8

我正在创建一堆基本状态报告，而我发现乏味的一件事是在我的所有表格中添加一个总行。我目前正在使用 Tidyverse 方法，这是我当前代码的一个示例。我正在寻找的是一个默认包含几个不同级别的选项。

#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)

重复多次这样做非常乏味。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，我正在寻找可通过 proc 中的类、方式或类型语句获得的相同类型的功能，这意味着让我可以控制汇总级别并在一次调用中获得多个级别。

任何帮助表示赞赏。我知道我可以创建自己的函数，但希望有些东西已经存在。我也更愿意坚持使用 tidyverse 编程风格，尽管我并没有这样做。

4

6 回答 6

5

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
于 2019-06-25T17:39:11.557 回答
3

您可以编写一个summarize在ungrouped tibble 上执行相同操作的函数并将其 rbinds 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“总体”组的名称添加一些逻辑

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
于 2019-06-21T21:08:08.017 回答
2 
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 包（v0.3.0）于 2019-06-21 创建

于 2019-06-21T20:21:06.027 回答
2

一种方法，也是乏味但在一个较长的管道中，是将第二个汇总指令放入bind_rows.
该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，强制转换为字符向量
2：在 bind_rows_(x, .id) ：
绑定字符和因子向量，强制转换为字符向量 

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
于 2019-06-21T20:22:23.393 回答
2

只需在双数据集上应用一次所需功能的解决方案：

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

诀窍是使用新的组 ID（即Species）传递原始数据集：mutate(iris, Species = "Overall")

于 2019-06-21T21:02:03.280 回答
2

也许是这样的：

由于您想对同一输入（iris）执行不同的操作，最好map将不同的汇总函数应用于数据。 map_dfr使用组合列表输出bind_rows

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
于 2019-06-21T20:36:29.177 回答