Question

我有data frame（不允许我在这里展示图片）。我试图获取按组件名称分组的每个顺序位置之间的时差。所以基本上，我想看看每个组件在某个位置需要多长时间，然后想要获取任何组件在某个位置的平均时间，然后是位置和组件类型。我最初试图传播数据，以便位置将是关键和值的时间，然后获得列之间的差异，但每个组件类型具有不同的位置，因此不起作用。

comps <- structure(list(component_name = c("COMPONENT000000001", 
    "COMPONENT000000001", 
"COMPONENT000000001", "COMPONENT000000001", "COMPONENT000000001", 
"COMPONENT000000001", "COMPONENT000000002", "COMPONENT000000002", 
"COMPONENT000000002", "COMPONENT000000002", "COMPONENT000000002", 
"COMPONENT000000002", "COMPONENT000000002"), component_type = 
    structure(c(4L, 
4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L), .Label = c("component_0", 
"component_1", "component_2", "component_3"), class = "factor"), 
    location = structure(c(6L, 2L, 14L, 1L, 1L, 4L, 6L, 2L, 14L, 
    14L, 1L, 1L, 4L), .Label = c("29MSJ_03_01", "5YU1V_01_02", 
    "7EFLP_03_02", "assembly room", "B57X3_03_00", "GH9CV_00_03", 
    "HUX1L_02_02", "JX3UO_01_01", "MRX5B_01_00", "TG6IA_00_02", 
    "VUFVH_00_00", "YBSFJ_00_01", "ZAENM_02_01", "ZZU3X_02_00"
    ), class = "factor"), times = structure(c(1514764800, 1514771683, 
    1514784872, 1514794911, 1514806504, 1514820010, 1514764800, 
    1514776184, 1514789862, 1514794911, 1514806046, 1514831050, 
    1514843151), class = c("POSIXct", "POSIXt"), tzone = "America/New_York")), .Names = c("component_name", 
"component_type", "location", "times"), row.names = c(NA, 13L
), class = "data.frame")



loc_diff <- comps %>%
          group_by(., type, location) %>%
          mutate(., diff = as.numeric(difftime(max(times), min(times))))
ld <- loc_diff %>%
      group_by(., location) %>%
      summarise(., avg = mean(diff))

这最初是我试图做的，但它给了我一个数据框，所有的平均值大致相同，我不认为这是基于我做过的其他探索。任何帮助是极大的赞赏。谢谢！

P.S。我不确定我是否应该对此做一些事情，但我是新手，我仍然试图让它发挥作用。

Answer 1

首先，您可以通过对component_name进行分组，然后在下一行和当前行的times之间取差来计算组件在每个位置上花费的时间。可以使用difftime找到两次之间的差异（以秒为单位）。

library(dplyr)
library(tidyr)
library(lubridate)

#First get the time spend by each component at a location
comps_timesSpendAtLocatoin <- comps %>%
  group_by(component_name) %>%
  mutate(timeSpendAtLocation = difftime(lead(times),times, units = "secs"))

#Group_by 'component_name' to find average time spend on a location by each component
comps_timesSpendAtLocatoin %>% group_by(component_name) %>%
  summarise(avgTimeComponentAtLocation = mean(timeSpendAtLocation, na.rm = TRUE))
# component_name     avgTimeComponentAtLocation
# <chr>              <time>                    
# 1 COMPONENT000000001 11042                     
# 2 COMPONENT000000002 13058.5 

#Average time spend on a location by component_type and location  
comps_timesSpendAtLocatoin %>% group_by(component_type, location) %>%
  summarise(avgTimeComponentTypeAtLocation = mean(timeSpendAtLocation, na.rm = TRUE))

# # A tibble: 5 x 3
# # Groups: component_type [?]
# component_type location      avgTimeComponentTypeAtLocation
# <fctr>         <fctr>        <time>                        
# 1 component_3    29MSJ_03_01   15551                         
# 2 component_3    5YU1V_01_02   13433.5                       
# 3 component_3    assembly room NaN                           
# 4 component_3    GH9CV_00_03   9133.5                        
# 5 component_3    ZZU3X_02_00   8741

R-试图获得每一行（顺序位置）之间的时差？

1 个答案: