data.table下
DT[ i, j, by ] # + extra arguments
| | |
| | -------> grouped by what?
| -------> what to do?
---> on which rows?
X[, a] # return col 'a' from X as vector. If not found, search in parent frame.
X[, .(a)] # same as above, but return as a data.table.
X[, sum(a)] # return sum(a) as a vector (with same scoping rules as above)
X[, .(sum(a)), by=c] # get sum(a) grouped by 'c'.
X[, sum(a), by=c] # same as above, .() can be ommitt
ed in by on single expression for convenience
X[, sum(a), by=c:f] # get sum(a) grouped by all columns in between 'c' and 'f' (both inclusive)
X[, sum(a), keyby=b] # get sum(a) grouped by 'b', and sort that result by the grouping column 'b'
X[, sum(a), by=b][order(b)] # same order as above, but by chaining compound expressions
X[c>1, sum(a), by=c] # get rows where c>1 is TRUE, and on those rows, get sum(a) grouped by 'c'
X[Y, .(a, b), on="c"] # get rows where Y$c == X$c, and select columns 'X$a' and 'X$b' for those rows
X[Y, .(a, i.a), on="c"] # get rows where Y$c == X$c, and then select 'X$a' and 'Y$a' (=i.a)
X[Y, sum(a*i.a), on="c" by=.EACHI] # for *each* 'Y$c', get sum(a*i.a) on matching rows in 'X$c'
X[, plot(a, b), by=c] # j accepts any expression, generates plot for each group and returns no data
# see ?assign to add/update/delete columns by reference using the same consistent interface
