density

数据与公共样式

airquality 的 Temp 没有缺失，五个月各有 30 或 31 天。月份显式固定为 May–September，所有图使用相同横轴和同一档基础带宽。

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

d <- read.csv("content/tessera/data/csv/airquality.csv", na.strings = "NA")
month_levels <- 5:9
month_labels <- c("May", "June", "July", "August", "September")
d$month <- factor(
  d$Month,
  levels = month_levels,
  labels = month_labels,
  ordered = TRUE
)

month_colors <- setNames(
  get_palette("walter_white2", type = "qualitative")[1:5],
  month_labels
)

density_scale <- scale_x_continuous(
  breaks = seq(55, 95, 10),
  expand = expansion(mult = c(0.03, 0.04))
)

density_theme <- theme_pubr(base_size = 13) +
  theme(
    panel.grid.major.y = element_blank(),
    panel.grid.major.x = element_line(color = "#E5E3DC", linewidth = 0.35),
    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),
    legend.title = element_text(face = "bold"),
    plot.margin = margin(14, 16, 12, 12)
  )

A · 单组密度

先忽略月份，只看 153 天温度的整体分布。adjust = 1 使用 ggplot2 计算的默认带宽；填充只帮助看面积，不承担分组含义。

#| fig: basic
#| fig-width: 8
#| fig-height: 5.2
ggplot(d, aes(Temp)) +
  geom_density(
    adjust = 1,
    fill = unname(month_colors[1]),
    color = "#333330",
    alpha = 0.72,
    linewidth = 0.75
  ) +
  density_scale +
  labs(
    title = "Daily temperature distribution",
    subtitle = "New York · May–September 1973 · n = 153",
    x = "Temperature (°F)",
    y = "Density"
  ) +
  density_theme

B · 分组重叠

把月份映射给 fill 和 color 可以直接比较共同坐标上的位置差异。透明度降低到 0.24 才能看见后画的曲线，但重叠区已经不是原始色板颜色；五组也接近这种画法的可读上限。

#| fig: overlay
#| fig-width: 8
#| fig-height: 5.6
ggplot(d, aes(Temp, fill = month, color = month)) +
  geom_density(adjust = 0.9, alpha = 0.24, linewidth = 0.8) +
  density_scale +
  scale_fill_manual(values = month_colors) +
  scale_color_manual(values = month_colors) +
  labs(
    title = "Overlaid monthly densities",
    subtitle = "Transparency reveals intersections but changes the palette",
    x = "Temperature (°F)",
    y = "Density",
    fill = "Month",
    color = "Month"
  ) +
  density_theme +
  theme(legend.position = "right")

C · 共同坐标的分面

分面消除遮挡，同时保留相同的横轴与纵轴。scales = "fixed" 不应省略：只有共同尺度下，位置、宽度和峰高才可以横向比较。

#| fig: facets
#| fig-width: 8.5
#| fig-height: 8.5
ggplot(d, aes(Temp, fill = month, color = month)) +
  geom_density(adjust = 0.9, alpha = 0.76, linewidth = 0.75, show.legend = FALSE) +
  facet_wrap(~ month, ncol = 1, scales = "fixed") +
  density_scale +
  scale_fill_manual(values = month_colors) +
  scale_color_manual(values = month_colors) +
  labs(
    title = "One density per month",
    subtitle = "Fixed axes preserve comparisons across panels",
    x = "Temperature (°F)",
    y = "Density"
  ) +
  density_theme +
  theme(
    strip.background = element_blank(),
    strip.text = element_text(face = "bold", hjust = 0)
  )

D · 分层密度

月份有明确顺序时，分层密度比五条透明曲线更清楚。scale = 0.86 让相邻轮廓留出间隙，不发生颜色混合；这也是 Palette Lab 使用的主版本。

#| fig: ridgeline
#| fig-width: 9
#| fig-height: 6.5
ggplot(d, aes(Temp, month, fill = month)) +
  geom_density_ridges(
    adjust = 0.9,
    scale = 0.86,
    rel_min_height = 0.01,
    color = "#333330",
    linewidth = 0.55,
    alpha = 0.92,
    show.legend = FALSE
  ) +
  density_scale +
  scale_fill_manual(values = month_colors) +
  labs(
    title = "Temperature shifts through the summer",
    subtitle = "Five independent density layers · no overlap mixing",
    x = "Temperature (°F)",
    y = NULL
  ) +
  theme_pubr(base_size = 13, legend = "none") +
  theme(
    panel.grid.major.x = element_line(color = "#E5E3DC", linewidth = 0.35),
    panel.grid.major.y = element_blank(),
    axis.line.y = element_blank(),
    axis.ticks.y = element_blank(),
    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)
  )

E · 带宽敏感性

固定数据与样式，只改变 adjust。较小值保留许多局部峰，较大值把它们合并；如果核心判断只在某一格成立，就不应把它写成稳定结论。

#| fig: bandwidth
#| fig-width: 11
#| fig-height: 4.2
bandwidth_plot <- function(adjust_value) {
  ggplot(d, aes(Temp)) +
    geom_density(
      adjust = adjust_value,
      fill = unname(month_colors[1]),
      color = "#333330",
      alpha = 0.72,
      linewidth = 0.65
    ) +
    density_scale +
    labs(
      title = paste0("adjust = ", adjust_value),
      x = "Temperature (°F)",
      y = NULL
    ) +
    theme_pubr(base_size = 11, legend = "none") +
    theme(
      panel.grid.major.x = element_line(color = "#E5E3DC", linewidth = 0.3),
      panel.grid.major.y = element_blank(),
      plot.title = element_text(face = "bold", size = 12, hjust = 0),
      plot.margin = margin(8, 8, 8, 8)
    )
}

ggarrange(
  bandwidth_plot(0.55),
  bandwidth_plot(1),
  bandwidth_plot(1.6),
  ncol = 3,
  align = "hv"
)

五种画法怎么选

1. 只看一个变量的整体形状 → A。
2. 只有两三组且重叠不严重 → B。
3. 需要最稳妥地逐组比较 → C。
4. 组别有自然顺序、希望一张图紧凑展示 → D。
5. 准备解释峰数或分布细节 → 先用 E 检查结论对带宽是否稳定。

evanverse::plot_density() 把 A–C 中最常用的 group_col、facet_col、alpha、adjust 和 palette 封装成统一接口。Recipe 没有依赖它，因为这里需要逐层展示标准 ggplot2 语法；其参数边界与分组逻辑仍是这份配方的设计参考。