ggplot2

ggplot2 参考

ggplot2 是一个使用图形语法生成可视化的 R 软件包。你可以通过数据、映射、图层、刻度、分面、坐标和主题组合绘图。

核心组件

数据和映射

ggplot(data = mpg, mapping = aes(x = cty, y = hwy))

• 数据：整洁数据框（行 = 观测值，列 = 变量）
• 映射：aes() 将数据列关联到视觉属性（x、y、颜色、大小等）

图层

图层使用几何对象、统计变换和位置调整来显示数据：

ggplot(mpg, aes(cty, hwy)) +
  geom_point() +
  geom_smooth(formula = y ~ x, method = "lm")

刻度

控制数据如何映射到视觉属性，并创建图例/坐标轴：

ggplot(mpg, aes(cty, hwy, colour = class)) +
  geom_point() +
  scale_colour_viridis_d()

分面

按变量将数据拆分到多个面板中：

ggplot(mpg, aes(cty, hwy)) +
  geom_point() +
  facet_grid(year ~ drv)

坐标

解读位置美学属性（笛卡尔坐标、极坐标、地图投影）：

ggplot(mpg, aes(cty, hwy)) +
  geom_point() +
  coord_fixed()

主题

控制与数据无关的视觉元素：

ggplot(mpg, aes(cty, hwy, colour = class)) +
  geom_point() +
  theme_minimal() +
  theme(legend.position = "top")

---

ggplot2 4.0 特性

ggplot2 4.0.0（2025 年 9 月）引入了 S7 类和多项重要新特性。

S7 迁移

使用 @ 而不是 $ 访问属性：

# ggplot2 4.0+
ggplot()@data

# Deprecated (still works temporarily)
ggplot()$data

更严格的类型验证：

element_text(hjust = "foo")
#> Error: @hjust must be <NULL>, <integer>, or <double>, not <character>

基于主题的图层默认值

墨色、纸色和强调色

内置主题支持 ink（前景色）、paper（背景色）和 accent（强调色）：

ggplot(mpg, aes(displ, hwy)) +
  geom_point() +
  geom_smooth(method = "lm", formula = y ~ x) +
  theme_gray(paper = "cornsilk", ink = "navy", accent = "tomato")

element_geom() 和 from_theme()

通过 theme(geom) 设置图层默认值：

ggplot(mpg, aes(class, displ)) +
  geom_boxplot(aes(colour = from_theme(accent))) +
  theme(geom = element_geom(
    accent = "tomato",
    paper = "cornsilk",
    bordertype = "dashed",
    borderwidth = 0.2,
    linewidth = 2,
    linetype = "solid"
  ))

主题调色板

在主题中设置默认调色板：

theme(
  palette.colour.continuous = c("chartreuse", "forestgreen"),
  palette.shape.discrete = c("triangle", "triangle open")
)

主题快捷方式

新的 theme_sub_*() 函数可减少冗长代码：

快捷方式	替换的前缀
theme_sub_axis()	axis.*
theme_sub_axis_x()	axis.*.x
theme_sub_axis_bottom()	axis.*.x.bottom
theme_sub_legend()	legend.*
theme_sub_panel()	panel.*
theme_sub_plot()	plot.*
theme_sub_strip()	strip.*

# Concise
theme_sub_axis_x(
  ticks = element_line(colour = "red"),
  ticks.length = unit(5, "mm")
) +
theme_sub_panel(
  widths = unit(5, "cm"),
  spacing.x = unit(5, "mm")
)

边距辅助函数

margin_auto(1)           # all sides = 1
margin_auto(1, 2)        # t/b=1, l/r=2
margin_auto(1, 2, 3)     # t=1, l/r=2, b=3
margin_part(r = 20)      # partial (NA inherits)

面板大小

theme_sub_panel(widths = unit(c(2, 3, 4), "cm"))  # per-panel
theme_sub_panel(widths = unit(9, "cm"))           # total area

标签

标签属性

带有 "label" 属性的变量会自动填充坐标轴标签：

attr(df$bill_dep, "label") <- "Bill depth (mm)"
ggplot(df, aes(bill_dep, bill_len)) + geom_point()

字典标签

dict <- c(species = "Species", bill_dep = "Bill depth (mm)")
ggplot(penguins, aes(bill_dep, bill_len, colour = species)) +
  geom_point() +
  labs(dictionary = dict)

函数标签

scale_colour_discrete(name = toupper)
guides(x = guide_axis(title = tools::toTitleCase))
labs(y = \(x) paste0(x, " variable"))

标签优先级（从低到高）：aes() < labs(dictionary) < 列属性 < labs() < scale_*(name) < guide_*(title)

命名中断点

scale_colour_discrete(breaks = c(
  "Pygoscelis adeliae" = "Adelie",
  "Pygoscelis papua" = "Gentoo"
))

离散刻度改进

# Palette for spacing
scale_x_discrete(palette = scales::pal_manual(c(1:3, 5:7)))

# Consistent limits across facets
scale_x_discrete(continuous.limits = c(1, 5))

# Minor breaks
scale_x_discrete(
  minor_breaks = scales::breaks_width(1, offset = 0.5),
  guide = guide_axis(minor.ticks = TRUE)
)

# Secondary axis
scale_x_discrete(sec.axis = dup_axis(
  name = "Counts",
  breaks = seq_len(7),
  labels = paste0("n = ", table(mpg$class))
))

位置美学属性

微调美学属性

geom_text(aes(nudge_x = sign(value) * 3, label = value))

避让顺序

ggplot(data, aes(x, y, fill = group)) +
  geom_boxplot(position = position_dodge(preserve = "single")) +
  aes(order = group)

分面

换行方向

facet_wrap(dir) 有 8 种方向选项：

dir	起始位置	填充方向
"lt"	左上	从左到右
"tl"	左上	从上到下
"lb"	左下	从左到右
"bl"	左下	从下到上
"rt"	右上	从右到左
"tr"	右上	从上到下
"rb"	右下	从右到左
"br"	右下	从下到上

自由空间

facet_wrap(~ island, scales = "free_x", space = "free_x")

图层布局

geom_point(colour = "grey", layout = "fixed_rows")  # repeat in rows
geom_point(layout = NULL)                            # use facet vars
annotate("text", label = "X", layout = 6)            # specific panel

选项：NULL、"fixed"、<integer>、"fixed_cols"、"fixed_rows"

样式设置

箱线图部分

geom_boxplot(
  whisker.linetype = "dashed",
  box.colour = "black",
  median.linewidth = 2,
  staplewidth = 0.5,
  staple.colour = "grey50"
)

小提琴图分位数

geom_violin(
  quantiles = c(0.1, 0.9),
  quantile.linetype = 1,
  quantile.colour = "red"
)

标签

geom_label(
  aes(linetype = factor(vs), linewidth = factor(am)),
  text.colour = "black",
  border.colour = "blue"
)

变化填充

geom_area(aes(fill = continuous_var))  # gradient (R 4.1+)

新统计方法

stat_manual()

make_centroids <- function(df) {
  transform(df, xend = mean(x), yend = mean(y))
}
stat_manual(geom = "segment", fun = make_centroids)

stat_connect()

geom_line(stat = "connect")           # stairstep
geom_ribbon(stat = "connect", alpha = 0.4)

# Custom connection shape
smooth <- cbind(x = seq(0, 1, length.out = 20)[-1],
                y = scales::rescale(plogis(x, 0.5, 0.1)))
stat_connect(connection = smooth)

坐标反转

coord_cartesian(reverse = "x")   # "y", "xy", "none"
coord_sf(reverse = "y")
coord_radial(reverse = "theta")  # "r", "thetar", "none"

弃用项

旧项	新项
fatten	median.linewidth / middle.linewidth
draw_quantiles	quantiles
geom_errorbarh()	geom_errorbar(orientation = "y")
coord_trans()	coord_transform()
borders()	annotation_borders()
facet_wrap(as.table)	facet_wrap(dir)
theme_get/set/update/replace()	get/set/update/replace_theme()
last_plot()	get_last_plot()
layer_data/grob/scales()	get_layer_data/grob()、get_panel_scales()