前言

ggplot2 包含很多繪制線條的函數(shù)：大致可分為如下幾類：

• 連接線：折線(geom_line)、路徑線(geom_path)、階梯線(geom_step)

• 參考線：水平線(geom_hline)、豎直線(geom_vline)、斜線(geom_abline)

• 線段和曲線: geom_segment、geom_spoke、geom_curve

• 函數(shù)曲線: geom_function、stat_function

示例

1. 連接線

主要有三種連接線：

1. geom_path：按照它們?cè)跀?shù)據(jù)中出現(xiàn)的順序連接起來
2. geom_line：按 x 軸上變量的順序連接起來
3. geom_step：創(chuàng)建一個(gè)階梯圖，突出顯示數(shù)據(jù)的變化

常用參數(shù)：

• linetype：線條類型
• size：線條大小
• lineend：線端點(diǎn)樣式：round, butt, square
• linejoin：線連接點(diǎn)樣式：round, mitre, bevel
• arrow：使用 grid::arrow() 函數(shù)設(shè)置箭頭樣式

繪制一條簡(jiǎn)單的時(shí)間序列折線

ggplot(economics, aes(date, unemploy)) + geom_line()

繪制多條折線

economics_long %>% 
  subset(variable %in% c("uempmed", "unemploy")) %>%
  ggplot(aes(date, value01, colour = variable)) +
  geom_line()

翻轉(zhuǎn)線條

ggplot(economics, aes(unemploy, date)) + geom_line(orientation = "y")

如果我們更加關(guān)注 y 值的變化情況，可以使用 geom_step 繪制階梯圖

recent <- economics[economics$date > as.Date("2013-01-01"), ]

p1 <- ggplot(recent, aes(date, unemploy)) + geom_line()

p2 <- ggplot(recent, aes(date, unemploy)) + geom_step()

plot_grid(p1, p2)

而 geom_path 可以讓你探索兩個(gè)變量是如何隨著時(shí)間的推移而發(fā)生變化的

例如，失業(yè)率和個(gè)人儲(chǔ)蓄率隨時(shí)間的關(guān)系

esamp <- sample_n(economics, 10)
  
m <- ggplot(esamp, aes(unemploy/pop, psavert))

p1 <- m + geom_path()

p2 <- m + geom_path(aes(colour = as.numeric(date)))

plot_grid(p1, p2)

設(shè)置箭頭

c <- ggplot(economics, aes(x = date, y = pop))
c1 <- c + geom_line(arrow = arrow())

c2 <- c + geom_line(
  arrow = arrow(angle = 15, ends = "both", type = "closed")
)
plot_grid(c1, c2)

更改連接線及端點(diǎn)樣式

base <- tibble(x = 1:3, y = c(4, 1, 9)) %>%
  ggplot(aes(x, y))

b1 <- base + geom_path(size = 8)

b2 <- base + geom_path(size = 8, lineend = "round")

b3 <- base + geom_path(size = 8, lineend = "round", colour = "red")

b4 <- base + geom_path(size = 8, linejoin = "mitre", lineend = "butt")

plot_grid(b1, b2, b3, b4)

當(dāng)線條的中間有 NA 值時(shí)，則會(huì)有一個(gè)斷點(diǎn)

df <- data.frame(x = 1:5, y = c(1, 2, NA, 4, 5))
ggplot(df, aes(x, y)) + geom_point() + geom_line()

設(shè)置線條類型

economics_long %>% 
  subset(variable %in% c("uempmed", "unemploy")) %>%
  ggplot(aes(date, value01, colour = variable)) +
  geom_line(aes(linetype = factor(variable))) +
  scale_linetype_manual("variable", values = c(5, 3))

注意：無法同時(shí)設(shè)置漸變色與線條類型，下面的代碼將會(huì)報(bào)錯(cuò)

economics_long %>% 
  subset(variable %in% c("uempmed", "unemploy")) %>%
  ggplot(aes(date, value01, group = variable)) +
  geom_line(aes(colour = value01), linetype = 2)

2. 參考線

為圖形添加參考線對(duì)圖形的注釋非常有用，主要有水平、豎直和對(duì)角線三種參考線，對(duì)應(yīng)于三個(gè)函數(shù)：

• geom_hline: yintercept（y 軸截距）
• geom_vline: xintercept（x 軸截距）
• geom_abline: slope（斜率） 和 intercept（截距）

p <- ggplot(mtcars, aes(wt, mpg)) + geom_point()

# 使用固定值
p1 <- p + geom_vline(xintercept = 5)
# 使用向量
p2 <- p + geom_vline(xintercept = 1:5)
# 水平線
p3 <- p + geom_hline(yintercept = 20)
# 斜線
p4 <- p + geom_abline(intercept = 31, slope = -5)

plot_grid(p1, p2, p3, p4)

計(jì)算擬合曲線的截距和斜率，然后繪制直線

> coef(lm(mpg ~ wt, data = mtcars))
(Intercept)          wt 
  37.285126   -5.344472 
> p + geom_abline(intercept = 37, slope = -5)

更簡(jiǎn)單的方式是使用 geom_smooth 繪制擬合直線

p + geom_smooth(method = "lm", se = FALSE)

在繪制分面圖形的時(shí)候，可以為不同的分面繪制不同的直線

p <- ggplot(mtcars, aes(mpg, wt)) +
  geom_point() +
  facet_wrap(~ cyl)

mean_wt <- data.frame(cyl = c(4, 6, 8), wt = c(2.28, 3.11, 4.00))
p + geom_hline(aes(yintercept = wt), mean_wt)

也可以添加其他屬性

ggplot(mtcars, aes(mpg, wt, colour = wt)) +
  geom_point() +
  geom_hline(aes(yintercept = wt, colour = wt), mean_wt) +
  facet_wrap(~ cyl)

3. 線段和曲線

geom_segment 用于繪制兩個(gè)點(diǎn)之間的直線，geom_curve 用于繪制兩點(diǎn)的曲線。

兩個(gè)點(diǎn)通過四個(gè)參數(shù) (x, y) 和 (xend, yend) 指定坐標(biāo)。

例如，在散點(diǎn)圖中標(biāo)注兩點(diǎn)之間的連接線

b <- ggplot(mtcars, aes(wt, mpg)) +
  geom_point()

df <- data.frame(x1 = 2.320, x2 = 3.520, y1 = 22.8, y2 = 15.5)
b +
  geom_curve(aes(x = x1, y = y1, xend = x2, yend = y2, colour = "curve"), data = df) +
  geom_segment(aes(x = x1, y = y1, xend = x2, yend = y2, colour = "segment"), data = df)

設(shè)置不同的曲率

b1 <- b + geom_curve(aes(x = x1, y = y1, xend = x2, yend = y2), data = df, curvature = -0.2)

b2 <- b + geom_curve(aes(x = x1, y = y1, xend = x2, yend = y2), data = df, curvature = 0.9)

plot_grid(b1, b2)

添加箭頭

b + geom_curve(
  aes(x = x1, y = y1, xend = x2, yend = y2),
  data = df,
  arrow = arrow(length = unit(0.05, "npc"))
)

使用 geom_segment 通過設(shè)置線段大小來繪制直方圖

counts <- as.data.frame(table(x = rpois(100,5)))
counts$x <- as.numeric(as.character(counts$x))

ggplot(counts, aes(x, Freq)) +
  geom_segment(aes(xend = x, yend = 0), size = 10, lineend = "butt")

而 geom_spoke 是由坐標(biāo)點(diǎn) (x, y) 以及角度 (angle) 和 半徑 (radius) 指定的線段

df <- expand.grid(x = 1:10, y=1:10)
df$angle <- runif(100, 0, 2*pi)
df$speed <- runif(100, 0, sqrt(0.1 * df$x))

ggplot(df, aes(x, y)) +
  geom_point() +
  geom_spoke(aes(angle = angle), radius = 0.5)

看起來像是散落的大頭針一樣

設(shè)置可變的半徑

ggplot(df, aes(x, y)) +
  geom_point() +
  geom_spoke(aes(angle = angle, radius = speed))

4. 函數(shù)曲線

使用 geom_function 或 stat_function 可以繪制指定函數(shù)的曲線，例如

set.seed(2021)
ggplot(data.frame(x = rnorm(100)), aes(x)) +
  geom_density() +
  geom_function(fun = dnorm, colour = "red")

繪制了函數(shù)在數(shù)據(jù)范圍內(nèi)的曲線

也可以只指定范圍，來繪制無數(shù)據(jù)的函數(shù)曲線

base <- ggplot() + xlim(-5, 5)
base + geom_function(fun = dnorm)

設(shè)置函數(shù)的參數(shù)值

base + geom_function(fun = dnorm, args = list(mean = 2, sd = .5))

其底層原理是在一些離散點(diǎn)上執(zhí)行函數(shù)，然后用線將各函數(shù)值連接起來

b1 <- base + stat_function(fun = dnorm, geom = "point")

b2 <- base + stat_function(fun = dnorm, geom = "point", n = 20)

plot_grid(b1, b2)

下面兩行代碼效果是一樣的

b1 <- base + geom_function(fun = dnorm, n = 20)

b2 <- base + stat_function(fun = dnorm, geom = "line", n = 20)

plot_grid(b1, b2)

自定義函數(shù)

# 一張圖繪制不同的函數(shù)
p1 <- base +
  geom_function(aes(colour = "normal"), fun = dnorm) +
  geom_function(aes(colour = "t, df = 1"), fun = dt, args = list(df = 1))
# 使用匿名函數(shù)
p2 <- base + geom_function(fun = function(x) 0.5*exp(-abs(x)))
# 同上
p3 <- base + geom_function(fun = ~ 0.5*exp(-abs(.x)))
# 使用自定義函數(shù)，效果同上
f <- function(x) 0.5*exp(-abs(x))
p4 <- base + geom_function(fun = f)

plot_grid(p1, p2, p3, p4)

樣式圖

1. 路線圖

sample_n(mtcars, 10) %>%
  ggplot(aes(mpg, disp)) +
  geom_point(colour = "#69b3a2", na.rm = TRUE) +
  geom_segment(aes(xend = c(tail(mpg, n=-1), NA),
                   yend = c(tail(disp, n=-1), NA)),
               arrow = arrow(length=unit(0.3,"cm")),
               colour = "#69b3a2") +
  geom_text(aes(label = disp), hjust = 1.2) +
  theme_bw()

2. 坡度圖

library(ggrepel)

mpg %>% 
  group_by(year, manufacturer) %>%
  summarise(value = sum(displ)) %>%
  pivot_wider(names_from = year, values_from = value) %>%
  mutate(class = if_else((`1999` - `2008`) > 0, "#8dd3c7", "#bebada")) %>%
  ggplot() +
  geom_segment(aes(x = 1, xend = 2, y = `1999`, yend = `2008`, colour = class),
               size = .75, show.legend = FALSE) +
  geom_vline(xintercept = 1, linetype = "solid", size = 1, colour = "#ff7f00") +
  geom_vline(xintercept = 2, linetype = "solid", size = 1, colour = "#1f78b4") +
  geom_point(aes(x = 1, y = `1999`), size = 3, shape = 21, fill = "green") +
  geom_point(aes(x = 2, y = `2008`), size = 3, shape = 21, fill = "red") +
  scale_colour_manual(labels = c("Up", "Down"), values = c("#8dd3c7", "#bebada")) +
  xlim(.5, 2.5) +
  
  geom_text_repel(aes(x = 1, y = `1999`, label = `1999`), 
                  hjust = "left", size = 3.5) +
  geom_text_repel(aes(x = 2, y = `2008`, label = `2008`), 
                  hjust = "right", size = 3.5) +
  geom_text(aes(y = 1.03*max(max(`1999`), max(`2008`))), label = "1999", x = 1,
            size = 5, hjust = 1.2) +
  geom_text(aes(y = 1.03*max(max(`1999`), max(`2008`))), label = "2008", x = 2,
            size = 5, hjust = -.2) +
  theme_void()

在這個(gè)例子中，由于點(diǎn)有重疊的現(xiàn)象，導(dǎo)致標(biāo)簽也會(huì)重疊在一起。

所以我們使用了 ggplot2 的擴(kuò)展包 ggrepel 的 geom_text_repel 來繪制不重疊標(biāo)簽。