```
# NOT RUN {
message("Using integer64 in vector")
x <- integer64(8) # create 64 bit vector
x
is.atomic(x) # TRUE
is.integer64(x) # TRUE
is.numeric(x) # TRUE
is.integer(x) # FALSE - debatable
is.double(x) # FALSE - might change
x[] <- 1:2 # assigned value is recycled as usual
x[1:6] # subscripting as usual
length(x) <- 13 # changing length as usual
x
rep(x, 2) # replicate as usual
seq(as.integer64(1), 10) # seq.integer64 is dispatched on first given argument
seq(to=as.integer64(10), 1) # seq.integer64 is dispatched on first given argument
seq.integer64(along.with=x) # or call seq.integer64 directly
# c.integer64 is dispatched only if *first* argument is integer64 ...
x <- c(x,runif(length(x), max=100))
# ... and coerces everything to integer64 - including double
x
names(x) <- letters # use names as usual
x
message("Using integer64 in array - note that 'matrix' currently does not work")
message("as.vector.integer64 removed as requested by the CRAN maintainer")
message("as consequence 'array' also does not work anymore")
# }
# NOT RUN {
<!-- %y <- array(as.integer64(NA), dim=c(3,4), dimnames=list(letters[1:3], LETTERS[1:4])) -->
# }
# NOT RUN {
message("we still can create a matrix or array by assigning 'dim'")
y <- rep(as.integer64(NA), 12)
dim(y) <- c(3,4)
dimnames(y) <- list(letters[1:3], LETTERS[1:4])
y["a",] <- 1:2 # assigning as usual
y
y[1:2,-4] # subscripting as usual
# cbind.integer64 dispatched on any argument and coerces everything to integer64
cbind(E=1:3, F=runif(3, 0, 100), G=c("-1","0","1"), y)
message("Using integer64 in data.frame")
str(as.data.frame(x))
str(as.data.frame(y))
str(data.frame(y))
str(data.frame(I(y)))
d <- data.frame(x=x, y=runif(length(x), 0, 100))
d
d$x
message("Using integer64 with csv files")
fi64 <- tempfile()
write.csv(d, file=fi64, row.names=FALSE)
e <- read.csv(fi64, colClasses=c("integer64", NA))
unlink(fi64)
str(e)
identical.integer64(d$x,e$x)
message("Serializing and unserializing integer64")
dput(d, fi64)
e <- dget(fi64)
identical.integer64(d$x,e$x)
e <- d[,]
save(e, file=fi64)
rm(e)
load(file=fi64)
identical.integer64(d,e)
### A couple of unit tests follow hidden in a dontshow{} directive ###
# }
# NOT RUN {
# }
# NOT RUN {
message("== Differences between integer64 and int64 ==")
require(bit64)
require(int64)
message("-- integer64 is atomic --")
is.atomic(integer64())
#is.atomic(int64())
str(integer64(3))
#str(int64(3))
message("-- The following performance numbers are measured under RWin64 --")
message("-- under RWin32 the advantage of integer64 over int64 is smaller --")
message("-- integer64 needs 7x/5x less RAM than int64 under 64/32 bit OS
(and twice the RAM of integer as it should be) --")
#as.vector(object.size(int64(1e6))/object.size(integer64(1e6)))
as.vector(object.size(integer64(1e6))/object.size(integer(1e6)))
message("-- integer64 creates 2000x/1300x faster than int64 under 64/32 bit OS
(and 3x the time of integer) --")
t32 <- system.time(integer(1e8))
t64 <- system.time(integer64(1e8))
#T64 <- system.time(int64(1e7))*10 # using 1e8 as above stalls our R on an i7 8 GB RAM Thinkpad
#T64/t64
t64/t32
i32 <- sample(1e6)
d64 <- as.double(i32)
message("-- the following timings are rather conservative since timings
of integer64 include garbage collection -- due to looped calls")
message("-- integer64 coerces 900x/100x faster than int64
under 64/32 bit OS (and 2x the time of coercing to integer) --")
t32 <- system.time(for(i in 1:1000)as.integer(d64))
t64 <- system.time(for(i in 1:1000)as.integer64(d64))
#T64 <- system.time(as.int64(d64))*1000
#T64/t64
t64/t32
td64 <- system.time(for(i in 1:1000)as.double(i32))
t64 <- system.time(for(i in 1:1000)as.integer64(i32))
#T64 <- system.time(for(i in 1:10)as.int64(i32))*100
#T64/t64
t64/td64
message("-- integer64 serializes 4x/0.8x faster than int64
under 64/32 bit OS (and less than 2x/6x the time of integer or double) --")
t32 <- system.time(for(i in 1:10)serialize(i32, NULL))
td64 <- system.time(for(i in 1:10)serialize(d64, NULL))
i64 <- as.integer64(i32);
t64 <- system.time(for(i in 1:10)serialize(i64, NULL))
rm(i64); gc()
#I64 <- as.int64(i32);
#T64 <- system.time(for(i in 1:10)serialize(I64, NULL))
#rm(I64); gc()
#T64/t64
t64/t32
t64/td64
message("-- integer64 adds 250x/60x faster than int64
under 64/32 bit OS (and less than 6x the time of integer or double) --")
td64 <- system.time(for(i in 1:100)d64+d64)
t32 <- system.time(for(i in 1:100)i32+i32)
i64 <- as.integer64(i32);
t64 <- system.time(for(i in 1:100)i64+i64)
rm(i64); gc()
#I64 <- as.int64(i32);
#T64 <- system.time(for(i in 1:10)I64+I64)*10
#rm(I64); gc()
#T64/t64
t64/t32
t64/td64
message("-- integer64 sums 3x/0.2x faster than int64
(and at about 5x/60X the time of integer and double) --")
td64 <- system.time(for(i in 1:100)sum(d64))
t32 <- system.time(for(i in 1:100)sum(i32))
i64 <- as.integer64(i32);
t64 <- system.time(for(i in 1:100)sum(i64))
rm(i64); gc()
#I64 <- as.int64(i32);
#T64 <- system.time(for(i in 1:100)sum(I64))
#rm(I64); gc()
#T64/t64
t64/t32
t64/td64
message("-- integer64 diffs 5x/0.85x faster than integer and double
(int64 version 1.0 does not support diff) --")
td64 <- system.time(for(i in 1:10)diff(d64, lag=2L, differences=2L))
t32 <- system.time(for(i in 1:10)diff(i32, lag=2L, differences=2L))
i64 <- as.integer64(i32);
t64 <- system.time(for(i in 1:10)diff(i64, lag=2L, differences=2L))
rm(i64); gc()
t64/t32
t64/td64
message("-- integer64 subscripts 1000x/340x faster than int64
(and at the same speed / 10x slower as integer) --")
ts32 <- system.time(for(i in 1:1000)sample(1e6, 1e3))
t32<- system.time(for(i in 1:1000)i32[sample(1e6, 1e3)])
i64 <- as.integer64(i32);
t64 <- system.time(for(i in 1:1000)i64[sample(1e6, 1e3)])
rm(i64); gc()
#I64 <- as.int64(i32);
#T64 <- system.time(for(i in 1:100)I64[sample(1e6, 1e3)])*10
#rm(I64); gc()
#(T64-ts32)/(t64-ts32)
(t64-ts32)/(t32-ts32)
message("-- integer64 assigns 200x/90x faster than int64
(and 50x/160x slower than integer) --")
ts32 <- system.time(for(i in 1:100)sample(1e6, 1e3))
t32 <- system.time(for(i in 1:100)i32[sample(1e6, 1e3)] <- 1:1e3)
i64 <- as.integer64(i32);
i64 <- system.time(for(i in 1:100)i64[sample(1e6, 1e3)] <- 1:1e3)
rm(i64); gc()
#I64 <- as.int64(i32);
#I64 <- system.time(for(i in 1:10)I64[sample(1e6, 1e3)] <- 1:1e3)*10
#rm(I64); gc()
#(T64-ts32)/(t64-ts32)
(t64-ts32)/(t32-ts32)
tdfi32 <- system.time(dfi32 <- data.frame(a=i32, b=i32, c=i32))
tdfsi32 <- system.time(dfi32[1e6:1,])
fi32 <- tempfile()
tdfwi32 <- system.time(write.csv(dfi32, file=fi32, row.names=FALSE))
tdfri32 <- system.time(read.csv(fi32, colClasses=rep("integer", 3)))
unlink(fi32)
rm(dfi32); gc()
i64 <- as.integer64(i32);
tdfi64 <- system.time(dfi64 <- data.frame(a=i64, b=i64, c=i64))
tdfsi64 <- system.time(dfi64[1e6:1,])
fi64 <- tempfile()
tdfwi64 <- system.time(write.csv(dfi64, file=fi64, row.names=FALSE))
tdfri64 <- system.time(read.csv(fi64, colClasses=rep("integer64", 3)))
unlink(fi64)
rm(i64, dfi64); gc()
#I64 <- as.int64(i32);
#tdfI64 <- system.time(dfI64<-data.frame(a=I64, b=I64, c=I64))
#tdfsI64 <- system.time(dfI64[1e6:1,])
#fI64 <- tempfile()
#tdfwI64 <- system.time(write.csv(dfI64, file=fI64, row.names=FALSE))
#tdfrI64 <- system.time(read.csv(fI64, colClasses=rep("int64", 3)))
#unlink(fI64)
#rm(I64, dfI64); gc()
message("-- integer64 coerces 40x/6x faster to data.frame than int64
(and factor 1/9 slower than integer) --")
#tdfI64/tdfi64
tdfi64/tdfi32
message("-- integer64 subscripts from data.frame 20x/2.5x faster than int64
(and 3x/13x slower than integer) --")
#tdfsI64/tdfsi64
tdfsi64/tdfsi32
message("-- integer64 csv writes about 2x/0.5x faster than int64
(and about 1.5x/5x slower than integer) --")
#tdfwI64/tdfwi64
tdfwi64/tdfwi32
message("-- integer64 csv reads about 3x/1.5 faster than int64
(and about 2x slower than integer) --")
#tdfrI64/tdfri64
tdfri64/tdfri32
rm(i32, d64); gc()
message("-- investigating the impact on garbage collection: --")
message("-- the fragmented structure of int64 messes up R's RAM --")
message("-- and slows down R's gargbage collection just by existing --")
td32 <- double(21)
td32[1] <- system.time(d64 <- double(1e7))[3]
for (i in 2:11)td32[i] <- system.time(gc(), gcFirst=FALSE)[3]
rm(d64)
for (i in 12:21)td32[i] <- system.time(gc(), gcFirst=FALSE)[3]
t64 <- double(21)
t64[1] <- system.time(i64 <- integer64(1e7))[3]
for (i in 2:11)t64[i] <- system.time(gc(), gcFirst=FALSE)[3]
rm(i64)
for (i in 12:21)t64[i] <- system.time(gc(), gcFirst=FALSE)[3]
#T64 <- double(21)
#T64[1] <- system.time(I64 <- int64(1e7))[3]
#for (i in 2:11)T64[i] <- system.time(gc(), gcFirst=FALSE)[3]
#rm(I64)
#for (i in 12:21)T64[i] <- system.time(gc(), gcFirst=FALSE)[3]
#matplot(1:21, cbind(td32, t64, T64), pch=c("d","i","I"), log="y")
matplot(1:21, cbind(td32, t64), pch=c("d","i"), log="y")
# }
# NOT RUN {
# }
```

Run the code above in your browser using DataCamp Workspace