将列合并到时间变量

Question

我有两个变量，小时和分钟。我想把它们变成一个单一的时间变量。

我尝试了以下方法，但没有成功：

test$hour <- as.numeric(test$hour)
test$min <- as.numeric(test$min)
test$time <- as.numeric(paste(test$hour, test$min, sep = ":"))

我也尝试了test$time <- strptime(paste(test$hour, test$min), "%H:%M")，但得到了相同的 NA 结果。

我的数据如下所示：

period  hour    min count
1   6   30  4.526305487
1   6   31  11.07462598
1   6   32  15.07302674
1   6   33  17.93844752
1   6   34  20.49889392
1   6   35  28.34603524
1   6   36  35.16286361
1   6   37  25.27624761
1   6   38  45.84684409
1   6   39  30.7370854
1   6   40  35.92090899
1   6   41  39.28625563
1   6   42  46.0457034
1   6   41.5    41.76117201
1   6   44  85.97052453
1   6   45  73.57407496
1   6   46  91.80656632
1   6   47  90.10439703
1   6   48  54.2160676
1   6   49  57.30371657
1   6   50  62.67364806
1   6   51  63.37224904
1   6   52  72.71908655
1   6   53  95.71827014
1   6   54  102.5008019
1   6   55  87.97671488
1   6   56  73.1705666
1   6   57  79.63483099
1   6   58  71.61188378

PS：除此之外，我想间隔 3 或 5 分钟，并汇总这些计数，但能够拥有 %H:%M 也将是向前迈出的一大步。欢迎任何想法！

Answer 1

你可以试试

test$time <- strptime(with(test, sprintf('%02d:%02d', hour, min)), '%H:%M')
test$time[1:5]
#[1] "2014-12-05 06:30:00 EST" "2014-12-05 06:31:00 EST"
#[3] "2014-12-05 06:32:00 EST" "2014-12-05 06:33:00 EST"
#[5] "2014-12-05 06:34:00 EST"

更新

对于aggregating的计数（sum），你可以试试

 aggregate(count~ cbind(timeGr=as.character(cut(time, breaks='3 min'))),
                                     test, FUN=sum)
                  timeGr     count
 #1  2014-12-05 06:30:00  30.67396
 #2  2014-12-05 06:33:00  66.78338
 #3  2014-12-05 06:36:00 106.28596
 #4  2014-12-05 06:39:00 147.70542
 #5  2014-12-05 06:42:00 132.01623
 #6  2014-12-05 06:45:00 255.48504
 #7  2014-12-05 06:48:00 174.19343
 #8  2014-12-05 06:51:00 231.80961
 #9  2014-12-05 06:54:00 263.64808
 #10 2014-12-05 06:57:00 151.24671

或使用data.table

 library(data.table)
 setDT(test)[, list(count=sum(count)), 
           by=list(timeGr=cut(time,breaks='3 min'))]
 #                 timeGr     count
 #1: 2014-12-05 06:30:00  30.67396
 #2: 2014-12-05 06:33:00  66.78338
 #3: 2014-12-05 06:36:00 106.28596
 #4: 2014-12-05 06:39:00 147.70542
 #5: 2014-12-05 06:42:00 132.01623
 #6: 2014-12-05 06:45:00 255.48504
 #7: 2014-12-05 06:48:00 174.19343
 #8: 2014-12-05 06:51:00 231.80961
 #9: 2014-12-05 06:54:00 263.64808
 #10:2014-12-05 06:57:00 151.24671

数据

 test <-  structure(list(period = 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), hour = c(6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 
 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 6L, 
 6L, 6L, 6L, 6L), min = c(30, 31, 32, 33, 34, 35, 36, 37, 38, 
 39, 40, 41, 42, 41.5, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 
 54, 55, 56, 57, 58), count = c(4.526305487, 11.07462598, 15.07302674, 
 17.93844752, 20.49889392, 28.34603524, 35.16286361, 25.27624761, 
 45.84684409, 30.7370854, 35.92090899, 39.28625563, 46.0457034, 
 41.76117201, 85.97052453, 73.57407496, 91.80656632, 90.10439703, 
 54.2160676, 57.30371657, 62.67364806, 63.37224904, 72.71908655, 
 95.71827014, 102.5008019, 87.97671488, 73.1705666, 79.63483099, 
 71.61188378)), .Names = c("period", "hour", "min", "count"), 
 class = "data.frame", row.names = c(NA, -29L))