ggplot2包|直方图

专题介绍：R是一种广泛用于数据分析和统计计算的强大语言，于上世纪90年代开始发展起来。得益于全世界众多爱好者的无尽努力，大家继而开发出了一种基于R但优于R基本文本编辑器的R Studio（用户的界面体验更好）。也正是由于全世界越来越多的数据科学社区和用户对R包的慷慨贡献，让R语言在全球范围内越来越流行。其中一些R包，例如MASS，SparkR， ggplot2，使数据操作,可视化和计算功能越来越强大。R是用于统计分析、绘图的语言和操作环境。R是属于GNU系统的一个自由、免费、源代码开放的软件，它是一个用于统计计算和统计制图的优秀工具。R作为一种统计分析软件，是集统计分析与图形显示于一体的。它可以运行于UNIX、Windows和Macintosh的操作系统上，而且嵌入了一个非常方便实用的帮助系统，相比于其他统计分析软件，R的学术性开发比较早，适合生物学和医学等学术学科的科研人员使用。

是新朋友吗？记得先点R语言关注我哦～

《R语言实践》专栏·第6篇

文 | RUser

7121字 |8分钟阅读

【R语言】开通了R语言群，大家相互学习和交流，请扫描下方二维码，备注：姓名-R群，我会邀请你入群，一起进步和成长。

伙伴们，我最近在重温李宏毅老师的机器学课程，并且做了一份学习笔记。你若是想学习和应用机器学习，强烈推荐你进入数据科学与人工智能公众号，查看我的学习笔记，亮点是1）点击阅读原文，就可以在手机上非常方便地观看课程视频；2）加入配套的机器学习群，参与讨论和交流，让我们一起来学习和应用机器学习。

我们先回顾一下，我已经总结和分享了ggplot2包绘制折线图、面积图、柱形图、散点图和气泡图，相关文章如下：

我们在做可视化的时候，根据变量的类型、变量的个数、变量的关系，选择合适可视化图形，以达成有效、简洁、美丽地表达信息和结果。

本文介绍ggplot2包绘制直方图。直方图，大家不陌生，它是一种常用图形，用于观察和表示单个连续变量的分布。我们绘制直方图的时候，首先要对数据分组或者分箱，然后统计每个组的频数，最后绘制成图形。直方图的作用1）能够显示各组频数或数量分布的情况；2）易于显示各组频数或数量的差异。直方图还可以发现那些数据比较集中，异常和孤立的数据分布在何处。直方图主要应用场景1）观察单一连续变量的分布；2）观察异常和孤立数据。

利用ggplot2包绘制直方图，步骤如下：

第一步：R包管理

if (!require("pacman")) {  install.packages("pacman")  require("pacman")}p_load(datasets, ggplot2, ggthemes, dplyr, grid, RColorBrewer)

第二步：数据加载和理解

使用data()函数导R语言自带数据集airquality。

使用glimpse()函数观察数据结构，summary()函数了解数据概况，sample_frac()函数做随机按比例检视数据。

data(airquality)glimpse(airquality)summary(airquality)sample_frac(airquality,0.1)

第三步：逐步绘制直方图

1）基本直方图

p1 <- ggplot(airquality, aes(x = Ozone)) +   geom_histogram()p1

2）添加正态密度曲线

p2 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..density..)) +  stat_function(fun = dnorm, colour = "red",                args = list(mean = mean(airquality$Ozone, na.rm = TRUE),                            sd = sd(airquality$Ozone, na.rm = TRUE)))p2

3）把密度分布改成频数，效果和基本直方图一样

p3 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..))p3

4）调整分组宽度

p4 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5)p4

5）调整轴标签

5.1）一行展示

p5 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone in parts per billion") +  scale_y_continuous(name = "Count")p5

5.2）换行展示

p5_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion") +  scale_y_continuous(name = "Count")p5_1

6）修改x轴的刻度和范围

p6 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25),                      limits = c(0, 175)) +  scale_y_continuous(name = "Count")p6

7）添加标题

p7 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25),                      limits = c(0, 175)) +  scale_y_continuous(name = "Count")  +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p7

8）调整柱子的颜色

barfill = "gold1" #填充的颜色barlines = "black" #柱子四周的颜色p8 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p8

或者

通过HEX编码

barfill <- "#4271AE"barlines <- "#1F3552"p8_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p8_1

9）颜色渐变

通过把aes(y = ..count..)改成aes(fill = ..count..)即可

p9 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(fill = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p9

或者

使用scale_fill_gradient()美化渐变颜色

p9_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(fill = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  scale_fill_gradient("Count", low = "blue", high = "red")p9_1

10）字体配置

windowsFonts(  # 中文字体  lishu = windowsFont(family = "LiSu"),            # 隶书  yahei = windowsFont(family = "Microsoft YaHei"), # 微软雅黑  xinwei = windowsFont(family = "STXingwei"),      # 华文新魏  kaiti = windowsFont(family = "KaiTi"),           # 楷体  heiti = windowsFont(family = "SimHei"),          # 黑体  # 英文字体  arial = windowsFont(family = "Arial"),             # Arial字体  newman = windowsFont(family = "Times New Roman"),  #Times New Roman字体     hand = windowsFont(family = "Lucida Calligraphy"), # Lucida手写体  Helvetica = windowsFont(family = "Helvetica")      # 印刷体)

11）主题风格装饰

主题一：经济学主题（我很喜欢的一种风格）

p11_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  theme_economist() + scale_fill_economist() +  theme(axis.line.x = element_line(size = .5, colour = "black"),        axis.title = element_text(size = 12),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.text = element_text(size = 10),        text = element_text(family = "arial"),        plot.title = element_text(family = "arial"))p11_1

主题二：自定义风格

p11_2 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 colour = "black", fill = "#56B4E9") +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  theme(axis.line.x = element_line(size = 1, colour = "black"),        axis.line.y = element_line(size = 1, colour = "black"),        axis.text.x = element_text(colour = "black", size = 10),        axis.text.y = element_text(colour = "black", size = 10),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_blank(),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(family = "Helvetica"),        text = element_text(family = "Helvetica"))p11_2

12）添加一个cut-off的直线

p12 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 colour = "black", fill = "#56B4E9") +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  geom_vline(xintercept = 75, size = 1, colour = "#FF3721",             linetype = "dashed") +  theme(axis.line.x = element_line(size = 1, colour = "black"),        axis.line.y = element_line(size = 1, colour = "black"),        axis.text.x = element_text(colour = "black", size = 10),        axis.text.y = element_text(colour = "black", size = 10),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_blank(),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(family = "Helvetica"),        text = element_text(family = "Helvetica"))p12

13）多个直方图对比观察

13.1）分面板观察

p13_1 <- ggplot(airquality_trimmed, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  facet_grid(. ~ Month.f, scales = "free") +  theme(panel.border = element_rect(colour = "black", fill = NA, size = .5),        axis.text.x = element_text(colour = "black", size = 9),        axis.text.y = element_text(colour = "black", size = 9),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_line(colour = "#d3d3d3"),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(size = 14, family = "yahei", face = "bold"),        text = element_text(family = "yahei"))p13_1

13.2）在同一个图形里面观察

p13_2 <- ggplot(airquality_trimmed, aes(x = Ozone, fill = Month.f)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 position = "identity", alpha = 0.75) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  scale_fill_brewer(palette = "Accent") +  theme(panel.border = element_rect(colour = "black", fill = NA, size = .5),        axis.text.x = element_text(colour = "black", size = 9),        axis.text.y = element_text(colour = "black", size = 9),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_line(colour = "#d3d3d3"),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(size = 14, family = "yahei", face = "bold"),        text = element_text(family = "yahei"))p13_2

14）图例管理

p14 <- ggplot(airquality_trimmed, aes(x = Ozone, fill = Month.f)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 position = "identity", alpha = 0.75) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  scale_fill_brewer(palette = "Accent") +  theme(panel.border = element_rect(colour = "black", fill = NA, size = .5),        axis.text.x = element_text(colour = "black", size = 9),        axis.text.y = element_text(colour = "black", size = 9),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_line(colour = "#d3d3d3"),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(size = 14, family = "yahei", face = "bold"),        text = element_text(family = "yahei")) +  labs(fill='Month')p14

关于直方图的绘制，你有什么问题，请留言。

加入R语言群，一起学习更多R语言知识和技能。

你若是要找数据类的工作，或者要招聘数据类人才，可以看下公众号数据人才，它是一个数据人才助手。

附录：完整代码

##############直方图#############
# 1 R包管理if (!require("pacman")) {  install.packages("pacman")  require("pacman")}p_load(datasets, ggplot2, ggthemes, dplyr, grid, RColorBrewer)
# 2 数据加载和理解data(airquality)glimpse(airquality)summary(airquality)sample_frac(airquality,0.1)
# 3 逐步绘制直方图# 1）基本直方图p1 <- ggplot(airquality, aes(x = Ozone)) +   geom_histogram()p1
# 2) 添加正态密度曲线p2 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..density..)) +  stat_function(fun = dnorm, colour = "red",                args = list(mean = mean(airquality$Ozone, na.rm = TRUE),                            sd = sd(airquality$Ozone, na.rm = TRUE)))p2
# 3）把分布密度改成频数p3 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..))p3
# 4）调整分组宽度p4 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5)p4
# 5）调整轴标签p5 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone in parts per billion") +  scale_y_continuous(name = "Count")p5# 或者p5_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion") +  scale_y_continuous(name = "Count")p5_1
# 6) 修改x轴的刻度p6 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25),                      limits = c(0, 175)) +  scale_y_continuous(name = "Count")p6
# 7）添加标题p7 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25),                      limits = c(0, 175)) +  scale_y_continuous(name = "Count")  +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p7
# 8）改变柱子的颜色barfill = "gold1" #填充的颜色barlines = "black" #柱子四周的颜色p8 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p8# 或者barfill <- "#4271AE"barlines <- "#1F3552"p8_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p8_1
# 9) 颜色渐变p9 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(fill = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation")p9# 或者p9_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(fill = ..count..), binwidth = 5) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  scale_fill_gradient("Count", low = "blue", high = "red")p9_1
# 10) 字体配置windowsFonts(  # 中文字体  lishu = windowsFont(family = "LiSu"),            # 隶书  yahei = windowsFont(family = "Microsoft YaHei"), # 微软雅黑  xinwei = windowsFont(family = "STXingwei"),      # 华文新魏  kaiti = windowsFont(family = "KaiTi"),           # 楷体  heiti = windowsFont(family = "SimHei"),          # 黑体  # 英文字体  arial = windowsFont(family = "Arial"),             # Arial字体  newman = windowsFont(family = "Times New Roman"),  #Times New Roman字体     hand = windowsFont(family = "Lucida Calligraphy"), # Lucida手写体  Helvetica = windowsFont(family = "Helvetica")      # 印刷体) 

# 11）主题风格装饰p11_1 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 5,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  theme_economist() + scale_fill_economist() +  theme(axis.line.x = element_line(size = .5, colour = "black"),        axis.title = element_text(size = 12),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.text = element_text(size = 10),        text = element_text(family = "arial"),        plot.title = element_text(family = "arial"))p11_1
# 自定义风格p11_2 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 colour = "black", fill = "#56B4E9") +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  theme(axis.line.x = element_line(size = 1, colour = "black"),        axis.line.y = element_line(size = 1, colour = "black"),        axis.text.x = element_text(colour = "black", size = 10),        axis.text.y = element_text(colour = "black", size = 10),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_blank(),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(family = "Helvetica"),        text = element_text(family = "Helvetica"))p11_2
# 12) 添加一个cut off的直线p12 <- ggplot(airquality, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 colour = "black", fill = "#56B4E9") +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  geom_vline(xintercept = 75, size = 1, colour = "#FF3721",             linetype = "dashed") +  theme(axis.line.x = element_line(size = 1, colour = "black"),        axis.line.y = element_line(size = 1, colour = "black"),        axis.text.x = element_text(colour = "black", size = 10),        axis.text.y = element_text(colour = "black", size = 10),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_blank(),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(family = "Helvetica"),        text = element_text(family = "Helvetica"))p12
# 13) 多个直方图对比观察# 13.1）分面板观察# 数据处理airquality_trimmed <- airquality %>%  filter(Month %in% c(5,7)) %>%  mutate(Month.f = factor(Month,                          labels = c("May", "July")))p13_1 <- ggplot(airquality_trimmed, aes(x = Ozone)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 colour = barlines, fill = barfill) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  facet_grid(. ~ Month.f, scales = "free") +  theme(panel.border = element_rect(colour = "black", fill = NA, size = .5),        axis.text.x = element_text(colour = "black", size = 9),        axis.text.y = element_text(colour = "black", size = 9),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_line(colour = "#d3d3d3"),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(size = 14, family = "yahei", face = "bold"),        text = element_text(family = "yahei"))p13_1# 同一个图形观察p13_2 <- ggplot(airquality_trimmed, aes(x = Ozone, fill = Month.f)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 position = "identity", alpha = 0.75) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  scale_fill_brewer(palette = "Accent") +  theme(panel.border = element_rect(colour = "black", fill = NA, size = .5),        axis.text.x = element_text(colour = "black", size = 9),        axis.text.y = element_text(colour = "black", size = 9),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_line(colour = "#d3d3d3"),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(size = 14, family = "yahei", face = "bold"),        text = element_text(family = "yahei"))p13_2
# 14）图例管理p14 <- ggplot(airquality_trimmed, aes(x = Ozone, fill = Month.f)) +  geom_histogram(aes(y = ..count..), binwidth = 10,                 position = "identity", alpha = 0.75) +  scale_x_continuous(name = "Mean ozone innparts per billion",                     breaks = seq(0, 175, 25), limits = c(0, 175)) +  scale_y_continuous(name = "Count") +  labs(title = "Frequency histogram of mean ozone",       subtitle = "Source: New York State Department of Conservation") +  scale_fill_brewer(palette = "Accent") +  theme(panel.border = element_rect(colour = "black", fill = NA, size = .5),        axis.text.x = element_text(colour = "black", size = 9),        axis.text.y = element_text(colour = "black", size = 9),        legend.position = "bottom",        legend.direction = "horizontal",        legend.box = "horizontal",        legend.key = element_blank(),        panel.grid.major = element_line(colour = "#d3d3d3"),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(size = 14, family = "yahei", face = "bold"),        text = element_text(family = "yahei")) +  labs(fill='Month')p14