box

数据与公共样式

plant_growth 有一个对照组和两个处理组，每组恰好十株植物。显式固定组别顺序，并把样本量写进横轴标签。

library(ggplot2)
library(ggpubr)
library(biopalette)

d <- read.csv("content/tessera/data/csv/plant_growth.csv")
group_levels <- c("ctrl", "trt1", "trt2")
d$group <- factor(d$group, levels = group_levels)

group_n <- table(d$group)
group_labels <- setNames(
  paste0(group_levels, "\n(n=", as.integer(group_n[group_levels]), ")"),
  group_levels
)

group_colors <- setNames(
  get_palette("walter_white2", type = "qualitative")[1:3],
  group_levels
)

box_scale <- scale_y_continuous(
  breaks = seq(3.5, 6.5, 1),
  expand = expansion(mult = c(0.04, 0.06))
)

box_theme <- theme_pubr(base_size = 13, legend = "none") +
  theme(
    panel.grid.major.y = element_line(color = "#E5E3DC", linewidth = 0.35),
    panel.grid.major.x = element_blank(),
    axis.line = element_line(color = "#333330", linewidth = 0.45),
    axis.ticks = element_line(color = "#333330", linewidth = 0.4),
    plot.title = element_text(face = "bold", size = 15, hjust = 0),
    plot.subtitle = element_text(color = "grey35", hjust = 0),
    plot.margin = margin(14, 16, 12, 12)
  )

A · 基础分组箱线图

先只看统计结构。fill = NA 让箱体完全不填色，只保留轮廓、中位数和须；三个组已经由横轴位置区分，不需要图例。

#| fig: basic
#| fig-width: 7.5
#| fig-height: 5.2
ggplot(d, aes(group, weight)) +
  geom_boxplot(
    width = 0.56,
    fill = NA,
    color = "#333330",
    linewidth = 0.7
  ) +
  scale_x_discrete(labels = group_labels) +
  box_scale +
  labs(
    title = "Plant weight by treatment",
    subtitle = "Outline only · no box fill",
    x = NULL,
    y = "Dried weight"
  ) +
  box_theme

B · 箱体按组着色

当处理组颜色需要与同一份报告的其他图保持一致时，把 fill 映射到组别。边框、中位数和须仍统一使用深色，避免三套视觉规则同时变化。

#| fig: color
#| fig-width: 7.5
#| fig-height: 5.2
ggplot(d, aes(group, weight, fill = group)) +
  geom_boxplot(
    width = 0.56,
    alpha = 0.72,
    color = "#333330",
    linewidth = 0.7
  ) +
  scale_x_discrete(labels = group_labels) +
  scale_fill_manual(values = group_colors) +
  box_scale +
  labs(
    title = "Plant weight by treatment",
    subtitle = "One categorical color per treatment group",
    x = NULL,
    y = "Dried weight"
  ) +
  box_theme

C · 箱线图叠加全部原始点

这是小样本时优先使用的版本。箱线图关闭默认异常值点，全部观测统一交给下一层绘制；抖动只发生在横向，并绑定固定种子，重复导出时点的位置不会变化。

#| fig: points
#| fig-width: 7.5
#| fig-height: 5.2
ggplot(d, aes(group, weight, fill = group)) +
  geom_boxplot(
    width = 0.54,
    alpha = 0.58,
    color = "#333330",
    linewidth = 0.7,
    outlier.shape = NA
  ) +
  geom_point(
    shape = 21,
    size = 2.8,
    stroke = 0.65,
    color = "#333330",
    position = position_jitter(width = 0.1, height = 0, seed = 2026)
  ) +
  scale_x_discrete(labels = group_labels) +
  scale_fill_manual(values = group_colors) +
  box_scale +
  labs(
    title = "Plant weight by treatment",
    subtitle = "All 30 observations retained",
    x = NULL,
    y = "Dried weight"
  ) +
  box_theme

D · 箱体宽度与点大小

width 只改变箱体在分类轴上占多少空间，不改变 Q1、Q3、中位数或须；size 只改变原始点的视觉重量，不改变数据。两者都应按最终输出尺寸判断，而不是在 RStudio 的大预览窗里凭感觉设定。

下面把其他设置固定，只分别改变一个参数。宽度对比采用真正的空心彩色箱体：箱体内部不填色，轮廓和原始点使用组别颜色。窄箱体适合类别多、版面紧的图；宽箱体更有块面感，但容易挤满分类间距。小点让箱体摘要占主导，大点则更强调每个真实观测。

#| fig: sizing
#| fig-width: 10
#| fig-height: 7.6
comparison_theme <- theme_pubr(base_size = 11, legend = "none") +
  theme(
    panel.grid.major.y = element_line(color = "#E5E3DC", linewidth = 0.3),
    panel.grid.major.x = element_blank(),
    axis.line = element_line(color = "#333330", linewidth = 0.4),
    plot.title = element_text(face = "bold", size = 12, hjust = 0),
    plot.margin = margin(8, 8, 8, 8)
  )

box_only <- function(box_width, title) {
  ggplot(d, aes(group, weight, color = group)) +
    geom_boxplot(
      width = box_width,
      fill = NA,
      linewidth = 0.8,
      outlier.shape = NA
    ) +
    geom_point(
      size = 2.4,
      alpha = 0.82,
      position = position_jitter(width = 0.1, height = 0, seed = 2026)
    ) +
    scale_x_discrete(labels = group_levels) +
    scale_color_manual(values = group_colors) +
    box_scale +
    labs(title = title, x = NULL, y = "Dried weight") +
    comparison_theme
}

box_with_points <- function(point_size, title) {
  ggplot(d, aes(group, weight, fill = group)) +
    geom_boxplot(
      width = 0.54,
      alpha = 0.58,
      color = "#333330",
      linewidth = 0.7,
      outlier.shape = NA
    ) +
    geom_point(
      shape = 21,
      size = point_size,
      stroke = 0.65,
      color = "#333330",
      position = position_jitter(width = 0.1, height = 0, seed = 2026)
    ) +
    scale_x_discrete(labels = group_levels) +
    scale_fill_manual(values = group_colors) +
    box_scale +
    labs(title = title, x = NULL, y = "Dried weight") +
    comparison_theme
}

ggarrange(
  box_only(0.34, "Narrow boxes · width = 0.34"),
  box_only(0.76, "Wide boxes · width = 0.76"),
  box_with_points(1.7, "Small points · size = 1.7"),
  box_with_points(3.8, "Large points · size = 3.8"),
  ncol = 2,
  nrow = 2,
  align = "hv"
)

四种画法怎么选

1. 只需要紧凑统计摘要 → A。
2. 组别颜色需要跨图保持一致 → B。
3. 样本量小、读者需要看到真实数据 → C；这是本例最诚实、也最适合正式使用的版本。
4. 需要适配不同版面尺寸 → D；先定最终宽度，再调箱体 width 和散点 size。