R 在函数中汇总数据，而不是子集

对于示例数据帧：

bout <- structure(list(Date = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = "02/02/2013", class = "factor"),
Time = structure(1:30, .Label = c("07:55:40", "07:55:50",
"07:56:00", "07:56:10", "07:56:20", "07:56:30", "07:56:40",
"07:56:50", "07:57:00", "07:57:10", "07:57:20", "07:57:30",
"07:57:40", "07:57:50", "07:58:00", "07:58:10", "07:58:20",
"07:58:30", "07:58:40", "07:58:50", "07:59:00", "07:59:10",
"07:59:20", "07:59:30", "07:59:40", "07:59:50", "08:00:00",
"08:00:10", "08:00:20", "08:00:30"), class = "factor"), Axis1 = c(0L,
0L, 100L, 500L, 233L, 155L, 60L, 0L, 0L, 115L, 80L, 878L,
158L, 0L, 13L, 0L, 0L, 25L, 10L, 45L, 33L, 43L, 655L, 498L,
41L, 151L, 404L, 436L, 28L, 0L), Latitude = c(56.52289678,
56.52291659, 56.52292762, 56.52295108, 56.52292694, 56.52292513,
56.5229401, 56.52294825, 56.52295531, 56.52296413, 56.52296976,
56.52292374, 56.52293053, 56.52292422, 56.52289636, 56.52288866,
56.52293357, 56.52290114, 56.5228365, 56.52280237, 56.52279844,
56.52281107, 56.52282589, 56.52279711, 56.52277008, 56.52278785,
56.52279951, 56.52269176, 56.52270186, 56.52269016), Longitude = c(-2.56573101,
-2.56578171, -2.56579263, -2.56578099, -2.56575181, -2.56574877,
-2.56575947, -2.5657653, -2.56577941, -2.56577104, -2.56577004,
-2.56576048, -2.56575937, -2.56582402, -2.56585538, -2.56579373,
-2.56572003, -2.56568263, -2.56568237, -2.56570739, -2.56570637,
-2.56571299, -2.56572322, -2.56566835, -2.56566237, -2.56569353,
-2.56571833, -2.56563307, -2.56565902, -2.56565666), area = structure(c(1L,
1L, 2L, 2L, 2L, 2L, 3L, 4L, 5L, 6L, 6L, 7L, 7L, 7L, 8L, 9L,
10L, 11L, 2L, 2L, 6L, 6L, 6L, 6L, 12L, 13L, 13L, 13L, 13L,
13L), .Label = c("E456", "E457", "E460", "E461", "E462",
"E463", "E465", "E468", "E469", "E470", "E471", "E478", "E479"
), class = "factor"), bout = c(0L, 0L, 1L, 1L, 1L,
1L, 1L, 0L, 0L, 2L, 2L, 2L, 2L, 2L, 2L, 0L, 0L, 0L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 0L)), .Names = c("Date",
"Time", "Axis1", "Latitude", "Longitude", "area", "bout"
), class = "data.frame", row.names = c(NA, -30L))

---

bout这里是一个开始，使用
dplyr
：

require(dplyr)

bout %>% 
  mutate(DateTime=as.POSIXct(strptime(paste(Date,Time),
                                      "%d/%m/%Y %H:%M:%S"))) %>% 
  group_by(bout) %>% 
  summarise(min.Date=min(DateTime))

#Source: local data frame [4 x 2]
#
#   bout            min.Date
# 1    0 2013-02-02 07:55:40
# 2    1 2013-02-02 07:56:00
# 3    2 2013-02-02 07:57:10
# 4    3 2013-02-02 07:58:40

这里有一个解决方案，使用plyr的
ddply（）
函数进行聚合，并使用chron来保持没有日期的时间。请注意，
ddply
似乎不能很好地处理POSIXt日期，因此这些日期是使用
as.Date（）
转换的，它创建了一个具有类“Date”的列

about$Date
bout.1 <- subset(bout, bout==1)
min.Date.1 <- min(bout.1$Date)
min.Time.1 <- min(bout.1$Time)
max.Time.1 <- max(bout.1$Time)
time.bout.1 <- difftime(max.Time.1, min.Time.1)

require(dplyr)

bout %>% 
  mutate(DateTime=as.POSIXct(strptime(paste(Date,Time),
                                      "%d/%m/%Y %H:%M:%S"))) %>% 
  group_by(bout) %>% 
  summarise(min.Date=min(DateTime))

#Source: local data frame [4 x 2]
#
#   bout            min.Date
# 1    0 2013-02-02 07:55:40
# 2    1 2013-02-02 07:56:00
# 3    2 2013-02-02 07:57:10
# 4    3 2013-02-02 07:58:40

bout$Date <- as.Date(bout$Date, origin = "1970-01-01", format = "%d/%m/%Y")
library(chron)
bout$Time <- times(as.character(bout$Time))

my.stats <- function(x) {
    min.Date <- min(x$Date)
    min.Time <- min(x$Time)
    max.Time <- max(x$Time)
    time.bout <- max.Time - min.Time
    return(data.frame(min.Date, min.Time, max.Time, time.bout))
}

library(plyr)
ddply(bout, .(bout), my.stats)

#   bout   min.Date min.Time max.Time time.bout
# 1    0 2013-02-02 07:55:40 08:00:30  00:04:50
# 2    1 2013-02-02 07:56:00 07:56:40  00:00:40
# 3    2 2013-02-02 07:57:10 07:58:00  00:00:50
# 4    3 2013-02-02 07:58:40 08:00:20  00:01:40