R 总结和传播数据

我有如下类似的数据：

df=data.frame(
company=c("McD","McD","McD","KFC","KFC"),
Title=c("Crew Member","Manager","Trainer","Crew Member","Manager"),
Manhours=c(12,NA,5,13,10)
)
df

我希望对其进行操作并获得如下数据帧：

 df=data.frame(
   company=c("KFC", "McD"),
   Manager=c(1,1),
   Surbodinate=c(1,2),
   TotalEmp=c(2,3),
   TotalHours=c(23,17)  
  )

df<- df %>%
   mutate(Role = if_else((Title=="Manager" ),
                         "Manager","Surbodinate"))%>%  
   count(company,  Role) %>%  
   spread(Role, n, fill=0)%>%
   as.data.frame() %>%
   mutate(TotalEmp= select(., Manager:Surbodinate) %>% 
       apply(1, sum, na.rm=TRUE))

df <- df %>%group_by(company) %>%
    summarize(TotalHours = sum(Manhours, na.rm = TRUE))

我已设法对员工及其数量进行了操纵和分类，如下所示：

 df=data.frame(
   company=c("KFC", "McD"),
   Manager=c(1,1),
   Surbodinate=c(1,2),
   TotalEmp=c(2,3),
   TotalHours=c(23,17)  
  )

df<- df %>%
   mutate(Role = if_else((Title=="Manager" ),
                         "Manager","Surbodinate"))%>%  
   count(company,  Role) %>%  
   spread(Role, n, fill=0)%>%
   as.data.frame() %>%
   mutate(TotalEmp= select(., Manager:Surbodinate) %>% 
       apply(1, sum, na.rm=TRUE))

df <- df %>%group_by(company) %>%
    summarize(TotalHours = sum(Manhours, na.rm = TRUE))

df%
变更（角色=如果其他（（头衔=“经理”），
“经理”、“监管者”））%>%
计数（公司、角色）%>%
分布（角色，n，填充=0）%>%
as.data.frame（）%>%
突变（TotalEmp=select（，管理者：Surbodinate）%>%
应用（1，总和，不适用。rm=TRUE））

此外，我将工时总结如下：

 df=data.frame(
   company=c("KFC", "McD"),
   Manager=c(1,1),
   Surbodinate=c(1,2),
   TotalEmp=c(2,3),
   TotalHours=c(23,17)  
  )

df<- df %>%
   mutate(Role = if_else((Title=="Manager" ),
                         "Manager","Surbodinate"))%>%  
   count(company,  Role) %>%  
   spread(Role, n, fill=0)%>%
   as.data.frame() %>%
   mutate(TotalEmp= select(., Manager:Surbodinate) %>% 
       apply(1, sum, na.rm=TRUE))

df <- df %>%group_by(company) %>%
    summarize(TotalHours = sum(Manhours, na.rm = TRUE))

df%集团公司%>%
汇总（总时数=总和（工时，不适用时数=真））

---

如何一次将这两个步骤结合起来，或者是否有更干净/更简单的方法来获得所需的输出？

这不是

tidyverse

也不是一个单步过程。但如果您使用

data.table

，您可以：

library(data.table)
setDT(df, key = "company")

totals <- DT[, .(TotalEmp = .N, TotalHours = sum(Manhours, na.rm = TRUE)), by = company]
dcast(DT, company ~ ifelse(Title == "Manager", "Manager", "Surbodinate"))[totals]

#   company Manager Surbodinate TotalEmp TotalHours
# 1     KFC       1           1        2         23
# 2     McD       1           2        3         17

库（data.table）
setDT（df，key=“公司”）
总计像这样的事情怎么样：

df %>%
  mutate(Role = ifelse(Title=="Manager" ,
                        "Manager", "Surbodinate"))%>%  
  group_by(company) %>% 
  mutate(TotalEmp = n(), 
         TotalHours = sum(Manhours, na.rm=TRUE)) %>%  
  reshape2::dcast(company + TotalEmp + TotalHours ~ Role)

dplyr解决方案：

df %>%
    mutate(Title = if_else((Title=="Manager" ),
                          "Manager","Surbodinate")) %>%
    group_by(company) %>%
    summarise(Manager = sum(Title == "Manager"), Subordinate = sum(Title == "Surbodinate"), TotalEmp = n(), Manhours = sum(Manhours, na.rm = TRUE))

  company Manager Subordinate TotalEmp Manhours
  <fct>     <int>       <int>    <int>    <dbl>
1 KFC           1           1        2       23
2 McD           1           2        3       17

df%>%
变异（Title=if_else（（Title=Manager）），
“经理”、“监管者”））%>%
集团（公司）%>%
总结（经理=总经理（职务=“经理”）、下属=总经理（职务=“总经理”）、总经理=总经理（、工时=总工时（工时，na.rm=真））
公司经理下属总EMP工时
1肯德基1123
2 McD 1 2 3 17