5

我有一个由客户交易数据组成的数据集。它具有某些事件发生时间的时间戳。我想只获取在某个事件之前发生的事件，而是针对每个客户，而不仅仅是单个时间点。

这是一个快照：

      custId         date_time_recorded              event           dateTime1
1  280512544 2012-11-13 15:25:37.947-08            shipped 2012-11-13 15:25:37
2  280512544 2012-11-13 15:22:42.614-08        statusCheck 2012-11-13 15:22:42
3  280512544  2012-11-13 15:03:16.62-08        statusCheck 2012-11-13 15:03:16
4  280512544 2012-11-13 15:01:35.149-08        statusCheck 2012-11-13 15:01:35
5  280512544 2012-11-13 14:45:41.964-08      status-picked 2012-11-13 14:45:41
6  280512544 2012-11-13 14:44:57.664-08 warehouse_notified 2012-11-13 14:44:57
7  280512544 2012-11-13 14:44:57.644-08        statusCheck 2012-11-13 14:44:57
8  280512544 2012-11-13 13:05:15.725-08      recordCreated 2012-11-13 13:05:15
9  280510610 2012-11-13 09:22:36.427-08            shipped 2012-11-13 09:22:36
10 280510610 2012-11-13 09:20:07.202-08        statusCheck 2012-11-13 09:20:07
11 280510610 2012-11-13 09:14:56.182-08        statusCheck 2012-11-13 09:14:56

我只想获取“已发货”事件之前发生的事件。我目前正在使用 ddply 来完成此操作，但这需要很长时间。 

keepPreShip <- function(x){
shipTime <- fastPOSIXct(x[grep("shipped", x$event, ignore.case = T), "date_time_recorded"],tz = "UTC")
#shipTime <- fastPOSIXct(x[x$event =="shipped", "date_time_recorded"],tz = "UTC")
x <- x[x$dateTime1 < shipTime,]
}

system.time(eventsMain1 <- ddply(ss1, .(custId), keepPreShip ))

有没有更快的方法来做到这一点？也许与data.table？

这是其中的一个dput数据：

> dput(ss1)
structure(list(custId = c(280512544L, 280512544L, 280512544L, 
280512544L, 280512544L, 280512544L, 280512544L, 280512544L, 280510610L, 
280510610L, 280510610L, 280510610L, 280510610L, 280510610L, 280510610L, 
280510610L, 280511123L, 280511123L, 280511123L, 280511123L), 
    date_time_recorded = c("2012-11-13 15:25:37.947-08", "2012-11-13 15:22:42.614-08", 
    "2012-11-13 15:03:16.62-08", "2012-11-13 15:01:35.149-08", 
    "2012-11-13 14:45:41.964-08", "2012-11-13 14:44:57.664-08", 
    "2012-11-13 14:44:57.644-08", "2012-11-13 13:05:15.725-08", 
    "2012-11-13 09:22:36.427-08", "2012-11-13 09:20:07.202-08", 
    "2012-11-13 09:14:56.182-08", "2012-11-13 09:11:40.438-08", 
    "2012-11-13 09:03:51.571-08", "2012-11-13 09:03:51.461-08", 
    "2012-11-13 09:03:49.174-08", "2012-11-13 06:42:10.208-08", 
    "2012-11-13 13:51:05.039-08", "2012-11-13 13:13:16.452-08", 
    "2012-11-13 12:42:08.917-08", "2012-11-13 12:28:51.541-08"
    ), event = c("shipped", "statusCheck", "statusCheck", "statusCheck", 
    "status-picked", "warehouse_notified", "statusCheck", "recordCreated", 
    "shipped", "statusCheck", "statusCheck", "statusCheck", "status-picked", 
    "warehouse_notified", "statusCheck", "recordCreated", "shipped", 
    "statusCheck", "statusCheck", "statusCheck"), dateTime1 = structure(c(1352820337.947, 
    1352820162.614, 1352818996.62, 1352818895.149, 1352817941.964, 
    1352817897.664, 1352817897.644, 1352811915.725, 1352798556.427, 
    1352798407.202, 1352798096.182, 1352797900.438, 1352797431.571, 
    1352797431.461, 1352797429.174, 1352788930.208, 1352814665.039, 
    1352812396.452, 1352810528.917, 1352809731.541), class = c("POSIXct", 
    "POSIXt"), tzone = "UTC")), .Names = c("custId", "date_time_recorded", 
"event", "dateTime1"), row.names = c(NA, 20L), class = "data.frame")
4

1 回答 1

6

这行得通。我希望它更快。

require(data.table)
# convert this column to date format first
ss1$date_time_recorded <- as.POSIXct(ss1$date_time_recorded)
dt <- data.table(ss1, key="custId")
dt[, .SD[dateTime1 < date_time_recorded[event == "shipped"]], by=custId]

#       custId  date_time_recorded         event           dateTime1
# 1: 280510610 2012-11-13 06:42:10 recordCreated 2012-11-13 06:42:10
# 2: 280511123 2012-11-13 12:42:08   statusCheck 2012-11-13 12:42:08
# 3: 280511123 2012-11-13 12:28:51   statusCheck 2012-11-13 12:28:51
# 4: 280512544 2012-11-13 13:05:15 recordCreated 2012-11-13 13:05:15
于 2013-01-24T20:32:44.353 回答