data.table R：在特定时间段内发生两个事件的瞬间

我需要确定在特定时间段内发生两个事件的实例，如下所示。如果先发生事件a，则事件B必须在24小时内发生。另一方面，如果B首先出现，则需要在72小时内找到A。此外，当满足标准时，我需要“开始”时间，即第一个事件发生的时间

事件A

structure(list(fake_id = c("1000686267", "1000686267", "1000686267", 
"1000686267", "1000686267", "1000686267", "1000686267", "1070640921", 
"1070640921", "1070640921", "1070640921", "1070640921", "1070640921", 
"1184695414", "1184695414", "1184695414", "1184695414", "1184695414"
), date = structure(c(1515063600, 1514822400, 1514822400, 1514822400, 
1514822400, 1515146400, 1514901600, 1515330000, 1514822400, 1514822400, 
1514822400, 1514822400, 1517385600, 1516701600, 1515142800, 1515178800, 
1515178800, 1516557600), class = c("POSIXct", "POSIXt"), tzone = "UTC")), row.names = c(NA, 
-18L), class = "data.frame", .Names = c("fake_id", 
"date"))

事件B

structure(list(fake_id = c("1000686267", "1000686267", "1000686267", 
"1000686267", "1000686267", "1000686267", "1000686267", "1000686267", 
"1000686267", "1000686267", "1000686267", "1000686267", "1000686267", 
"1000686267", "1000686267", "1000686267", "1000686267", "1070640921", 
"1070640921", "1070640921", "1070640921", "1070640921", "1070640921", 
"1184695414", "1184695414", "1184695414", "1184695414", "1184695414", 
"1184695414", "1184695414"), date = structure(c(1516795200, 1516795200, 
1516795200, 1516917600, 1517400000, 1517400000, 1515492000, 1515492000, 
1516190400, 1516190400, 1517410800, 1517410800, 1516921200, 1515070800, 
1515070800, 1515052800, 1516633200, 1517374800, 1515322800, 1515322800, 
1516525200, 1515232800, 1516543200, 1516550400, 1515189600, 1516543200, 
1516543200, 1515142800, 1515142800, 1515142800), class = c("POSIXct", 
"POSIXt"), tzone = "UTC")), row.names = c(NA, -30L), class = "data.frame", .Names = c("fake_id", 
"date"))

一些代码

 library (data.table)

 event_a <- data.table(event_a[, c("fake_id", "date"), with = FALSE])
 event_b <- data.table(event_b[, c("fake_id", "date"), with = FALSE])

 event_a[, `:=`("criteria_a", "criteria_a")]
 event_b[, `:=`("criteria_b", "criteria_b")]

 setkeyv(event_a, c("fake_id", "date"))
 setkeyv(event_b, c("fake_id", "date"))

 join_window <- 60 * 60 * c(24, 72)

 event_subset_a <- event_a[event_b, roll = join_window[1]]
 event_subset_b <- event_b[event_a, roll = join_window[2]]

 event_df <- rbind(event_subset_a, event_subset_b)
 event_df[, `:=`(c("criteria_a", "criteria_b"),  NULL)]

 setkeyv(event_df, c("fake_id", "date"))
 event_df <- unique(event_df)

所需输出

      fake_id                date
1  1184695414 2018-01-05 09:00:00
2  1184695414 2018-01-05 19:00:00
3  1184695414 2018-01-05 22:00:00
4  1184695414 2018-01-21 14:00:00
5  1184695414 2018-01-21 16:00:00
6  1184695414 2018-01-21 18:00:00
7  1184695414 2018-01-23 10:00:00

      fake_id                date
1  1184695414 2018-01-05 09:00:00
2  1184695414 2018-01-21 14:00:00
3  1184695414 2018-01-23 10:00:00

---

起初我认为这个问题需要用一个非相等联接来解决，但后来我意识到一个标准联接就足够了

整个过程如下：

消除重复的行

连接两个表

过滤条件A首先出现的条件。将其标记为“A型”，并确定发病时间

过滤条件B最先出现的情况。将其标记为“B型”，并确定发病时间

删除未标记的行

修改列的名称，以便更容易理解哪些列属于何处 消除重复的行

---

eventA这类似于@PavoDive，但重点是在实际连接之前创建非等连接条件：

library (data.table)
setDT(event_a)
setDT(event_b)

# for the join - eventB needs to be within -72 to 24 hours
event_a[, `:=`(min_date = date - 72*60*60,
               max_date = date + 24*60*60)]

# join unique data.tables
unique(event_b)[unique(event_a),
           #non-equi join conditions
                on = .(fake_id = fake_id,
                       date > min_date,
                       date < max_date),
                nomatch = 0L,
                allow.cartesian = T,
            #select columns - you would only include fake_id and onset for desired output
                j = .(fake_id,
                      a_date = i.date,
                      b_date = x.date,
                      onset = pmin(i.date, x.date),
                      first_type = ifelse(i.date == x.date,
                                          NA_character_,
                                          ifelse(i.date < x.date,
                                                 'A',
                                                 'B'))
                      )
                ]

       fake_id              a_date              b_date               onset first_type
 1: 1000686267 2018-01-04 11:00:00 2018-01-04 13:00:00 2018-01-04 11:00:00          A
 2: 1000686267 2018-01-04 11:00:00 2018-01-04 08:00:00 2018-01-04 08:00:00          B
 3: 1000686267 2018-01-05 10:00:00 2018-01-04 13:00:00 2018-01-04 13:00:00          B
 4: 1000686267 2018-01-05 10:00:00 2018-01-04 08:00:00 2018-01-04 08:00:00          B
 5: 1070640921 2018-01-07 13:00:00 2018-01-07 11:00:00 2018-01-07 11:00:00          B
 6: 1070640921 2018-01-07 13:00:00 2018-01-06 10:00:00 2018-01-06 10:00:00          B
 7: 1070640921 2018-01-31 08:00:00 2018-01-31 05:00:00 2018-01-31 05:00:00          B
 8: 1184695414 2018-01-23 10:00:00 2018-01-21 16:00:00 2018-01-21 16:00:00          B
 9: 1184695414 2018-01-23 10:00:00 2018-01-21 14:00:00 2018-01-21 14:00:00          B
10: 1184695414 2018-01-05 09:00:00 2018-01-05 22:00:00 2018-01-05 09:00:00          A
11: 1184695414 2018-01-05 09:00:00 2018-01-05 09:00:00 2018-01-05 09:00:00       <NA>
12: 1184695414 2018-01-05 19:00:00 2018-01-05 22:00:00 2018-01-05 19:00:00          A
13: 1184695414 2018-01-05 19:00:00 2018-01-05 09:00:00 2018-01-05 09:00:00          B
14: 1184695414 2018-01-21 18:00:00 2018-01-21 16:00:00 2018-01-21 16:00:00          B
15: 1184695414 2018-01-21 18:00:00 2018-01-21 14:00:00 2018-01-21 14:00:00          B

库（data.table）
setDT（事件a）
setDT（事件b）
#对于加入-eventB需要在-72到24小时内完成
事件a[，`:=`（最小日期=日期-72*60*60，
最大日期=日期+24*60*60]
#联接唯一数据表
唯一（事件_b）[唯一（事件_a），
#非等连接条件
on=（假身份证=假身份证，
日期>最小日期，
日期<最长日期），
nomatch=0升，
allow.cartesian=T，
#选择列-您将只包含所需输出的伪id和起始值
j=（假身份证，
a_date=i.date，
b_date=x.date，
起效时间=pmin（i.date，x.date），
first_type=ifelse（i.date==x.date，
NA_character_，
如果其他（i.日期

输出的不同之处在于第11行中的开始时间相同。我的联接条件没有捕获到这一点，因为
data.table
当前不支持不相等。
为什么要将
data.table
和
dplyr
语法混合在一起？如果您能显示预期的输出，那将非常有用。我现在不在电脑旁，但最近我对一个类似的问题给出了答案。您可能想看看它，看看是否可以应用一些函数，特别是
data.table:：foverlaps
和非equi连接@毛里塔尼亚，对不起！作为dplyr的忠实粉丝，这是一种习惯力量。@RonakShah，希望这能有所帮助。谢谢
setnames(eventA, "date", "dateA")
setnames(eventB, "date", "dateB")

eventA <- eventA[!duplicated(eventA), ]
eventB <- eventB[!duplicated(eventB), ]

eventA[eventB, 
       allow.cartesian = TRUE][
          dateA < dateB & dateB <= dateA + dhours(24), 
          `:=` (type = "A", 
                onset = dateA)][
                    dateB < dateA & dateA <= dateB + dhours(72), 
                    `:=` (type = "B", 
                          onset = dateB)][!is.na(type), ][]

       fake_id               dateA               dateB type               onset
 1: 1000686267 2018-01-04 11:00:00 2018-01-04 08:00:00    B 2018-01-04 08:00:00
 2: 1000686267 2018-01-05 10:00:00 2018-01-04 08:00:00    B 2018-01-04 08:00:00
 3: 1000686267 2018-01-04 11:00:00 2018-01-04 13:00:00    A 2018-01-04 11:00:00
 4: 1000686267 2018-01-05 10:00:00 2018-01-04 13:00:00    B 2018-01-04 13:00:00
 5: 1070640921 2018-01-07 13:00:00 2018-01-06 10:00:00    B 2018-01-06 10:00:00
 6: 1070640921 2018-01-07 13:00:00 2018-01-07 11:00:00    B 2018-01-07 11:00:00
 7: 1070640921 2018-01-31 08:00:00 2018-01-31 05:00:00    B 2018-01-31 05:00:00
 8: 1184695414 2018-01-05 19:00:00 2018-01-05 09:00:00    B 2018-01-05 09:00:00
 9: 1184695414 2018-01-05 09:00:00 2018-01-05 22:00:00    A 2018-01-05 09:00:00
10: 1184695414 2018-01-05 19:00:00 2018-01-05 22:00:00    A 2018-01-05 19:00:00
11: 1184695414 2018-01-21 18:00:00 2018-01-21 14:00:00    B 2018-01-21 14:00:00
12: 1184695414 2018-01-23 10:00:00 2018-01-21 14:00:00    B 2018-01-21 14:00:00
13: 1184695414 2018-01-21 18:00:00 2018-01-21 16:00:00    B 2018-01-21 16:00:00
14: 1184695414 2018-01-23 10:00:00 2018-01-21 16:00:00    B 2018-01-21 16:00:00

library (data.table)
setDT(event_a)
setDT(event_b)

# for the join - eventB needs to be within -72 to 24 hours
event_a[, `:=`(min_date = date - 72*60*60,
               max_date = date + 24*60*60)]

# join unique data.tables
unique(event_b)[unique(event_a),
           #non-equi join conditions
                on = .(fake_id = fake_id,
                       date > min_date,
                       date < max_date),
                nomatch = 0L,
                allow.cartesian = T,
            #select columns - you would only include fake_id and onset for desired output
                j = .(fake_id,
                      a_date = i.date,
                      b_date = x.date,
                      onset = pmin(i.date, x.date),
                      first_type = ifelse(i.date == x.date,
                                          NA_character_,
                                          ifelse(i.date < x.date,
                                                 'A',
                                                 'B'))
                      )
                ]

       fake_id              a_date              b_date               onset first_type
 1: 1000686267 2018-01-04 11:00:00 2018-01-04 13:00:00 2018-01-04 11:00:00          A
 2: 1000686267 2018-01-04 11:00:00 2018-01-04 08:00:00 2018-01-04 08:00:00          B
 3: 1000686267 2018-01-05 10:00:00 2018-01-04 13:00:00 2018-01-04 13:00:00          B
 4: 1000686267 2018-01-05 10:00:00 2018-01-04 08:00:00 2018-01-04 08:00:00          B
 5: 1070640921 2018-01-07 13:00:00 2018-01-07 11:00:00 2018-01-07 11:00:00          B
 6: 1070640921 2018-01-07 13:00:00 2018-01-06 10:00:00 2018-01-06 10:00:00          B
 7: 1070640921 2018-01-31 08:00:00 2018-01-31 05:00:00 2018-01-31 05:00:00          B
 8: 1184695414 2018-01-23 10:00:00 2018-01-21 16:00:00 2018-01-21 16:00:00          B
 9: 1184695414 2018-01-23 10:00:00 2018-01-21 14:00:00 2018-01-21 14:00:00          B
10: 1184695414 2018-01-05 09:00:00 2018-01-05 22:00:00 2018-01-05 09:00:00          A
11: 1184695414 2018-01-05 09:00:00 2018-01-05 09:00:00 2018-01-05 09:00:00       <NA>
12: 1184695414 2018-01-05 19:00:00 2018-01-05 22:00:00 2018-01-05 19:00:00          A
13: 1184695414 2018-01-05 19:00:00 2018-01-05 09:00:00 2018-01-05 09:00:00          B
14: 1184695414 2018-01-21 18:00:00 2018-01-21 16:00:00 2018-01-21 16:00:00          B
15: 1184695414 2018-01-21 18:00:00 2018-01-21 14:00:00 2018-01-21 14:00:00          B