R数据表：当前测量前的计数

我有一套在几天内进行的测量。测量次数通常为4次。可以在任何测量中捕获的数字范围为1-5（在现实生活中，给定测试集，该范围可能高达100或低至20）

我想每天计算在当前日期之前每个值发生了多少次

让我用一些样本数据解释一下：

# test data creation
d1 = list(as.Date("2013-5-4"),  4,2)
d2 = list(as.Date("2013-5-9"),  2,5)
d3 = list(as.Date("2013-5-16"), 3,2)
d4 = list(as.Date("2013-5-30"), 1,4)

d = rbind(d1,d2,d3,d4)
colnames(d) <- c("Date", "V1", "V2")

tt = as.data.table(d)

---

您可能需要%运算符中的

%

> foo<-sample(1:10,4)
> bar<-sample(1:10,3)
> foo
[1] 5 3 9 6
> bar
[1] 1 7 2
> bar2<-sample(1:10,5)
> bar2
[1] 2 9 4 8 5
> which(bar2%in%foo)
[1] 2 5   #those are the indices of the values in bar2 which appear in foo

> which(bar%in%foo)
 integer(0)

>foo bar foo
[1] 5 3 9 6
>酒吧
[1] 1 7 2
>bar2 bar2
[1] 2 9 4 8 5
>其中（bar2%在%foo中）
[1] 2 5#这些是bar2中出现在foo中的值的索引
>其中（条形图%foo中的%foo）
整数（0）
这是一个开始。我看不出有什么理由“一炮打响”。这是可能的。试试你自己

library(data.table)
DT = as.data.table(d)

DT[,i:=as.numeric(Date)]
setkey(DT,"i")

uv <- 1:max(unlist(DT[,2:3]))
DT[,paste0("C",uv):=lapply(uv,function(x) x %in% unlist(.SD)),.SDcols=2:3,by=i]
DT[,paste0("C",uv):=lapply(.SD,function(x) c(NA,head(cumsum(x),-1))),.SDcols=paste0("C",uv)]
DT[,paste0("PC",uv):=lapply(.SD,function(x) x/(2*.I-2)),.SDcols=paste0("C",uv)]

#          Date V1 V2     i C1 C2 C3 C4 C5 PC1 PC2       PC3       PC4       PC5
# 1: 2013-05-04  4  2 15829 NA NA NA NA NA  NA  NA        NA        NA        NA
# 2: 2013-05-09  2  5 15834  0  1  0  1  0   0 0.5 0.0000000 0.5000000 0.0000000
# 3: 2013-05-16  3  2 15841  0  2  0  1  1   0 0.5 0.0000000 0.2500000 0.2500000
# 4: 2013-05-30  1  4 15855  0  3  1  1  1   0 0.5 0.1666667 0.1666667 0.1666667

库（data.table）
DT=表（d）中的原始数据
DT[，i:=作为数字（日期）]
设置键（DT，“i”）
紫外线1。数据表

首先，将问题中的
t
的奇怪结构替换为更常见的结构：

library(data.table)
t <- data.table(
  Date = as.Date(c("2013-5-4", "2013-5-9", "2013-5-16", "2013-5-30")),
  V1 = c(4, 2, 3, 1),
  V2 = c(2, 5, 2, 4)
)

最后一行给出：

         Date V1 V2 C1 PC1 C2 PC2 C3       PC3 C4       PC4 C5       PC5
1: 2013-05-04  4  2  0 NaN  0 NaN  0       NaN  0       NaN  0       NaN
2: 2013-05-09  2  5  0   0  1 0.5  0 0.0000000  1 0.5000000  0 0.0000000
3: 2013-05-16  3  2  0   0  2 0.5  0 0.0000000  1 0.2500000  1 0.2500000
4: 2013-05-30  1  4  0   0  3 0.5  1 0.1666667  1 0.1666667  1 0.1666667

1a.data.table备选方案

如果可以省略第一个日期的行（这不是很有用，因为在第一个日期之前没有日期），那么我们可以执行以下繁琐但直接的自联接：

t <- data.table(
  Date = as.Date(c("2013-5-4", "2013-5-9", "2013-5-16", "2013-5-30")),
  V1 = c(4, 2, 3, 1),
  V2 = c(2, 5, 2, 4)
)
tt <- t[, one := 1]
setkey(tt, one)
tt[tt,,allow.cartesian=TRUE][Date > Date.1, list(
    C1 = sum(.SD == 1), PC1 = mean(.SD == 1), 
    C2 = sum(.SD == 2), PC2 = mean(.SD == 2), 
    C3 = sum(.SD == 3), PC3 = mean(.SD == 3), 
    C4 = sum(.SD == 4), PC4 = mean(.SD == 4), 
    C5 = sum(.SD == 5), PC5 = mean(.SD == 5)
), by = list(Date, V1, V2), .SDcols = c("V1.1", "V2.1")]

2。sqldf

data.table的另一种替代方法是使用SQL进行类似的繁琐但直接的自连接：

library(sqldf)
sqldf("select a.Date, a.V1, a.V2, 
sum(((b.V1 = 1) + (b.V2 = 1)) * (a.Date > b.Date)) C1,
sum(((b.V1 = 1) + (b.V2 = 1)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC1,
sum(((b.V1 = 2) + (b.V2 = 2)) * (a.Date > b.Date)) C2,
sum(((b.V1 = 2) + (b.V2 = 2)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC2,
sum(((b.V1 = 3) + (b.V2 = 3)) * (a.Date > b.Date)) C3,
sum(((b.V1 = 3) + (b.V2 = 3)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC3,
sum(((b.V1 = 4) + (b.V2 = 4)) * (a.Date > b.Date)) C4,
sum(((b.V1 = 4) + (b.V2 = 4)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC4,
sum(((b.V1 = 5) + (b.V2 = 5)) * (a.Date > b.Date)) C5,
sum(((b.V1 = 5) + (b.V2 = 5)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC5
from t a, t b where a.Date >= b.Date
group by a.Date")

2a。sqldf备选方案

另一种方法是使用字符串操作创建上述sql字符串，如下所示：

f <- function(i) {
    s <- fn$identity("sum(((b.V1 = $i) + (b.V2 = $i)) * (a.Date > b.Date))")
    fn$identity("$s C$i,\n $s /\ncast (2 * count(*) - 2 as real) PC$i")
}
s <- fn$identity("select a.Date, a.V1, a.V2, `toString(sapply(1:5, f))`
    from t a, t b where a.Date >= b.Date
    group by a.Date")

sqldf(s)

同样，可以创建sql字符串，以避免以与前面的解决方案相同的方式进行重复

更新：增加了PC列和一些简化

更新2：添加其他解决方案
我喜欢初始解决方案，因为它将所有原始数据和新分析数据一起提供给我（即使第一行是垃圾数据）。我正在努力理解它如何只考虑“当前”行和“之后”（而不是“之前”）的每一行。第一个解决方案似乎深入到了多层作业中，这是一种有趣的方法。我想尝试一下，但它会返回错误。1. '上述代码中未定义d'DT[，paste0（“PC”，uv）：=lappy（.SD，函数（x）x/（2*.I-2）），.SDcols=paste0（“C”，uv）]在
[.data.frame
（DT，
：=
（paste0（“PC”，uv），lappy（.SD，函数（x）x/（2*）：未使用的参数（.SDcols=paste0（“C”，uv））
头（x，-1）
删除x的最后一行/位置。我在第一个位置添加NA以获得正确长度的向量。
tt[tt,,allow.cartesian=TRUE][Date > Date.1, setNames(as.list(rbind(
   sapply(1:n, function(i, .SD) sum(.SD==i), .SD=.SD),
   sapply(1:n, function(i, .SD) mean(.SD==i), .SD=.SD)
  )), c(rbind(Cnames, PCnames))),
  by = list(Date, V1, V2), .SDcols = c("V1.1", "V2.1")]

library(sqldf)
sqldf("select a.Date, a.V1, a.V2, 
sum(((b.V1 = 1) + (b.V2 = 1)) * (a.Date > b.Date)) C1,
sum(((b.V1 = 1) + (b.V2 = 1)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC1,
sum(((b.V1 = 2) + (b.V2 = 2)) * (a.Date > b.Date)) C2,
sum(((b.V1 = 2) + (b.V2 = 2)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC2,
sum(((b.V1 = 3) + (b.V2 = 3)) * (a.Date > b.Date)) C3,
sum(((b.V1 = 3) + (b.V2 = 3)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC3,
sum(((b.V1 = 4) + (b.V2 = 4)) * (a.Date > b.Date)) C4,
sum(((b.V1 = 4) + (b.V2 = 4)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC4,
sum(((b.V1 = 5) + (b.V2 = 5)) * (a.Date > b.Date)) C5,
sum(((b.V1 = 5) + (b.V2 = 5)) * (a.Date > b.Date)) / 
cast (2 * count(*) - 2 as real) PC5
from t a, t b where a.Date >= b.Date
group by a.Date")

f <- function(i) {
    s <- fn$identity("sum(((b.V1 = $i) + (b.V2 = $i)) * (a.Date > b.Date))")
    fn$identity("$s C$i,\n $s /\ncast (2 * count(*) - 2 as real) PC$i")
}
s <- fn$identity("select a.Date, a.V1, a.V2, `toString(sapply(1:5, f))`
    from t a, t b where a.Date >= b.Date
    group by a.Date")

sqldf(s)

sqldf("select a.Date, a.V1, a.V2, 
sum((b.V1 = 1) + (b.V2 = 1)) C1,
avg((b.V1 = 1) + (b.V2 = 1)) PC1,
sum((b.V1 = 2) + (b.V2 = 2)) C2,
avg((b.V1 = 2) + (b.V2 = 2)) PC2,
sum((b.V1 = 3) + (b.V2 = 3)) C3,
avg((b.V1 = 3) + (b.V2 = 3)) PC3,
sum((b.V1 = 4) + (b.V2 = 4)) C4,
avg((b.V1 = 4) + (b.V2 = 4)) PC4,
sum((b.V1 = 5) + (b.V2 = 5)) C5,
avg((b.V1 = 5) + (b.V2 = 5)) PC5
from t a, t b where a.Date > b.Date
group by a.Date")