Question

我有一个数据框，其中包含不同船只在一段时间内进行的航行。航行通常由一个开始端口，一个或多个装货端口和一个或多个卸货端口组成。我的目标是找到从开始端口到装载端口的距离，如果有多个装载端口，则从一个装载端口到下一个装载端口，再到从装载端口到卸料端口。我还需要找到进行特定行程的月份。这是一些测试数据：

test <- structure(list(Vessel = c("STI Selatar", "STI Selatar", "STI Selatar", 
"STI Selatar", "STI Selatar", "STI Selatar", "STI Selatar", "STI Selatar", 
"STI Selatar", "STI Selatar", "STI Selatar", "STI Selatar", "STI Amber", 
"STI Amber", "STI Amber", "STI Amber", "STI Amber", "STI Amber", 
"STI Amber", "STI Amber", "STI Amber"), VoyNum = c(14L, 14L, 
14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 14L, 62L, 62L, 62L, 
62L, 62L, 62L, 62L, 62L, 62L), Port = c("ROTTERDAM", "ROTTERDAM", 
"ENGLISH CHANNEL", "GIBRALTAR", "PIRAEUS", "ELEUSIS", "ELEUSIS", 
"AGIOI THEODOROI", "SUEZ CANAL", "SINGAPORE STRAIT", "YOSU", 
"DAESAN", "BOTANY BAY", "NAPA NAPA", "NAPA NAPA", "PNGLNG TERMINAL", 
"TORRES STRAIT", "SINGAPORE STRAIT", "SINGAPORE", "SINGAPORE STRAIT", 
"TOLO HARBOUR"), Function = structure(c(2L, 14L, 8L, 8L, 5L, 
14L, 6L, 6L, 1L, 8L, 4L, 4L, 2L, 14L, 6L, 6L, 1L, 8L, 4L, 8L, 
4L), .Label = c("Canal Transit", "Commencing", "Delivery", "Discharging", 
"Fuelling", "Loading", "Other", "Passing", "Port Call Cancelled", 
"Redelivery", "Repair", "Sampling", "Terminating", "Waiting"), class = "factor"), 
    Date_Arrival = structure(c(978307200, 1535198400, 978307200, 
    978307200, 1537237440, 1537696800, 1537736460, 1538161920, 
    1539118440, 978307200, 1541531520, 1541736000, 978307200, 
    1520194320, 1520258460, 1520654400, 1520800560, 978307200, 
    1521556560, 978307200, 1522321200), class = c("POSIXct", 
    "POSIXt"), tzone = "UTC"), Date_Departure = structure(c(1535196600, 
    1536346080, 978307200, 978307200, 1537688160, 1537736340, 
    1538155080, 1538938800, 1539190800, 978307200, 1541621880, 
    1541979000, 1519702560, 1520258340, 1520642520, 1520740800, 
    1520837280, 978307200, 1521894960, 978307200, 1522461600), class = c("POSIXct", 
    "POSIXt"), tzone = "UTC"), BallastLaden = c(0L, 0L, 0L, 0L, 
    0L, 0L, 1L, 1L, 1L, 1L, 1L, 1L, 0L, 0L, 1L, 1L, 1L, 1L, 1L, 
    1L, 1L), Miles = c(4, 2930, 0, 0, 24, 0.43, 23, 623, 7466, 
    0, 338, 0, 1720, 0.43, 43, 213, 2594, 0, 1424, 0, 0)), row.names = c(NA, 
-21L), class = c("tbl_df", "tbl", "data.frame"))

Miles变量显示当前行和下一行之间的距离。 VoyNum是船只的航行ID。 Function变量包含有关开始加载和卸载的信息。为了找出特定行程的哪个月，我正在寻找Date_Departure和Date_Arrival之间的间隔，将其间隔一半，然后将其添加到Date_Departure中。这是所需的输出：

# A tibble: 8 x 7
  Vessel      VoyNum FromPort        ToPort          Miles BallastLaden Month
  <chr>        <int> <chr>           <chr>           <dbl>        <int> <chr>
1 STI Selatar     14 ROTTERDAM       ELEUSIS         2958.            0 Sep  
2 STI Selatar     14 ELEUSIS         AGIOI THEODOROI   23             1 Sep  
3 STI Selatar     14 AGIOI THEODOROI YOSU            8089             1 Oct  
4 STI Selatar     14 YOSU            DAESAN           338             1 Nov  
5 STI Amber       62 BOTANY BAY      NAPA NAPA       1720.            0 Mar  
6 STI Amber       62 NAPA NAPA       PNGLNG TERMINAL   43             1 Mar  
7 STI Amber       62 PNGLNG TERMINAL SINGAPORE       2807             1 Mar  
8 STI Amber       62 SINGAPORE       TOLO HARBOUR    1424             1 Mar

如何结合使用dplyr和group_by()来实现summarize()？

我可以这样总结总的压载或载重里程，但这并不是我真正需要的，因为这些支腿中的每一个都进一步分成了多个端口：

test %>% group_by(Vessel, VoyNum) %>% summarise(BMiles=sum(test$Miles[BallastLaden==0]),                                                      LMiles=sum(test$Miles[BallastLaden==1]))

Answer 1

这是一个tidyverse解决方案：

library(lubridate)
test %>% group_by(VoyNum) %>% arrange(Date_Departure) %>% mutate(cumMiles = cumsum(Miles)) %>%
  filter(Function %in% c("Commencing", "Loading", "Discharging")) %>% 
  mutate(Miles = c(diff(cumMiles - Miles), last(Miles)), ToPort = lead(Port),
         Month = month(Date_Departure + floor(c(Date_Arrival[-1], 0) - Date_Departure) / 2, label = TRUE)) %>%
  rename(FromPort = Port) %>% slice(-n()) %>%
  select(Vessel, VoyNum, FromPort, ToPort, Miles, BallastLaden, Month)
# A tibble: 8 x 7
# Groups:   VoyNum [2]
#   Vessel      VoyNum FromPort        ToPort          Miles BallastLaden Month
#   <chr>        <int> <chr>           <chr>           <dbl>        <int> <ord>
# 1 STI Selatar     14 ROTTERDAM       ELEUSIS         2958.            0 Sep  
# 2 STI Selatar     14 ELEUSIS         AGIOI THEODOROI   23             1 Sep  
# 3 STI Selatar     14 AGIOI THEODOROI YOSU            8089             1 Oct  
# 4 STI Selatar     14 YOSU            DAESAN           338             1 Nov  
# 5 STI Amber       62 BOTANY BAY      NAPA NAPA       1720.            0 Mar  
# 6 STI Amber       62 NAPA NAPA       PNGLNG TERMINAL   43             1 Mar  
# 7 STI Amber       62 PNGLNG TERMINAL SINGAPORE       2807             1 Mar  
# 8 STI Amber       62 SINGAPORE       TOLO HARBOUR    1424             1 Mar

使用dplyr汇总数据框

1 个答案: