R：在时间间隔内计算日期

假设我们有数据输入：

df.in <- data.frame(event = c(1,2,3,4,5), 
                    start = c("2015-01-01", "2015-01-01", "2015-01-02",
                              "2015-01-02", "2015-01-03"),
                    end = c("2015-01-03", "2015-01-04", "2015-01-03",
                            "2015-01-05", "2015-01-05"))
df.in$start <- as.Date(df.in$start, "%Y-%m-%d")
df.in$end <- as.Date(df.in$end, "%Y-%m-%d")

> df.in
  event      start        end
1     1 2015-01-01 2015-01-03
2     2 2015-01-01 2015-01-04
3     3 2015-01-02 2015-01-03
4     4 2015-01-02 2015-01-05
5     5 2015-01-03 2015-01-05

因此，我目前的想法是一个循环：

for(i in seq_along(df.out$date)){
  temp.df <- df.in[df.in$start <= df.out$date[i],]
  df.out$count[i] <- nrow(temp.df) - nrow(temp.df[temp.df$end <= df.out$date[i],])
}
> df.out
        date count
1 2015-01-01     2
2 2015-01-02     4
3 2015-01-03     3
4 2015-01-04     2
5 2015-01-05     0

for（i在序列中沿（df.out$日期））{
temp.df所以我对
data.table:：foverlaps（）
做了研究。我将把我的发现留给任何可能会发现它有用的人，因为老实说，我在搜索类似帖子时并没有真正找到这些小东西

考虑到我们正在比较区间，并且区间仅在
y
参数上，即
df。在这个特殊情况下，我们必须人为地创建一个区间。就像
df.out$date2啊…所以我在搜索时又弄错了关键字。显然，我是在寻找“重叠”。谢谢！考虑到我对数据表软件包已经熟悉了整整一个小时，就我的知识而言，这些东西似乎有些复杂。不过，我将以你的例子进行一点实验，看看它会带来什么，非常感谢！我已经对你的答案进行了编辑（如果你不介意的话），以说明我的评论。
#1 **
#2 ****
#3 ***
#4 **
#5 

for(i in seq_along(df.out$date)){
  temp.df <- df.in[df.in$start <= df.out$date[i],]
  df.out$count[i] <- nrow(temp.df) - nrow(temp.df[temp.df$end <= df.out$date[i],])
}
> df.out
        date count
1 2015-01-01     2
2 2015-01-02     4
3 2015-01-03     3
4 2015-01-04     2
5 2015-01-05     0

require(data.table)
df.out <- data.table(date = c("2015-01-01", "2015-01-02", "2015-01-03", 
                              "2015-01-04", "2015-01-05"),
                     count = 0)
df.out$date <- as.Date(df.out$date, "%Y-%m-%d")

df.in <- data.table(event = c(1,2,3,4,5), 
                    start = c("2015-01-01", "2015-01-01", "2015-01-02",
                              "2015-01-02", "2015-01-03"),
                    end = c("2015-01-03", "2015-01-04", "2015-01-03",
                            "2015-01-05", "2015-01-05"))
df.in$start <- as.Date(df.in$start, "%Y-%m-%d")
df.in$end <- as.Date(df.in$end, "%Y-%m-%d") - 1

setkey(df.in, start, end)
df.out$date2 <- df.out$date
df.test <- foverlaps(x = df.out, y = df.in, type = "within", by.x = c("date", "date2"), by.y = c("start", "end"))
df.test$count[!is.na(df.test$event)] <- 1
aggregate(count ~ date, data = df.test, sum)

        date count
1 2015-01-01     2
2 2015-01-02     4
3 2015-01-03     3
4 2015-01-04     2
5 2015-01-05     0

df.out <- data.table(date = as.Date(c("2015-01-01", "2015-01-02", "2015-01-03", 
                              "2015-01-04", "2015-01-05")))

df.in <- data.table(event = 1:5, 
                    start = as.Date(c("2015-01-01", "2015-01-01", "2015-01-02",
                              "2015-01-02", "2015-01-03")),
                    end = as.Date(c("2015-01-03", "2015-01-04", "2015-01-03",
                            "2015-01-05", "2015-01-05")))

df.out[, `:=`(start = date, end = date)]
df.in[, end := end - 1L]
setkey(df.out, start, end)
foverlaps(df.in, df.out)[, .(count = .N), by = date]
#          date count
# 1: 2015-01-01     2
# 2: 2015-01-02     4
# 3: 2015-01-03     3
# 4: 2015-01-04     2

res <- foverlaps(df.in, df.out, which = TRUE)[, .N, by = yid]
df.out[res$yid, Count := res$N]
df.out[is.na(Count), Count := 0L]