## Not run:
# example(data.table) # to run these examples at the prompt## End(Not run)
DF = data.frame(x=rep(c("a","b","c"),each=3), y=c(1,3,6), v=1:9)
DT = data.table(x=rep(c("a","b","c"),each=3), y=c(1,3,6), v=1:9)
DF
DT
identical(dim(DT),dim(DF)) # TRUE
identical(DF$a, DT$a) # TRUE
is.list(DF) # TRUE
is.list(DT) # TRUE
is.data.frame(DT) # TRUE
tables()
DT[2] # 2nd row
DT[,v] # v column (as vector)
DT[,list(v)] # v column (as data.table)
DT[2:3,sum(v)] # sum(v) over rows 2 and 3
DT[2:5,cat(v,"\n")] # just for j's side effect
DT[c(FALSE,TRUE)] # even rows (usual recycling)
DT[,2,with=FALSE] # 2nd column
colNum = 2
DT[,colNum,with=FALSE] # same
setkey(DT,x) # set a 1-column key. No quotes, for convenience.
setkeyv(DT,"x") # same (v in setkeyv stands for vector)
v="x"
setkeyv(DT,v) # same
# key(DT)<-"x" # copies whole table, please use set* functions instead
DT["a"] # binary search (fast)
DT[x=="a"] # same; i.e. binary search (fast)
DT[,sum(v),by=x] # keyed by
DT[,sum(v),by=key(DT)] # same
DT[,sum(v),by=y] # ad hoc by
DT["a",sum(v)] # j for one group
DT[c("a","b"),sum(v),by=.EACHI] # j for two groups
X = data.table(c("b","c"),foo=c(4,2))
X
DT[X] # join
DT[X,sum(v),by=.EACHI] # join and eval j for each row in i
DT[X,mult="first"] # first row of each group
DT[X,mult="last"] # last row of each group
DT[X,sum(v)*foo,by=.EACHI] # join inherited scope
setkey(DT,x,y) # 2-column key
setkeyv(DT,c("x","y")) # same
DT["a"] # join to 1st column of key
DT[.("a")] # same, .() is an alias for list()
DT[list("a")] # same
DT[.("a",3)] # join to 2 columns
DT[.("a",3:6)] # join 4 rows (2 missing)
DT[.("a",3:6),nomatch=0] # remove missing
DT[.("a",3:6),roll=TRUE] # rolling join (locf)
DT[,sum(v),by=.(y%%2)] # by expression
DT[,.SD[2],by=x] # 2nd row of each group
DT[,tail(.SD,2),by=x] # last 2 rows of each group
DT[,lapply(.SD,sum),by=x] # apply through columns by group
DT[,list(MySum=sum(v),
MyMin=min(v),
MyMax=max(v)),
by=.(x,y%%2)] # by 2 expressions
DT[,sum(v),x][V1<20] # compound query
DT[,sum(v),x][order(-V1)] # ordering results
print(DT[,z:=42L]) # add new column by reference
print(DT[,z:=NULL]) # remove column by reference
print(DT["a",v:=42L]) # subassign to existing v column by reference
print(DT["b",v2:=84L]) # subassign to new column by reference (NA padded)
DT[,m:=mean(v),by=x][] # add new column by reference by group
# NB: postfix [] is shortcut to print()
DT[,.SD[which.min(v)],by=x][] # nested query by group
DT[!.("a")] # not join
DT[!"a"] # same
DT[!2:4] # all rows other than 2:4
DT[x!="b" | y!=3] # not yet optimized, currently vector scans
DT[!.("b",3)] # same result but much faster
# new feature: 'on' argument, from v1.9.6+
DT1 = data.table(x=c("c", "a", "b", "a", "b"), a=1:5)
DT2 = data.table(x=c("d", "c", "b"), mul=6:8)
DT1[DT2, on=c(x="x")] # join on columns 'x'
DT1[DT2, on="x"] # same as above
DT1[DT2, .(sum(a) * mul), by=.EACHI, on="x"] # using by=.EACHI
DT1[DT2, .(sum(a) * mul), by=.EACHI, on="x", nomatch=0L] # using by=.EACHI
# Follow r-help posting guide, support is here (*not* r-help) :
# http://stackoverflow.com/questions/tagged/data.table
# or
# datatable-help@lists.r-forge.r-project.org
## Not run:
# vignette("datatable-intro")
# vignette("datatable-faq")
#
# test.data.table() # over 1,300 low level tests
#
# update.packages() # keep up to date
# ## End(Not run)Run the code above in your browser using DataCamp Workspace