主页 / coding / 问题 / 77698630
Accepted
Cloft X
Asked: 2023-12-21 22:29:04 +0800 CST

如何按多个组进行分组并在 R 中的堆栈和闪避位置获取条形图？

  • 772

我想绘制以下数据：

df <- structure(list(age.cat = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 
1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 
2L, 2L), levels = c("0-5", "5-10", "10-15", "15-20", "20-25", 
"25-30", "30-35", "35-40", "40-45", "45-50", "50-55", "55-60", 
"60+"), class = "factor"), sex = c("0", "0", "0", "0", "0", "0", 
"1", "1", "1", "1", "1", "1", "0", "0", "0", "0", "0", "0", "1", 
"1", "1", "1", "1", "1"), activity_group = c("Food Process", 
"Household", "Labor", "Manufacture", "Other", "Resource Acq", 
"Food Process", "Household", "Labor", "Manufacture", "Other", 
"Resource Acq", "Food Process", "Household", "Labor", "Manufacture", 
"Other", "Resource Acq", "Food Process", "Household", "Labor", 
"Manufacture", "Other", "Resource Acq"), count = c(97L, 86L, 
12L, 75L, 0L, 68L, 62L, 115L, 15L, 88L, 0L, 68L, 153L, 70L, 2L, 
71L, 0L, 290L, 175L, 150L, 44L, 138L, 0L, 500L), total = c(146L, 
2586L, 34L, 81L, 2767L, 92L, 100L, 2462L, 27L, 95L, 2549L, 121L, 
240L, 2002L, 48L, 116L, 1573L, 362L, 256L, 2450L, 75L, 170L, 
2180L, 836L), prop = c(0.0169996494917631, 0.0150718541885734, 
0.00210304942166141, 0.0131440588853838, 0, 0.0119172800560813, 
0.0115801270078446, 0.0214792678371311, 0.00280164363093015, 
0.0164363093014569, 0, 0.0127007844602167, 0.0352453351762267, 
0.0161253167472932, 0.00046072333563695, 0.0163556784151117, 
0, 0.0668048836673577, 0.0293279705044411, 0.0251382604323781, 
0.0073738897268309, 0.0231271995977878, 0, 0.0837942014412603
)), class = c("grouped_df", "tbl_df", "tbl", "data.frame"), row.names = c(NA, 
-24L), groups = structure(list(age.cat = structure(c(1L, 1L, 
2L, 2L), levels = c("0-5", "5-10", "10-15", "15-20", "20-25", 
"25-30", "30-35", "35-40", "40-45", "45-50", "50-55", "55-60", 
"60+"), class = "factor"), sex = c("0", "1", "0", "1"), .rows = structure(list(
    1:6, 7:12, 13:18, 19:24), ptype = integer(0), class = c("vctrs_list_of", 
"vctrs_vctr", "list"))), class = c("tbl_df", "tbl", "data.frame"
), row.names = c(NA, -4L), .drop = TRUE))

head(df)
# A tibble: 6 × 6
# Groups:   age.cat, sex [1]
  age.cat sex   activity_group count total    prop
  <fct>   <chr> <chr>          <int> <int>   <dbl>
1 0-5     0     Food Process      97   146 0.0170 
2 0-5     0     Household         86  2586 0.0151 
3 0-5     0     Labor             12    34 0.00210
4 0-5     0     Manufacture       75    81 0.0131 
5 0-5     0     Other              0  2767 0      
6 0-5     0     Resource Acq      68    92 0.0119

prop我想使用（在 y 轴上）相对于age.cat（在 x 轴上）绘制条形图ggplot2。但我不知道如何按sex和进行分组activity_group。首先，我想在“dodge”位置进行分组sex，我使用以下代码完成了这一操作：

# Plot
prop %>%
  ggplot(aes(age.cat, prop, fill = sex)) +
  geom_col(position = "dodge")

但我也希望每个条形都向我显示propfor activity_groupin 位置“堆栈”。任何帮助表示赞赏，谢谢！

2 个回答

  1. Best Answer

    ggplot 中没有组合的闪避和堆叠位置选项。实现闪避堆叠外​​观的两种方法是：

    1. 偷偷摸摸的构面：将性别放在 x 轴上，并按年龄类别进行构面，然后将水平面板间距减小到 0，使其看起来好像嵌套了 x 轴类别
    2. 伪离散 x 轴：创建一个数字 x 轴并自己伪造躲避，使用中断和标签使其看起来像离散轴。

    第一个选项是最简单的：

    df %>%
  ggplot(aes(paste0('Sex: ', sex), prop, fill = activity_group)) +
  geom_col(position = "stack", alpha = 0.5, color = 'gray50') +
  facet_grid(.~age.cat, switch = 'x') +
  theme_minimal(base_size = 14) +
  scale_x_discrete('Age Category', expand = c(0.5, 0.5)) +
  scale_fill_brewer('Activity group', palette = 'Dark2') +
  labs(y = 'Proportion') +
  theme(strip.placement = 'outside',
        axis.text.x = element_text(face = 3),
        panel.grid.major.x = element_blank(),
        panel.spacing.x = unit(0, 'mm'))

    在此输入图像描述

    这是完整性的第二个选项：

    df %>%
  mutate(xpos = as.numeric(age.cat) + 0.3 * (as.numeric(sex) - 0.5)) %>%
  ggplot(aes(xpos, prop)) +
  geom_col(aes( fill = activity_group),
           position = "stack", alpha = 0.5, color = 'gray50') +
  geom_text(aes(y = -0.01, label = paste('Sex:', sex)), check_overlap = TRUE,
            fontface = 3, color = 'gray30') +
  theme_minimal(base_size = 14) +
  scale_x_continuous('Age Category',
                     breaks = 1:2, labels = levels(df$age.cat)[1:2]) +
  scale_fill_brewer('Activity group', palette = 'Dark2') +
  labs(y = 'Proportion') +
  theme(strip.placement = 'outside',
        axis.text.x = element_text(face = 3),
        panel.grid.major.x = element_blank(),
        panel.spacing.x = unit(0, 'mm'))

    在此输入图像描述

    • 2

  2. 还可以使用两个过滤geom_col调用并将它们调整到中断的每一侧（这里使用 alpha ，这sex不是很简洁）：

    library(tidyverse)

prop %>%
  ggplot(aes(age.cat, prop, fill = activity_group, alpha = sex)) +
  geom_col(data = filter(prop, sex == 0), position = "stack", just = 1, width = 0.4) +
  geom_col(data = filter(prop, sex == 1), position = "stack", just = 0, width = 0.4) +
  scale_alpha_manual(breaks = c("0", "1"), values = c(0.7, 1))

    • 2

相关问题