public
Last active

  • Download Gist
MERGE.R
R
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143
MERGE <- function (x, y, by = intersect(names(x), names(y)), by.x = by,
by.y = by, all = FALSE, all.x = all, all.y = all, sort = TRUE,
suffixes = c(".x", ".y"), incomparables = NULL, ...)
{
fix.by <- function(by, df) {
if (is.null(by))
by <- numeric()
by <- as.vector(by)
nc <- ncol(df)
if (is.character(by)) {
poss <- c("row.names", names(df))
if (any(!charmatch(by, poss, 0L)))
stop("'by' must specify uniquely valid column(s)")
by <- match(by, poss) - 1L
}
else if (is.numeric(by)) {
if (any(by < 0L) || any(by > nc))
stop("'by' must match numbers of columns")
}
else if (is.logical(by)) {
if (length(by) != nc)
stop("'by' must match number of columns")
by <- seq_along(by)[by]
}
else stop("'by' must specify column(s) as numbers, names or logical")
if (any(is.na(by)))
stop("'by' must specify valid column(s)")
unique(by)
}
nx <- nrow(x <- as.data.frame(x))
ny <- nrow(y <- as.data.frame(y))
by.x <- fix.by(by.x, x)
by.y <- fix.by(by.y, y)
if ((l.b <- length(by.x)) != length(by.y))
stop("'by.x' and 'by.y' specify different numbers of columns")
if (l.b == 0L) {
nm <- nm.x <- names(x)
nm.y <- names(y)
has.common.nms <- any(cnm <- nm.x %in% nm.y)
if (has.common.nms) {
names(x)[cnm] <- paste0(nm.x[cnm], suffixes[1L])
cnm <- nm.y %in% nm
names(y)[cnm] <- paste0(nm.y[cnm], suffixes[2L])
}
if (nx == 0L || ny == 0L) {
res <- cbind(x[FALSE, ], y[FALSE, ])
}
else {
ij <- expand.grid(seq_len(nx), seq_len(ny))
res <- cbind(x[ij[, 1L], , drop = FALSE], y[ij[,
2L], , drop = FALSE])
}
}
else {
if (any(by.x == 0L)) {
x <- cbind(Row.names = I(row.names(x)), x)
by.x <- by.x + 1L
}
if (any(by.y == 0L)) {
y <- cbind(Row.names = I(row.names(y)), y)
by.y <- by.y + 1L
}
# row.names(x) <- NULL
# row.names(y) <- NULL
if (l.b == 1L) {
bx <- x[, by.x]
if (is.factor(bx))
bx <- as.character(bx)
by <- y[, by.y]
if (is.factor(by))
by <- as.character(by)
}
else {
bx <- x[, by.x, drop = FALSE]
by <- y[, by.y, drop = FALSE]
names(bx) <- names(by) <- paste0("V", seq_len(ncol(bx)))
bz <- do.call("paste", c(rbind(bx, by), sep = "\r"))
bx <- bz[seq_len(nx)]
by <- bz[nx + seq_len(ny)]
}
comm <- match(bx, by, 0L)
bxy <- bx[comm > 0L]
xinds <- match(bx, bxy, 0L, incomparables)
yinds <- match(by, bxy, 0L, incomparables)
if (nx > 0L && ny > 0L)
m <- .Internal(merge(xinds, yinds, all.x, all.y))
else m <- list(xi = integer(), yi = integer(), x.alone = seq_len(nx),
y.alone = seq_len(ny))
nm <- nm.x <- names(x)[-by.x]
nm.by <- names(x)[by.x]
nm.y <- names(y)[-by.y]
ncx <- ncol(x)
if (all.x)
all.x <- (nxx <- length(m$x.alone)) > 0L
if (all.y)
all.y <- (nyy <- length(m$y.alone)) > 0L
lxy <- length(m$xi)
has.common.nms <- any(cnm <- nm.x %in% nm.y)
if (has.common.nms && nzchar(suffixes[1L]))
nm.x[cnm] <- paste0(nm.x[cnm], suffixes[1L])
x <- x[c(m$xi, if (all.x) m$x.alone), c(by.x, seq_len(ncx)[-by.x]),
drop = FALSE]
names(x) <- c(nm.by, nm.x)
if (all.y) {
ya <- y[m$y.alone, by.y, drop = FALSE]
names(ya) <- nm.by
ya <- cbind(ya, x[rep.int(NA_integer_, nyy), nm.x,
drop = FALSE])
x <- rbind(x, ya)
}
if (has.common.nms && nzchar(suffixes[2L])) {
cnm <- nm.y %in% nm
nm.y[cnm] <- paste0(nm.y[cnm], suffixes[2L])
}
y <- y[c(m$yi, if (all.x) rep.int(1L, nxx), if (all.y) m$y.alone),
-by.y, drop = FALSE]
if (all.x) {
zap <- (lxy + 1L):(lxy + nxx)
for (i in seq_along(y)) {
if (is.matrix(y[[1]]))
y[[1]][zap, ] <- NA
else is.na(y[[i]]) <- zap
}
}
if (has.common.nms)
names(y) <- nm.y
nm <- c(names(x), names(y))
if (any(d <- duplicated(nm)))
if (sum(d) > 1L)
warning("column names ", paste(sQuote(nm[d]),
collapse = ", "), " are duplicated in the result",
domain = NA)
else warning("column name ", sQuote(nm[d]), " is duplicated in the result",
domain = NA)
res <- cbind(x, y)
if (sort)
res <- res[if (all.x || all.y)
do.call("order", x[, seq_len(l.b), drop = FALSE])
else sort.list(bx[m$xi]), , drop = FALSE]
}
# attr(res, "row.names") <- .set_row_names(nrow(res))
res
}

Please sign in to comment on this gist.

Something went wrong with that request. Please try again.