r - 如何在 R 中使用并发值求和

Question

下面是示例数据和我正在使用的代码。

  library(dplyr)
  library(data.table)

   firm <- c("firm1","firm2","firm3","firm4","firm5","firm6","firm7","firm8","firm9")
   employment <- c(1,50,90,249,499,115,145,261,210)
   small <- c(1,1,1,3,4,2,2,4,3)

   smbtest <- data.frame(firm,employment,small)

   smbsummary <- smbtest %>% 
   select (employment,small) %>%
   group_by(small) %>%
   summarise(employment = sum(employment), worksites = n())

想要的结果是这样的

   smb     employment    worksites
    1          141           3
    2          401           5
    3          860           7
    4         1620           9

smb 表示小型企业。 smb 的值遵循以下模式

  smb1     >= 0 and <100
  smb2     >= 0 and <150
  smb3     >= 0 and <250
  smb4     >= 0 and <500

这就是我想要的

   smb     employment   worksites
    1          141          3
    2          260          2
    3          459          2 
    4          760          2  

所以问题是我如何将其设置为不分离出独特元素的地方。我希望它是累积的。如果有意义的话，0 到 100 是 1 到 150 的一部分。

Answer 1

我们只需要在最后添加一个mutate 步骤来获得累积总和('worksites' 的cumsum)。默认丢弃最后一组(因为只有一组，会自动丢弃，但指定.groups更好)

library(dplyr)
smbtest %>% 
  select(employment,small) %>%
  group_by(small) %>%
  summarise(employment = sum(employment), worksites = n(), 
         .groups = 'drop') %>% 
  mutate(worksites = cumsum(worksites))

-输出

# A tibble: 4 x 3
#  small employment worksites
#* <dbl>      <dbl>     <int>
#1     1        141         3
#2     2        260         5
#3     3        459         7
#4     4        760         9

---

如果我们需要对多列进行累加求和，那么使用across

smbtest %>% 
  select(employment,small) %>%
  group_by(small) %>%
  summarise(employment = sum(employment), worksites = n(), 
         .groups = 'drop') %>%
  mutate(across(c(employment, worksites), cumsum))

---

或者collapse中的类似选项

library(collapse)
slt(smbtest, employment, small) %>%
    fgroup_by(small) %>%
    fsummarise(worksites = fNobs(employment), 
              employment = fsum(employment)) %>%    
    ftransformv(-1, cumsum)
# A tibble: 4 x 3
#  small worksites employment
#  <dbl>     <int>      <dbl>
#1     1         3        141
#2     2         5        401
#3     3         7        860
#4     4         9       1620

数据

smbtest <- tibble(firm, employment, small)