Question

我正在创建一堆基本状态报告，而我发现乏味的事情之一是向所有表添加总计行。我目前正在使用Tidyverse方法，这是我当前代码的一个示例。我要寻找的是默认包含一些不同级别的选项。

#load into RStudio viewer (not required)
iris = iris

#summary at the group level
summary_grouped = iris %>% 
       group_by(Species) %>%
       summarize(mean_s_length = mean(Sepal.Length),
                 max_s_width = max(Sepal.Width))

#summary at the overall level
summary_overall = iris %>% 
  summarize(mean_s_length = mean(Sepal.Length),
            max_s_width = max(Sepal.Width)) %>%
  mutate(Species = "Overall")

#append results for report       
summary_table = rbind(summary_grouped, summary_overall)

多次执行此操作非常繁琐。我有点想要：

summary_overall = iris %>% 
       group_by(Species, total = TRUE) %>%
       summarize(mean_s_length = mean(Sepal.Length),
                 max_s_width = max(Sepal.Width))

仅供参考-如果您熟悉SAS，我正在寻找通过proc中的类，方式或类型语句提供的相同类型的功能，这意味着让我控制汇总级别并在一个调用中获得多个级别。

感谢您的帮助。我知道我可以创建自己的函数，但希望已经存在一些东西。我还希望坚持使用整洁的编程风格，尽管我对此没有设置。

Answer 1

只需在双重数据集中应用所需功能一次的解决方案：

while

技巧是传递具有新组ID（即library(tidyverse) iris %>% rbind(mutate(., Species = "Overall")) %>% group_by(Species) %>% summarize( mean_s_length = mean(Sepal.Length), max_s_width = max(Sepal.Width) ) # A tibble: 4 x 3 Species mean_s_length max_s_width <chr> <dbl> <dbl> 1 Overall 5.84 4.4 2 setosa 5.01 4.4 3 versicolor 5.94 3.4 4 virginica 6.59 3.8）的原始数据集：Species

Answer 2

您可以编写一个函数，对summarize编辑的小动作执行相同的ungroup，并将其绑定到最后。

summarize2 <- function(df, ...){
 bind_rows(summarise(df, ...), summarize(ungroup(df), ...))
}

iris %>% 
  group_by(Species) %>%
  summarize2(
    mean_s_length = mean(Sepal.Length),
    max_s_width = max(Sepal.Width)
  )

# # A tibble: 4 x 3
#   Species    mean_s_length max_s_width
#   <fct>              <dbl>       <dbl>
# 1 setosa              5.01         4.4
# 2 versicolor          5.94         3.4
# 3 virginica           6.59         3.8
# 4 NA                  5.84         4.4

如果需要，您可以为“整体”组的命名添加一些逻辑

summarize2 <- function(df, ...){
  s1 <- summarise(df, ...)
  s2 <- summarize(ungroup(df), ...)
  for(v in group_vars(s1)){
    if(is.factor(s1[[v]]))
      s1[[v]] <- as.character(s1[[v]])
    if(is.character(s1[[v]])) 
     s2[[v]] <- 'Overall'
    else if(is.numeric(s1[[v]])) 
     s2[[v]] <- -Inf
  }
  bind_rows(s1, s2)
}


iris %>% 
  group_by(Species, g = Petal.Length %/% 1) %>%
  summarize2(
    mean_s_length = mean(Sepal.Length),
    max_s_width = max(Sepal.Width)
  )

# # Groups:   Species [4]
#   Species        g mean_s_length max_s_width
#   <chr>      <dbl>         <dbl>       <dbl>
# 1 setosa         1          5.01         4.4
# 2 versicolor     3          5.35         2.9
# 3 versicolor     4          6.09         3.4
# 4 versicolor     5          6.35         3  
# 5 virginica      4          5.85         3  
# 6 virginica      5          6.44         3.4
# 7 virginica      6          7.43         3.8
# 8 Overall     -Inf          5.84         4.4

Answer 3

library(dplyr)

iris %>% 
  group_by(Species) %>%
  summarize(mean_s_length = mean(Sepal.Length),
            max_s_width = max(Sepal.Width)) %>%
  ungroup() %>% 
  mutate_at(vars(Species), as.character) %>% 
  {rbind(.,c("Overal",mean(.$mean_s_length),max(.$max_s_width)))} %>%
  mutate_at(vars(-Species), as.double) %>% 
  mutate_at(vars(Species), as.factor)
#> # A tibble: 4 x 3
#>   Species    mean_s_length max_s_width
#>   <fct>              <dbl>       <dbl>
#> 1 setosa              5.01         4.4
#> 2 versicolor          5.94         3.4
#> 3 virginica           6.59         3.8
#> 4 Overal              5.84         4.4

^{由reprex package（v0.3.0）于2019-06-21创建}

Answer 4

一种方法（也很乏味，但需要更长的时间）是将第二个摘要说明放在bind_rows中。
as.character调用避免了警告：

警告消息：
  1：在bind_rows_（x，.id）中：
    绑定因子和字符向量，强制为字符向量
  2：在bind_rows_（x，.id）中：
    绑定字符和因子向量，强制为字符向量

library(tidyverse)

summary_grouped <- iris %>% 
  mutate(Species = as.character(Species)) %>%
  group_by(Species) %>%
  summarize(mean_s_length = mean(Sepal.Length),
            max_s_width = max(Sepal.Width)) %>%
  bind_rows(iris %>% 
              summarize(mean_s_length = mean(Sepal.Length),
                        max_s_width = max(Sepal.Width)) %>%
              mutate(Species = "Overall"))
## A tibble: 4 x 3
#  Species    mean_s_length max_s_width
#  <chr>              <dbl>       <dbl>
#1 setosa              5.01         4.4
#2 versicolor          5.94         3.4
#3 virginica           6.59         3.8
#4 Overall             5.84         4.4

Answer 5

也许是这样的：

由于您要在同一输入（iris）上执行不同的操作，因此最好map通过不同的摘要功能并将其应用于数据。 map_dfr使用bind_rows

组合列表输出

library(dplyr)
library(purrr)

pipe <- . %>%
  group_by(Species) %>%
  summarize(
    mean_s_length = mean(Sepal.Length),
    max_s_width   = max(Sepal.Width))

map_dfr(
  list(pipe, . %>% mutate(Species = "Overall") %>% pipe),
  exec, 
  iris)
#> Warning in bind_rows_(x, .id): binding factor and character vector,
#> coercing into character vector
#> Warning in bind_rows_(x, .id): binding character and factor vector,
#> coercing into character vector
#> # A tibble: 4 x 3
#>   Species    mean_s_length max_s_width
#>   <chr>              <dbl>       <dbl>
#> 1 setosa              5.01         4.4
#> 2 versicolor          5.94         3.4
#> 3 virginica           6.59         3.8
#> 4 Overall             5.84         4.4

Answer 6

另一种选择：

library(tidyverse)  

iris %>% 
  mutate_at("Species", as.character) %>%
  list(group_by(.,Species), .) %>%
  map(~summarize(.,mean_s_length = mean(Sepal.Length),
                 max_s_width = max(Sepal.Width))) %>%
  bind_rows() %>%
  replace_na(list(Species="Overall"))
#> # A tibble: 4 x 3
#>   Species    mean_s_length max_s_width
#>   <chr>              <dbl>       <dbl>
#> 1 setosa              5.01         4.4
#> 2 versicolor          5.94         3.4
#> 3 virginica           6.59         3.8
#> 4 Overall             5.84         4.4

汇总不同聚合级别的数据-R和tidyverse

6 个答案: