r - 加入两个具有最接近时间戳间隔的数据集

Question

我编辑了我的问题 - 请阅读第二部分 Edit 2

我需要使用壁橱时间戳加入两个数据集。第一个数据集是来自移动应用程序的日记数据集:

    df1 <- data.frame(stringsAsFactors=FALSE,
        datetime = c("2019-03-19T13:26:52Z", "2019-03-19T13:26:19Z",
                     "2019-03-19T13:23:46Z", "2019-03-19T13:22:20Z",
                     "2019-03-19T13:09:56Z", "2019-03-19T13:06:04Z", "2019-03-19T13:05:21Z",
                     "2019-03-19T13:04:37Z", "2019-03-19T12:47:28Z",
                     "2019-03-19T12:46:42Z"),
       transport = c("Trainride", "Trainride", "Trainride", "Trainride",
                     "Trainride", "Trainride", "Trainride", "Trainride",
                     "Trainride", "Trainride"),
              id = c("5-3", "5-3", "5-3", "5-3", "5-3", "5-3", "5-3", "5-3", "5-3",
                     "5-3"),
            disc = c("start", "stop", "start", "stop", "start", "stop", "start",
                     "stop", "start", "stop")
    )
 # datetime dttr object   
    df1 <- df1 %>% 
      mutate(datetime = lubridate::as_datetime(datetime))

这里:

              datetime transport  id  disc
1  2019-03-19 13:26:52 Trainride 5-3 start
2  2019-03-19 13:26:19 Trainride 5-3  stop
3  2019-03-19 13:23:46 Trainride 5-3 start
4  2019-03-19 13:22:20 Trainride 5-3  stop
5  2019-03-19 13:09:56 Trainride 5-3 start
6  2019-03-19 13:06:04 Trainride 5-3  stop
7  2019-03-19 13:05:21 Trainride 5-3 start
8  2019-03-19 13:04:37 Trainride 5-3  stop
9  2019-03-19 12:47:28 Trainride 5-3 start
10 2019-03-19 12:46:42 Trainride 5-3  stop

第二个数据集是来自加速度计日志的数据集，显示运动(=INVH)或空闲(=NIVH):

df2 <- data.frame(stringsAsFactors=FALSE,
           datetime = c("2019-03-19T23:20:00Z", "2019-03-19T23:17:30Z",
                        "2019-03-19T13:08:00Z", "2019-03-19T13:07:00Z",
                        "2019-03-19T12:38:45Z", "2019-03-19T12:32:45Z",
                        "2019-03-19T11:13:15Z", "2019-03-19T11:11:45Z", "2019-03-19T10:17:45Z",
                        "2019-03-19T10:16:45Z"),
                 id = c("5-3", "5-3", "5-3", "5-3", "5-3", "5-3", "5-3", "5-3", "5-3",
                        "5-3"),
               code = c("NIVH", "INVH", "NIVH", "INVH", "NIVH", "INVH", "NIVH",
                        "INVH", "NIVH", "INVH")
       )
 # datetime dttr object 
df2 <- df2 %>% 
  mutate(datetime = lubridate::as_datetime(datetime))

这里:

              datetime  id code
1  2019-03-19 23:20:00 5-3 NIVH
2  2019-03-19 23:17:30 5-3 INVH
3  2019-03-19 13:08:00 5-3 NIVH
4  2019-03-19 13:07:00 5-3 INVH
5  2019-03-19 12:38:45 5-3 NIVH
6  2019-03-19 12:32:45 5-3 INVH
7  2019-03-19 11:13:15 5-3 NIVH
8  2019-03-19 11:11:45 5-3 INVH
9  2019-03-19 10:17:45 5-3 NIVH
10 2019-03-19 10:16:45 5-3 INVH

我需要根据时间戳字段之间的时间差连接两个数据帧。例如，在 df1 上左连接以查看应用日志数据与真实加速度计日志的一致性。简单的左连接在这里不起作用，因为在大多数情况下都有延迟时间。所以我的问题是如何加入这两个数据集基于差异为最小绝对差异的记录。

编辑 2 ---@soren 建议的解决方案很有帮助，但是如果我将 start datetime 和 endtime 设置为有一个 interval ，将不起作用。有什么想法吗？

df1 <- df1 %>% 
  mutate(datetime = lubridate::as_datetime(datetime)) %>% 
  arrange(datetime) %>% 
  mutate(datetime_end = lead(datetime), 
         # Create an interval object.
         Travel_Interval = lubridate::interval(start = datetime, end = datetime_end))

Answer 1

滚动连接将完成此操作，按最近的日期时间连接数据框。以下使用data.table的解决方案

library(data.table)
dt1 <- as.data.table(df1)
setkeyv(dt1,"datetime")

dt2 <- as.data.table(df2)
setkeyv(dt2,"datetime")
dt2[,nearest_date:=datetime]

dt2[dt1,roll="nearest"]

> dt2[dt1,roll="nearest"]
               datetime  id code        nearest_date transport i.id  disc
 1: 2019-03-19 12:46:42 5-3 NIVH 2019-03-19 12:38:45 Trainride  5-3  stop
 2: 2019-03-19 12:47:28 5-3 NIVH 2019-03-19 12:38:45 Trainride  5-3 start
 3: 2019-03-19 13:04:37 5-3 INVH 2019-03-19 13:07:00 Trainride  5-3  stop
 4: 2019-03-19 13:05:21 5-3 INVH 2019-03-19 13:07:00 Trainride  5-3 start
 5: 2019-03-19 13:06:04 5-3 INVH 2019-03-19 13:07:00 Trainride  5-3  stop
 6: 2019-03-19 13:09:56 5-3 NIVH 2019-03-19 13:08:00 Trainride  5-3 start
 7: 2019-03-19 13:22:20 5-3 NIVH 2019-03-19 13:08:00 Trainride  5-3  stop
 8: 2019-03-19 13:23:46 5-3 NIVH 2019-03-19 13:08:00 Trainride  5-3 start
 9: 2019-03-19 13:26:19 5-3 NIVH 2019-03-19 13:08:00 Trainride  5-3  stop
10: 2019-03-19 13:26:52 5-3 NIVH 2019-03-19 13:08:00 Trainride  5-3 start

请注意，添加了附加列“nearest_date”dt2[,nearest_date:=datetime]，以便在连接 dt2 和 dt1 时，保留 datetime 的值(或可用于差异计算)。而默认情况下将数据集合并/连接在一起仅返回主键列。通常，这是可取的，因为连接的列通常是相同的。在这里，它们不是滚动连接，保留列或手动创建冗余列很有用，如此处所示。

还要注意，最近的 id 值和 datetime 也可能与应用程序相关(OP 中只给出了一个 id 值)。这是通过设置连接语法中使用的键来完成的:

setkeyv(dt2,c("id","datetime"))
setkeyv(dt1,c("id","datetime"))