Question

我有一个数据表只包含一系列次数。我有另一个包含两列的数据表：start_time和end_time。我想获取第一个数据表并添加一列，其中值是第二个数据表中所有行的计数，其中第一个数据表的时间适合开始和结束时间。这是我的代码

start_date <- as.POSIXct(x = "2017-01-31 17:00:00", format = "%Y-%m-%d %H:%M:%S")
end_date <- as.POSIXct(x = "2017-02-01 09:00:00", format = "%Y-%m-%d %H:%M:%S")

all_dates <- as.data.table(seq(start_date, end_date, "min"))

colnames(all_dates) <- c("Bin")

start_times <- sample(seq(start_date,end_date,"min"), 100)
offsets <- sample(seq(60,7200,60), 100)
end_times <- start_times + offsets
input_data <- data.table(start_times, end_times)

这是我想要做的，但这是错误的，并给出了错误。写这个的正确方法是什么？

all_dates[, BinCount := input_data[start_times < Bin & end_times > Bin, .N] ]

最后我应该得到像

这样的东西

Bin                   BinCount
2017-01-31 17:00:00   1
2017-01-31 17:01:00   5
...

Answer 1

使用sqldf可以非常轻松地解决问题，因为它提供了使用范围检查连接表的简便方法。因此，一种解决方案可能是：

The data from OP:
library(data.table)
start_date <- as.POSIXct(x = "2017-01-31 17:00:00", format = "%Y-%m-%d %H:%M:%S")
end_date <- as.POSIXct(x = "2017-02-01 09:00:00", format = "%Y-%m-%d %H:%M:%S")

all_dates <- as.data.table(seq(start_date, end_date, "min"))

colnames(all_dates) <- c("Bin")

start_times <- sample(seq(start_date,end_date,"min"), 100)
offsets <- sample(seq(60,7200,60), 100)
end_times <- start_times + offsets
input_data <- data.table(start_times, end_times)


library(sqldf)

result <- sqldf("SELECT all_dates.bin, count() as BinCount 
                FROM all_dates, input_data
                 WHERE all_dates.bin > input_data.start_times AND 
                 all_dates.bin < input_data.end_times
                 GROUP BY bin" )

result
                    Bin BinCount
1   2017-01-31 17:01:00        1
2   2017-01-31 17:02:00        1
3   2017-01-31 17:03:00        1
4   2017-01-31 17:04:00        1
5   2017-01-31 17:05:00        1
6   2017-01-31 17:06:00        1
...........
...........
497 2017-02-01 01:17:00        6
498 2017-02-01 01:18:00        5
499 2017-02-01 01:19:00        5
500 2017-02-01 01:20:00        4
 [ reached getOption("max.print") -- omitted 460 rows ]

Answer 2

在data.table中，您正在进行范围加入。

library(data.table)

start_date <- as.POSIXct(x = "2017-01-31 17:00:00", format = "%Y-%m-%d %H:%M:%S")
end_date <- as.POSIXct(x = "2017-02-01 09:00:00", format = "%Y-%m-%d %H:%M:%S")

all_dates <- as.data.table(seq(start_date, end_date, "min"))

colnames(all_dates) <- c("Bin")

set.seed(123)
start_times <- sample(seq(start_date,end_date,"min"), 100)
offsets <- sample(seq(60,7200,60), 100)
end_times <- start_times + offsets
input_data <- data.table(start_times, end_times)

## doing the range-join and calculating the number of items per bin in one chained step
input_data[
    all_dates
    , on = .(start_times < Bin, end_times > Bin)
    , nomatch = 0
    , allow.cartesian = T
][, .N, by = start_times]

#             start_times N
# 1:  2017-01-31 17:01:00 1
# 2:  2017-01-31 17:02:00 1
# 3:  2017-01-31 17:03:00 1
# 4:  2017-01-31 17:04:00 1
# 5:  2017-01-31 17:05:00 1
# ---                      
# 956: 2017-02-01 08:56:00 6
# 957: 2017-02-01 08:57:00 4
# 958: 2017-02-01 08:58:00 4
# 959: 2017-02-01 08:59:00 5
# 960: 2017-02-01 09:00:00 5

注意：

我已将all_dates对象放在联接的右侧，因此结果包含input_data列的名称，即使它们是您的Bins（请参阅{{ 3}}关于这个主题的讨论）
我正在使用set.seed()，因为你正在采样

Answer 3

未请求，但这是使用tidyverse的紧凑替代解决方案。使用lubridate解析器interval和%within%以及purrr::map_int生成所需的bin计数。

library(tidyverse)
library(lubridate)
start_date <- ymd_hms(x = "2017-01-31 17:00:00") # lubridate parsers
end_date <- ymd_hms(x = "2017-02-01 09:00:00")

all_dates <- tibble(seq(start_date, end_date, "min")) # tibble swap for data.table

colnames(all_dates) <- c("Bin")

start_times <- sample(seq(start_date,end_date,"min"), 100)
offsets <- sample(seq(60,7200,60), 100)
end_times <- start_times + offsets
input_data <- tibble(
  start_times,
  end_times,
  intvl = interval(start_times, end_times) # Add interval column
  )

all_dates %>% # Checks date in Bin and counts intervals it lies within
  mutate(BinCount = map_int(.$Bin, ~ sum(. %within% input_data$intvl)))
# A tibble: 961 x 2
   Bin                 BinCount
   <dttm>                 <int>
 1 2017-01-31 17:00:00        0
 2 2017-01-31 17:01:00        0
 3 2017-01-31 17:02:00        0
 4 2017-01-31 17:03:00        0
 5 2017-01-31 17:04:00        0
 6 2017-01-31 17:05:00        0
 7 2017-01-31 17:06:00        0
 8 2017-01-31 17:07:00        1
 9 2017-01-31 17:08:00        1
10 2017-01-31 17:09:00        1
# ... with 951 more rows

R data.table将列添加为另一个data.table的函数

3 个答案: