Question

expand.grid(country = c('Sweden','Norway', 'Denmark','Finland'),
            sport = c('curling','crosscountry','downhill')) %>% 
    mutate(medals = sample(0:3, 12, TRUE)) -> 
 data

使用reshape2的dcast在一行中实现了这一点。使用边距的自定义名称需要额外的步骤。

library(reshape2)

data %>% 
  dcast(country ~  sport, margins = TRUE, sum) %>% 

 # optional renaming of the margins `(all)`
  rename(Total = `(all)`) %>% 
  mutate(country = ifelse(country == "(all)", "Total", country))

我的dplyr + tidyr方法很冗长。使用tidyr和dplyr编写此内容的最佳（紧凑且可读）方式是什么。

library(dplyr)
library(tidyr)

data %>% 
  group_by(sport) %>% 
  summarise(medals = sum(medals)) %>% 
  mutate(country = 'Total') ->
  sport_totals

data %>% 
  group_by(country) %>% 
  summarise(medals = sum(medals)) %>% 
  mutate(sport = 'Total') ->
  country_totals

data %>% 
  summarise(medals = sum(medals)) %>% 
  mutate(sport = 'Total',
         country = 'Total') ->
  totals

data %>% 
  bind_rows(country_totals, sport_totals, totals) %>% 
  spread(sport, medals)

Answer 1

我不知道这是最好的（紧凑且可读的）但是它有效;）

data %>%
  spread(sport, medals) %>%
  mutate(Total = rowSums(.[2:4])) %>%
  rbind(., data.frame(country="Total", t(colSums(.[2:5]))))

  country curling crosscountry downhill Total
1  Sweden       0            2        0     2
2  Norway       1            1        0     2
3 Denmark       2            2        1     5
4 Finland       3            0        2     5
5   Total       6            5        3    14

用dplyr和tidyr计算小计

1 个答案: