连续行与条件的时间差

时间：2016-05-17 07:56:55

标签： r loops posix difftime

我有一个时间列表：

> sapply(copy, class)
$timefact
[1] "POSIXct" "POSIXt" 

$timefact_hour
[1] "integer"

> head(copy)

             timefact timefact_hour
1 2016-04-07 23:42:00            23
2 2016-04-07 23:37:00            23
3 2016-04-07 23:31:00            23
4 2016-04-07 23:27:00            23
5 2016-04-07 23:19:00            23
6 2016-04-07 23:17:00            23

我的目标是创建第三列，它将是一个整数值，表示给定行与其上方行之间的分钟数差异。

因此输出应该如下所示：

> output
             timefact timefact_hour timediff
1 2016-04-07 23:42:00            23       NA
2 2016-04-07 23:37:00            23        5
3 2016-04-07 23:31:00            23        6
4 2016-04-07 23:27:00            23        4
5 2016-04-07 23:19:00            23        8
6 2016-04-07 23:17:00            23        2

但是，我想排除所有小时数不同的情况，并且只查找与上一行共享相同小时的行的差异。例如：

> output
              timefact timefact_hour timediff
90 2016-04-07 12:14:00            12        6
91 2016-04-07 12:04:00            12       10
92 2016-04-07 11:56:00            11       NA
93 2016-04-07 11:49:00            11        7
94 2016-04-07 11:42:00            11        7
95 2016-04-07 11:36:00            11        6

到目前为止，我已经提出了以下代码，

for(i in 2:nrow(copy)) {
   print(difftime(copy[i,"timefact"], copy[i-1,"timefact"], tz = "EST", units = "mins"))
  }

这似乎有效，但我不知道如何a）将它作为第三列添加到数据框中，b）跳过上面的行不是同一小时的行。任何意见，将不胜感激！我在下面列出了一些数据样本：

> dput(copy)
structure(list(timefact = structure(list(sec = c(0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 
0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0), min = c(42L, 37L, 31L, 27L, 
19L, 17L, 10L, 6L, 1L, 56L, 50L, 45L, 34L, 27L, 18L, 4L, 58L, 
53L, 50L, 44L, 44L, 37L, 34L, 28L, 23L, 16L, 12L, 4L, 59L, 50L, 
19L, 13L, 46L, 26L, 26L, 19L, 11L, 8L, 2L, 55L, 51L, 44L, 37L, 
31L, 9L, 0L, 48L, 43L, 34L, 30L, 10L, 6L, 57L, 52L, 44L, 39L, 
30L, 23L, 23L, 1L, 1L, 54L, 48L, 32L, 23L, 16L, 12L, 5L, 1L, 
48L, 44L, 37L, 27L, 18L, 13L, 6L, 0L, 39L, 31L, 23L, 17L, 4L, 
54L, 49L, 44L, 38L, 33L, 24L, 20L, 14L, 4L, 56L, 49L, 42L, 36L, 
48L, 36L, 31L, 22L, 14L), hour = c(23L, 23L, 23L, 23L, 23L, 23L, 
23L, 23L, 23L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 21L, 20L, 20L, 20L, 20L, 
19L, 19L, 19L, 19L, 19L, 19L, 19L, 18L, 18L, 18L, 18L, 18L, 18L, 
18L, 17L, 17L, 17L, 17L, 17L, 17L, 16L, 16L, 16L, 16L, 16L, 16L, 
16L, 16L, 16L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 14L, 14L, 
14L, 14L, 14L, 14L, 14L, 14L, 13L, 13L, 13L, 13L, 13L, 12L, 12L, 
12L, 12L, 12L, 12L, 12L, 12L, 12L, 11L, 11L, 11L, 11L, 10L, 10L, 
10L, 10L, 10L), mday = c(7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 
7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L, 7L), mon = c(3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 
3L, 3L), year = c(116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 116L, 
116L, 116L, 116L, 116L), wday = c(4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), yday = c(97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L, 
97L, 97L, 97L, 97L, 97L, 97L, 97L, 97L), isdst = c(0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 0L, 
0L), zone = c("EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", "EST", 
"EST", "EST", "EST"), gmtoff = c(NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_, NA_integer_, NA_integer_, NA_integer_, 
NA_integer_, NA_integer_)), .Names = c("sec", "min", "hour", 
"mday", "mon", "year", "wday", "yday", "isdst", "zone", "gmtoff"
), class = c("POSIXlt", "POSIXt"), tzone = c("EST", "EST", "   "
)), timefact_hour = c(23L, 23L, 23L, 23L, 23L, 23L, 23L, 23L, 
23L, 22L, 22L, 22L, 22L, 22L, 22L, 22L, 21L, 21L, 21L, 21L, 21L, 
21L, 21L, 21L, 21L, 21L, 21L, 21L, 20L, 20L, 20L, 20L, 19L, 19L, 
19L, 19L, 19L, 19L, 19L, 18L, 18L, 18L, 18L, 18L, 18L, 18L, 17L, 
17L, 17L, 17L, 17L, 17L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 16L, 
16L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 15L, 14L, 14L, 14L, 14L, 
14L, 14L, 14L, 14L, 13L, 13L, 13L, 13L, 13L, 12L, 12L, 12L, 12L, 
12L, 12L, 12L, 12L, 12L, 11L, 11L, 11L, 11L, 10L, 10L, 10L, 10L, 
10L)), .Names = c("timefact", "timefact_hour"), row.names = c(NA, 
100L), class = "data.frame")

1 个答案:

答案 0 :(得分：1)

首先将timefact列转换为类POSIXct 

copy$timefact <- as.POSIXct(copy$timefact)

然后，使用lubridate和dplyr：

library(lubridate)
library(lubridate)

copy %>%
  group_by(timefact_hour) %>%
  mutate(timediff = lag(minute(timefact) - lead(minute(timefact))))

或data.table：

library(data.table)

setDT(copy)[, timediff := shift(minute(timefact) - 
                                  shift(minute(timefact), type = "lead")), 
            by = timefact_hour]
相关问题
最新问题