3

我一直在阅读有关 expss 包的两个标题表here和here，但在线代码对我不起作用。我的想法是创建一个与此图像非常相似的表：

在此处输入图像描述

数据框是：

df <- data.frame(Categoria = c("gender", "gender" , "gender", "gender", "gender", "gender", 
                                 "religion", "religion", "religion", "religion", "religion",
                                 "religion", "religion", "religion", "religion", "religion", 
                                 "religion", "religion"),
                 Opcoes_da_categoria = c("Mulher", "Homem", "Mulher", "Homem", "Mulher", 
                                           "Homem", "Outra religião", "Católico", "Agnóstico ou ateu",
                                           "Evangélico", "Outra religião", "Católico", 
                                           "Agnóstico ou ateu", "Evangélico", "Outra religião",
                                           "Católico", "Agnóstico ou ateu", "Evangélico"),
                 Resposta = c("A Favor", "A Favor", "Contra",  "Contra",  "Não sei", "Não sei",
                              "A Favor", "A Favor", "A Favor", "A Favor", "Contra", "Contra",
                              "Contra", "Contra", "Não sei", "Não sei", "Não sei", "Não sei"),
                 value_perc = c(65, 50, 33, 43, 2, 7, 67, 64, 56, 28, 31, 34, 35, 66, 2, 2, 10, 5))

我创建两个标题表的代码如下，但由于以下问题，它无法正常工作：

  • 该表应该有两个标题
  • 列名不应出现在表格中
  • 该值不应该有十进制大小写
library(expss)

my_table <- df %>%
  tab_cells(Resposta) %>%
  tab_weight(value_perc) %>% 
  tab_cols(Opcoes_da_categoria, Categoria) %>%
  tab_stat_cpct(total_label = NULL) %>%
  tab_pivot()

library(gridExtra)

png("my_table.png", height = 50*nrow(my_table), width = 200*ncol(my_table))
grid.table(my_table)
dev.off()

在此处输入图像描述

4

3 回答 3

2

我不知道expss，但最近使用了 flextable，发现它很好。远离这方面的专家，我设法制作了一张漂亮的桌子，它接近你想要的。从您的 DF 开始，必须进行一些更改，以使 DF 具有您的表格所需的格式。通过提取名称的部分 before 重命名 col-names _。构建了描述 col 和 header-names 依赖关系的DF类型。（可以在上面的链接中找到）。然后是flextable部分，它首先构建flextable然后应用typology和其他格式化命令。

由此产生的结果，显示了所附图片。


library(tidyverse)
library(flextable)
#> 
#> Attache Paket: 'flextable'
#> The following object is masked from 'package:purrr':
#> 
#>     compose
df <- data.frame(
  Categoria = c(
    "gender", "gender", "gender", "gender", "gender", "gender",
    "religion", "religion", "religion", "religion", "religion",
    "religion", "religion", "religion", "religion", "religion",
    "religion", "religion"
  ),
  Opcoes_da_categoria = c(
    "Mulher", "Homem", "Mulher", "Homem", "Mulher",
    "Homem", "Outra religião", "Católico", "Agnóstico ou ateu",
    "Evangélico", "Outra religião", "Católico",
    "Agnóstico ou ateu", "Evangélico", "Outra religião",
    "Católico", "Agnóstico ou ateu", "Evangélico"
  ),
  Resposta = c(
    "A Favor", "A Favor", "Contra", "Contra", "Não sei", "Não sei",
    "A Favor", "A Favor", "A Favor", "A Favor", "Contra", "Contra",
    "Contra", "Contra", "Não sei", "Não sei", "Não sei", "Não sei"
  ),
  value_perc = c(65, 50, 33, 43, 2, 7, 67, 64, 56, 28, 31, 34, 35, 66, 2, 2, 10, 5)
)


# adjust your df to match cols and names with tidyvers
dfa <- df %>%
  pivot_wider(names_from =c('Opcoes_da_categoria', 'Categoria'), values_from = 'value_perc')
nam <- str_extract(colnames(dfa),'^[^_]+')
colnames(dfa) <- nam

typology <- data.frame(
  col_keys = c( "Resposta",
                "Mulher", "Homem",
                "Outra religião", "Católico",
                "Agnóstico ou ateu", "Evangélico"),
  what = c("", "Genero", "Genero", "Religio",
           "Religio", "Religio", 'Religio'),
  measure = c( "Resposta", 
               "Mulher", "Homem",
               "Outra religião", "Católico",
               "Agnóstico ou ateu", "Evangélico"),
  stringsAsFactors = FALSE )

library(officer) # needed for making border
dftab <- flextable::flextable(dfa)

border_v = fp_border(color="gray")
dftab <- dftab %>% 
  set_header_df(mapping = typology, key = "col_keys" ) %>% 
  merge_h(part = "header") %>% 
  merge_v(part = "header") %>% 
  theme_booktabs() %>% 
  vline(border = border_v, j =3, part = 'body') %>% 
  vline(border = border_v, j =3, part = 'header')
print(dftab)
#> a flextable object.
#> col_keys: `Resposta`, `Mulher`, `Homem`, `Outra religião`, `Católico`, `Agnóstico ou ateu`, `Evangélico` 
#> header has 2 row(s) 
#> body has 3 row(s) 
#> original dataset sample: 
#>   Resposta Mulher Homem Outra religião Católico Agnóstico ou ateu Evangélico
#> 1  A Favor     65    50             67       64                56         28
#> 2   Contra     33    43             31       34                35         66
#> 3  Não sei      2     7              2        2                10          5

在此处输入图像描述

于 2020-06-22T17:20:43.810 回答
1

这是一个灵活的kable解决方案，只要您可以将数据转换为宽格式，就应该适应不同的表。希望它有所帮助-如果您有任何问题，请告诉我！

library(dplyr)
library(tidyr)
library(knitr)
library(kableExtra)

df_wide <- df %>% # transform data to wide format, "drop" name for Resposta
  pivot_wider(names_from = c(Categoria, Opcoes_da_categoria), 
              values_from = value_perc, names_sep = "_") %>%
  rename(" " = Resposta)

cols <- sub("(.*?)_(.*)", "\\2", names(df_wide)) # grab everything after the _
grps <- sub("(.*?)_(.*)", "\\1", names(df_wide)) # grab everything before the _

df_wide %>%
  kable(col.names = cols) %>% 
  kable_styling(c("striped"), full_width = FALSE) %>% # check out ?kable_styling for other options
  add_header_above(table(grps)[unique(grps)]) # unique makes sure it is the correct order
于 2020-06-22T17:34:57.120 回答
0

您尝试在 RStudio数据查看器中查看表格。它将 expss 表显示为通常的 data.frames。

您可以expss通过设置在 RStudio 查看器（不是数据查看器）中查看表expss_output_viewer()：

df <- data.frame(Categoria = c("gender", "gender" , "gender", "gender", "gender", "gender", 
                               "religion", "religion", "religion", "religion", "religion",
                               "religion", "religion", "religion", "religion", "religion", 
                               "religion", "religion"),
                 Opcoes_da_categoria = c("Mulher", "Homem", "Mulher", "Homem", "Mulher", 
                                         "Homem", "Outra religião", "Católico", "Agnóstico ou ateu",
                                         "Evangélico", "Outra religião", "Católico", 
                                         "Agnóstico ou ateu", "Evangélico", "Outra religião",
                                         "Católico", "Agnóstico ou ateu", "Evangélico"),
                 Resposta = c("A Favor", "A Favor", "Contra",  "Contra",  "Não sei", "Não sei",
                              "A Favor", "A Favor", "A Favor", "A Favor", "Contra", "Contra",
                              "Contra", "Contra", "Não sei", "Não sei", "Não sei", "Não sei"),
                 value_perc = c(65, 50, 33, 43, 2, 7, 67, 64, 56, 28, 31, 34, 35, 66, 2, 2, 10, 5))

library(expss)

my_table <- df %>%
    tab_cells(Resposta) %>%
    tab_weight(value_perc) %>% 
    tab_cols(Opcoes_da_categoria, Categoria) %>%
    tab_stat_cpct(total_label = NULL) %>%
    tab_pivot()

expss_digits(0) # turn off decimal digits
expss_output_viewer() # turn on displaying tables in the viewer
my_table

expss_output_default() # turn off displaying tables in the viewer

此代码给出以下结果： 在此处输入图像描述

如果您真的想在数据查看器中显示表格，您可以将表格转换为通常的 data.frame。有一个特殊的命令 - split_table_to_df：

View(split_table_to_df(my_table))

结果： 在此处输入图像描述

更新：

df <- data.frame(Categoria = c("gender", "gender" , "gender", "gender", "gender", "gender", 
                               "religion", "religion", "religion", "religion", "religion",
                               "religion", "religion", "religion", "religion", "religion", 
                               "religion", "religion"),
                 Opcoes_da_categoria = c("Mulher", "Homem", "Mulher", "Homem", "Mulher", 
                                         "Homem", "Outra religião", "Católico", "Agnóstico ou ateu",
                                         "Evangélico", "Outra religião", "Católico", 
                                         "Agnóstico ou ateu", "Evangélico", "Outra religião",
                                         "Católico", "Agnóstico ou ateu", "Evangélico"),
                 Resposta = c("A Favor", "A Favor", "Contra",  "Contra",  "Não sei", "Não sei",
                              "A Favor", "A Favor", "A Favor", "A Favor", "Contra", "Contra",
                              "Contra", "Contra", "Não sei", "Não sei", "Não sei", "Não sei"),
                 value_perc = c(65, 50, 33, 43, 2, 7, 67, 64, 56, 28, 31, 34, 35, 66, 2, 2, 10, 5))

library(expss)

my_table <- df %>%
    apply_labels(
        Resposta = "",
        Opcoes_da_categoria = "",
        Categoria = ""
    ) %>% 
    tab_cells(Resposta) %>%
    tab_weight(value_perc) %>% 
    tab_cols(Categoria, Opcoes_da_categoria) %>%
    tab_stat_cpct(total_row_position = "none") %>%
    tab_pivot()

expss_digits(0) # turn off decimal digits
View(my_table)

在此处输入图像描述

于 2020-06-22T21:38:37.673 回答