Question

这个问题可能已在SO中得到解决和回答，但无法找到答案。我计算了非常大的数据帧上的条件的累积和。请看下面的例子

Data=data.frame("Catg"=c("A","A","A","A","A","B","B","B","C","C","C","D","D","D","D","D","D","D","D","E","E","F"),"Val"=c(67,42,12,32,28,1,11,9,38,61,75,99,22,44,89,99,51,34,82,99,74,42))
Res=NULL
UniqCatg=unique(Data$Catg)
for(i in 1:length(UniqCatg))
    Res=c(Res, cumsum(Data[Data$Catg==UniqCatg[i],"Val"]))
Data$Res=Res
Data

是否有一种聪明的方法可以在没有for循环的情况下完成它？（比如应用功能）

Answer 1

您可以使用ave：

Data$Res <- ave(Data$Val, Data$Catg, FUN=cumsum)
#   Catg Val Res
#1     A  67  67
#2     A  42 109
#3     A  12 121
#4     A  32 153
#5     A  28 181
#6     B   1   1
#7     B  11  12
#8     B   9  21
#9     C  38  38
#10    C  61  99
#11    C  75 174
#12    D  99  99
#13    D  22 121
#14    D  44 165
#15    D  89 254
#16    D  99 353
#17    D  51 404
#18    D  34 438
#19    D  82 520
#20    E  99  99
#21    E  74 173
#22    F  42  42

Answer 2

或plyr::ddply ...

require( plyr )
ddply( Data , "Catg" , transform , Res = cumsum(Val) )
#   Catg Val Res
#1     A  67  67
#2     A  42 109
#3     A  12 121
#4     A  32 153
#5     A  28 181
#6     B   1   1
#7     B  11  12
#8     B   9  21
#9     C  38  38
#10    C  61  99
#11    C  75 174
#12    D  99  99
#13    D  22 121
#14    D  44 165
#15    D  89 254
#16    D  99 353
#17    D  51 404
#18    D  34 438
#19    D  82 520
#20    E  99  99
#21    E  74 173
#22    F  42  42

R中的应用函数的条件累积和

2 个答案: