bit64 (version 4.8.4)

hashmap: Hashing for 64bit integers

Description

This is an explicit implementation of hash functionality that underlies matching and other functions in R. Explicit means that you can create, store and use hash functionality directly. One advantage is that you can re-use hashmaps, which avoid re-building hashmaps again and again.

Usage

hashfun(x, ...)
# S3 method for integer64
hashfun(x, minfac = 1.41, hashbits = NULL, ...)
hashmap(x, ...)
# S3 method for integer64
hashmap(x, nunique = NULL, minfac = 1.41, hashbits = NULL, cache = NULL, ...)
hashpos(cache, ...)
# S3 method for cache_integer64
hashpos(cache, x, nomatch = NA_integer_, ...)
hashrev(cache, ...)
# S3 method for cache_integer64
hashrev(cache, x, nomatch = NA_integer_, ...)
hashfin(cache, ...)
# S3 method for cache_integer64
hashfin(cache, x, ...)
hashrin(cache, ...)
# S3 method for cache_integer64
hashrin(cache, x, ...)
hashdup(cache, ...)
# S3 method for cache_integer64
hashdup(cache, ...)
hashuni(cache, ...)
# S3 method for cache_integer64
hashuni(cache, keep.order = FALSE, ...)
hashupo(cache, ...)
# S3 method for cache_integer64
hashupo(cache, keep.order = FALSE, ...)
hashtab(cache, ...)
# S3 method for cache_integer64
hashtab(cache, ...)
hashmaptab(x, ...)
# S3 method for integer64
hashmaptab(x, nunique = NULL, minfac = 1.5, hashbits = NULL, ...)
hashmapuni(x, ...)
# S3 method for integer64
hashmapuni(x, nunique = NULL, minfac = 1.5, hashbits = NULL, ...)
hashmapupo(x, ...)
# S3 method for integer64
hashmapupo(x, nunique = NULL, minfac = 1.5, hashbits = NULL, ...)

Value

See Details

Details

function	see also	description
hashfun	digest	export of the hash function used in hashmap
hashmap	match()	return hashmap
hashpos	match()	return positions of x in hashmap
hashrev	match()	return positions of hashmap in x
hashfin	%in%.integer64	return logical whether x is in hashmap
hashrin	%in%.integer64	return logical whether hashmap is in x
hashdup	duplicated()	return logical whether hashdat is duplicated using hashmap
hashuni	unique()	return unique values of hashmap
hashmapuni	unique()	return unique values of x
hashupo	unique()	return positions of unique values in hashdat
hashmapupo	unique()	return positions of unique values in x
hashtab	table()	tabulate values of hashdat using hashmap in keep.order=FALSE
hashmaptab	table()	tabulate values of x building hasmap on the fly in keep.order=FALSE

See Also

match(), runif64()

Examples

x <- as.integer64(sample(c(NA, 0:9)))
y <- as.integer64(sample(c(NA, 1:9), 10, TRUE))
hashfun(y)
hx <- hashmap(x)
hy <- hashmap(y)
ls(hy)
hashpos(hy, x)
hashrev(hx, y)
hashfin(hy, x)
hashrin(hx, y)
hashdup(hy)
hashuni(hy)
hashuni(hy, keep.order=TRUE)
hashmapuni(y)
hashupo(hy)
hashupo(hy, keep.order=TRUE)
hashmapupo(y)
hashtab(hy)
hashmaptab(y)

    if (FALSE) {
    message("explore speed given size of the hasmap in 2^hashbits and size of the data")
    message("more hashbits means more random access and less collisions")
    message("i.e. more data means less random access and more collisions")
    bits <- 24
    b <- seq(-1, 0, 0.1)
    tim <- matrix(NA, length(b), 2, dimnames=list(b, c("bits", "bits+1")))
    for (i in 1:length(b)) {
      n <- as.integer(2^(bits+b[i]))
      x <- as.integer64(sample(n))
      tim[i, 1] <- repeat.time(hashmap(x, hashbits=bits))[3]
      tim[i, 2] <- repeat.time(hashmap(x, hashbits=bits+1))[3]
      print(tim)
      matplot(b, tim)
    }
    message("we conclude that n*sqrt(2) is enough to avoid collisions")
    }