1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
\name{merge}
\alias{merge}
\alias{merge.data.table}
\title{Merge two data.tables}
\description{
Fast merge of two \code{data.table}s. The \code{data.table} method behaves
very similarly to that of \code{data.frame}s except that, by default, it attempts to merge
\itemize{
\item at first based on the shared key columns, and if there are none,
\item then based on key columns of the first argument \code{x}, and if there
are none,
\item then based on the common columns between the two \code{data.table}s.
}
Set the \code{by}, or \code{by.x} and \code{by.y} arguments explicitly to override this default.
}
\usage{
\method{merge}{data.table}(x, y, by = NULL, by.x = NULL, by.y = NULL, all = FALSE,
all.x = all, all.y = all, sort = TRUE, suffixes = c(".x", ".y"), no.dups = TRUE,
allow.cartesian=getOption("datatable.allow.cartesian"), # default FALSE
\dots)
}
\arguments{
\item{x, y}{\code{data table}s. \code{y} is coerced to a \code{data.table} if
it isn't one already.}
\item{by}{A vector of shared column names in \code{x} and \code{y} to merge on.
This defaults to the shared key columns between the two tables.
If \code{y} has no key columns, this defaults to the key of \code{x}.}
\item{by.x, by.y}{Vectors of column names in \code{x} and \code{y} to merge on.}
\item{all}{logical; \code{all = TRUE} is shorthand to save setting both
\code{all.x = TRUE} and \code{all.y = TRUE}.}
\item{all.x}{logical; if \code{TRUE}, then extra rows will be added to the
output, one for each row in \code{x} that has no matching row in \code{y}.
These rows will have 'NA's in those columns that are usually filled with values
from \code{y}. The default is \code{FALSE}, so that only rows with data from both
\code{x} and \code{y} are included in the output.}
\item{all.y}{logical; analogous to \code{all.x} above.}
\item{sort}{logical. If \code{TRUE} (default), the merged \code{data.table} is
sorted by setting the key to the \code{by / by.x} columns. If \code{FALSE}, the
result is not sorted.}
\item{suffixes}{A \code{character(2)} specifying the suffixes to be used for
making non-\code{by} column names unique. The suffix behaviour works in a similar
fashion as the \code{\link{merge.data.frame}} method does.}
\item{no.dups}{logical indicating that \code{suffixes} are also appended to
non-\code{by.y} column names in \code{y} when they have the same column name
as any \code{by.x}.}
\item{allow.cartesian}{See \code{allow.cartesian} in \code{\link{[.data.table}}.}
\item{\dots}{Not used at this time.}
}
\details{
\code{\link{merge}} is a generic function in base R. It dispatches to either the
\code{merge.data.frame} method or \code{merge.data.table} method depending on
the class of its first argument. Note that, unlike \code{SQL}, \code{NA} is
matched against \code{NA} (and \code{NaN} against \code{NaN}) while merging.
In versions \code{<= v1.9.4}, if the specified columns in \code{by} were not the
key (or head of the key) of \code{x} or \code{y}, then a \code{\link{copy}} is
first re-keyed prior to performing the merge. This was less performant as well as memory
inefficient. The concept of secondary keys (implemented in \code{v1.9.4}) was
used to overcome this limitation from \code{v1.9.6}+. No deep copies are made
any more, thereby improving performance and memory efficiency. Also, there is better
control for providing the columns to merge on with the help of the newly implemented
\code{by.x} and \code{by.y} arguments.
For a more \code{data.table}-centric way of merging two \code{data.table}s, see
\code{\link{[.data.table}}; e.g., \code{x[y, \dots]}. See FAQ 1.11 for a detailed
comparison of \code{merge} and \code{x[y, \dots]}.
}
\value{
A new \code{data.table} based on the merged \code{data table}s, and sorted by the
columns set (or inferred for) the \code{by} argument if argument \code{sort} is
set to \code{TRUE}.
}
\seealso{
\code{\link{data.table}}, \code{\link{as.data.table}}, \code{\link{[.data.table}},
\code{\link{merge.data.frame}}
}
\examples{
(dt1 <- data.table(A = letters[1:10], X = 1:10, key = "A"))
(dt2 <- data.table(A = letters[5:14], Y = 1:10, key = "A"))
merge(dt1, dt2)
merge(dt1, dt2, all = TRUE)
(dt1 <- data.table(A = letters[rep(1:3, 2)], X = 1:6, key = "A"))
(dt2 <- data.table(A = letters[rep(2:4, 2)], Y = 6:1, key = "A"))
merge(dt1, dt2, allow.cartesian=TRUE)
(dt1 <- data.table(A = c(rep(1L, 5), 2L), B = letters[rep(1:3, 2)], X = 1:6, key = "A,B"))
(dt2 <- data.table(A = c(rep(1L, 5), 2L), B = letters[rep(2:4, 2)], Y = 6:1, key = "A,B"))
merge(dt1, dt2)
merge(dt1, dt2, by="B", allow.cartesian=TRUE)
# test it more:
d1 <- data.table(a=rep(1:2,each=3), b=1:6, key="a,b")
d2 <- data.table(a=0:1, bb=10:11, key="a")
d3 <- data.table(a=0:1, key="a")
d4 <- data.table(a=0:1, b=0:1, key="a,b")
merge(d1, d2)
merge(d2, d1)
merge(d1, d2, all=TRUE)
merge(d2, d1, all=TRUE)
merge(d3, d1)
merge(d1, d3)
merge(d1, d3, all=TRUE)
merge(d3, d1, all=TRUE)
merge(d1, d4)
merge(d1, d4, by="a", suffixes=c(".d1", ".d4"))
merge(d4, d1)
merge(d1, d4, all=TRUE)
merge(d4, d1, all=TRUE)
# new feature, no need to set keys anymore
set.seed(1L)
d1 <- data.table(a=sample(rep(1:3,each=2)), z=1:6)
d2 <- data.table(a=2:0, z=10:12)
merge(d1, d2, by="a")
merge(d1, d2, by="a", all=TRUE)
# new feature, using by.x and by.y arguments
setnames(d2, "a", "b")
merge(d1, d2, by.x="a", by.y="b")
merge(d1, d2, by.x="a", by.y="b", all=TRUE)
merge(d2, d1, by.x="b", by.y="a")
}
\keyword{ data }
|
