R: Examples for 'base::merge'

### ** Examples

authors <- data.frame(
    ## I(*) : use character columns of names to get sensible sort order
    surname = I(c("Tukey", "Venables", "Tierney", "Ripley", "McNeil")),
    nationality = c("US", "Australia", "US", "UK", "Australia"),
    deceased = c("yes", rep("no", 4)))
authorN <- within(authors, { name <- surname; rm(surname) })
books <- data.frame(
    name = I(c("Tukey", "Venables", "Tierney",
             "Ripley", "Ripley", "McNeil", "R Core")),
    title = c("Exploratory Data Analysis",
              "Modern Applied Statistics ...",
              "LISP-STAT",
              "Spatial Statistics", "Stochastic Simulation",
              "Interactive Data Analysis",
              "An Introduction to R"),
    other.author = c(NA, "Ripley", NA, NA, NA, NA,
                     "Venables & Smith"))

(m0 <- merge(authorN, books))

      name nationality deceased                         title other.author
1   McNeil   Australia       no     Interactive Data Analysis         <NA>
2   Ripley          UK       no            Spatial Statistics         <NA>
3   Ripley          UK       no         Stochastic Simulation         <NA>
4  Tierney          US       no                     LISP-STAT         <NA>
5    Tukey          US      yes     Exploratory Data Analysis         <NA>
6 Venables   Australia       no Modern Applied Statistics ...       Ripley

(m1 <- merge(authors, books, by.x = "surname", by.y = "name"))

   surname nationality deceased                         title other.author
1   McNeil   Australia       no     Interactive Data Analysis         <NA>
2   Ripley          UK       no            Spatial Statistics         <NA>
3   Ripley          UK       no         Stochastic Simulation         <NA>
4  Tierney          US       no                     LISP-STAT         <NA>
5    Tukey          US      yes     Exploratory Data Analysis         <NA>
6 Venables   Australia       no Modern Applied Statistics ...       Ripley

 m2 <- merge(books, authors, by.x = "name", by.y = "surname")
stopifnot(exprs = {
   identical(m0, m2[, names(m0)])
   as.character(m1[, 1]) == as.character(m2[, 1])
   all.equal(m1[, -1], m2[, -1][ names(m1)[-1] ])
   identical(dim(merge(m1, m2, by = NULL)),
             c(nrow(m1)*nrow(m2), ncol(m1)+ncol(m2)))
})

## "R core" is missing from authors and appears only here :
merge(authors, books, by.x = "surname", by.y = "name", all = TRUE)

   surname nationality deceased                         title     other.author
1   McNeil   Australia       no     Interactive Data Analysis             <NA>
2   R Core        <NA>     <NA>          An Introduction to R Venables & Smith
3   Ripley          UK       no            Spatial Statistics             <NA>
4   Ripley          UK       no         Stochastic Simulation             <NA>
5  Tierney          US       no                     LISP-STAT             <NA>
6    Tukey          US      yes     Exploratory Data Analysis             <NA>
7 Venables   Australia       no Modern Applied Statistics ...           Ripley

## example of using 'incomparables'
x <- data.frame(k1 = c(NA,NA,3,4,5), k2 = c(1,NA,NA,4,5), data = 1:5)
y <- data.frame(k1 = c(NA,2,NA,4,5), k2 = c(NA,NA,3,4,5), data = 1:5)
merge(x, y, by = c("k1","k2")) # NA's match

  k1 k2 data.x data.y
1  4  4      4      4
2  5  5      5      5
3 NA NA      2      1

merge(x, y, by = "k1") # NA's match, so 6 rows

  k1 k2.x data.x k2.y data.y
1  4    4      4    4      4
2  5    5      5    5      5
3 NA    1      1   NA      1
4 NA    1      1    3      3
5 NA   NA      2   NA      1
6 NA   NA      2    3      3

merge(x, y, by = "k2", incomparables = NA) # 2 rows

  k2 k1.x data.x k1.y data.y
1  4    4      4    4      4
2  5    5      5    5      5

Examples for 'base::merge'

Merge Two Data Frames