R 分组、汇总和重塑数据框

我有一个原始数据如下

raw_data <- data.frame(
                            name=c("Ronak","Bob","Moh"),
                            l_name=c("Shah","Marly","Salah"),
                            R_programming=c(1,5,2),
                            football=c(2,4,6),
                            snooker=c(6,3,2),
                            Python=c(3,2,6),
                            location=c("Maly","US","Maly")
                      )

然后，我根据上述平均值计算分数和等级，并重塑数据

我的预期产出是

output <- data.frame(
                        location=c("US","Maly"),
                        indicator=rep(c("programming","sport"),each=2),
                        average=c(3,3.5,3.5,4),
                        score=c(0.6,0.7,0.7,0.8),
                        scale=c("Moderate high","high","high","high")
                    )

---

输出
按
位置分组
并取节目和运动的平均值。以长格式获取数据，并为
分数
和
比例
创建新列

library(dplyr)

raw_data %>%
  group_by(location) %>%
  summarise(programming_average = mean(c(R_programming, Python), na.rm = TRUE), 
            sport_average = mean(c(football,snooker),na.rm=TRUE)) %>%
  tidyr::pivot_longer(cols = -location, 
               names_to = c('indicator', '.value'), 
               names_sep = '_') %>%
  mutate(score = average/5, 
         scale = case_when(score <= 0.6 ~ 'moderate high', 
                           score > 0.6 ~ 'high'))

#  location indicator  average score scale        
#  <chr>    <chr>        <dbl> <dbl> <chr>        
#1 Maly     programming     3     0.6 moderate high
#2 Maly     sport          4     0.8 high         
#3 US       programming     3.5   0.7 high         
#4 US       sport          3.5   0.7 high         

库（dplyr）
原始数据%>%
分组依据（位置）%>%
总结（编程平均值=平均值（c（R\u编程，Python），na.rm=真），
运动平均值=平均值（c（足球、斯诺克），na.rm=真实值））%>%
tidyr:：pivot_更长（cols=-位置，
名称_to=c（'indicator'，'.value'），
名称\u sep=''.''%>%
变异（分数=平均值/5，
量表=情况（得分0.6~‘高’）
#位置指标平均得分量表
#                        
#1 Maly编程3 0.6中等偏高
#2 Maly sport 4 0.8偏高
#3美国编程3.5 0.7高
#4美国体育3.5 0.7偏高

library(dplyr)

raw_data %>%
  group_by(location) %>%
  summarise(programming_average = mean(c(R_programming, Python), na.rm = TRUE), 
            sport_average = mean(c(football,snooker),na.rm=TRUE)) %>%
  tidyr::pivot_longer(cols = -location, 
               names_to = c('indicator', '.value'), 
               names_sep = '_') %>%
  mutate(score = average/5, 
         scale = case_when(score <= 0.6 ~ 'moderate high', 
                           score > 0.6 ~ 'high'))

#  location indicator  average score scale        
#  <chr>    <chr>        <dbl> <dbl> <chr>        
#1 Maly     programming     3     0.6 moderate high
#2 Maly     sport          4     0.8 high         
#3 US       programming     3.5   0.7 high         
#4 US       sport          3.5   0.7 high