4 levels "a","b","c","d": 1 1 1 1 1 1 1 1 1 1 ...
#> $ y.cent: num -0.547 -0.946 -1.217 -0.956 -1.069 ...
# It all works with "data.set" objects
some.dataset <- as.data.set(some.data)
some.grouped.dataset <- Groups(some.dataset,~f+g)
with(some.grouped.dataset,
c(Mean=mean(y),
Variance=var(y)))
#> , , g = A
#>
#> f
#> a b c d
#> Mean 1.910285 3.163240 3.497435 4.165605
#> Variance 1.255861 1.378847 1.465161 2.056243
#>
#> , , g = B
#>
#> f
#> a b c d
#> Mean 1.8131131 3.7942688 3.6629450 6.739396
#> Variance 0.4534572 0.6756092 0.8136362 1.578382
#>
#> , , g = C
#>
#> f
#> a b c d
#> Mean NA 4.147919 5.2010090 6.9828828
#> Variance NA 1.381988 0.2987582 0.5685829
#>
#> , , g = D
#>
#> f
#> a b c d
#> Mean 4.628047 4.571508 6.4334933 7.306113
#> Variance 1.177018 0.691624 0.8311554 1.186533
#>
#> , , g = E
#>
#> f
#> a b c d
#> Mean 4.765704 5.7050421 7.0673435 8.190686
#> Variance 1.409835 0.5370272 0.3285284 1.233791
#>
# The following two expressions are equivalent:
with(Groups(some.data,~f+g),mean(y))
#> g
#> f A B C D E
#> a 1.910285 1.813113 NA 4.628047 4.765704
#> b 3.163240 3.794269 4.147919 4.571508 5.705042
#> c 3.497435 3.662945 5.201009 6.433493 7.067344
#> d 4.165605 6.739396 6.982883 7.306113 8.190686
withGroups(some.data,~f+g,mean(y))
#> g
#> f A B C D E
#> a 1.910285 1.813113 NA 4.628047 4.765704
#> b 3.163240 3.794269 4.147919 4.571508 5.705042
#> c 3.497435 3.662945 5.201009 6.433493 7.067344
#> d 4.165605 6.739396 6.982883 7.306113 8.190686
# The following two expressions are equivalent:
some.data <- within(Groups(some.data,~f+g),{
y.cent <- y - mean(y)
y.cent.1 <- y - sum(y)/n_
})
some.data <- withinGroups(some.data,~f+g,{
y.cent <- y - mean(y)
y.cent.1 <- y - sum(y)/n_
})
# Both variants of groupwise centred varaibles should
# have zero groupwise means:
withGroups(some.data,~f+g,{
c(round(mean(y.cent),15),
round(mean(y.cent.1),15))
})
#> , , g = A
#>
#> f
#> a b c d
#> 1 0 0 0 0
#> 2 0 0 0 0
#>
#> , , g = B
#>
#> f
#> a b c d
#> 1 0 0 0 0
#> 2 0 0 0 0
#>
#> , , g = C
#>
#> f
#> a b c d
#> 1 NA 0e+00 0e+00 0
#> 2 NA -1e-15 -1e-15 0
#>
#> , , g = D
#>
#> f
#> a b c d
#> 1 0 0 0 0e+00
#> 2 0 0 0 1e-15
#>
#> , , g = E
#>
#> f
#> a b c d
#> 1 0 0 0 0
#> 2 0 0 0 0
#>