ggplot2包|散点图

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5篇

文 | RUser

2841字 |6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：R群，我会邀请你入群，一起进步和成长。

朋友们，实际工作中，你们用散点图吗？散点图一般用来做什么？散点图的变体有哪些？请大家留言。

本文介绍ggplot2包绘制散点图，一种基本的散点图，用于表示两个连续变量之间的关系。通过这种可视图，直观感受两变量之间会潜藏一种什么关系，为后续的分析和建模提供指导。利用ggplot2包绘制散点图，步骤如下：

首先，R包管理

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

其次，数据获取和整理

采用R语言自带的airquality数据集。

data(airquality)glimpse(airquality)summary(airquality)

第三，逐步绘制散点图

1）基础的散点图

使用geom_point()函数

aq_trim <- airquality %>%  filter(Month %in% c(7,8,9)) %>%  mutate(Month = factor(Month,                        labels = c("July", "August", "September")))p1 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +  geom_point()p1

2）修改点的形状

使用shape参数

p2 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +   geom_point(shape = 21)p2

3）调整x轴的刻度

使用scale_x_continuous()函数

p3 <- p2 +   scale_x_continuous(breaks = seq(1, 31, 5))p3

4）调整轴的标签和标题

使用labs()函数

p4 <- p3 +   labs(title = "Air Quality in New York by Day") +  labs(x = "Day of the month", y = "Ozone (ppb)")p4

5）配置调色板

p5 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +  geom_point(shape = 21, colour = "mediumvioletred", fill = "springgreen") +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)") +  scale_x_continuous(breaks = seq(1, 31, 5))p5

或者

p5 <- ggplot(aq_trim, aes(x = Day, y = Ozone, fill = Month)) +  geom_point(shape = 21) +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)") +  scale_x_continuous(breaks = seq(1, 31, 5))p5
fill <- c("steelblue", "yellowgreen", "violetred1")p5 <- p5 + scale_fill_manual(values = fill)p5

6）图例管理

p6 <- p5 + theme(legend.position = "bottom",                  legend.direction = "horizontal")p6

7）字体设置

font_add("Tahoma","Tahoma.ttf")showtext_auto()

8）配置主题风格

a) 使用经济学杂志主题

p8_1 <- ggplot(aq_trim, aes(x = Day, y = Ozone, fill = Month)) +  geom_point(shape = 21) +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)", fill = "Months ") +  scale_x_continuous(breaks = seq(1, 31, 5)) +  scale_size(range = c(1, 10)) +  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.text = element_text(size = 10),        plot.title = element_text(family = "Tahoma"),        text = element_text(family = "Tahoma"))p8_1

b) 使用自定义主题

fill <- c("#56B4E9","#F0E442","violetred1")p8_2 <- ggplot(aq_trim, aes(x = Day, y = Ozone, fill = Month)) +  geom_point(shape = 21) +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)", fill = "Months ") +  scale_x_continuous(breaks = seq(1, 31, 5)) +  scale_fill_manual(values = fill) +  scale_size(range = c(1, 10)) +  theme(axis.line.x = element_line(size = .5, colour = "black"),        axis.line.y = element_line(size = .5, 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.key = element_blank(),        panel.grid.major = element_blank(),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(family = "Tahoma"),        text = element_text(family = "Tahoma"))p8_2

我做数据工作，主要用到编程语言是R语言和Python语言，我会充分地考虑彼此的优势，在实际的数据问题和工作环境中，选择合适的编程语言，以高效地工作。Python语言的资料、学习和应用，可以关注数据科学与人工智能公众号。

若是你想找数据相关的工作，或者你们团队需要招聘数据人才，可以关注数据人才公众号。

附录：完整代码

##################散点图#2021-03-21#################
# 1 R包管理if (!require("pacman")) {  install.packages("pacman")  require("pacman")}p_load(ggplot2, ggthemes, dplyr, scales, grid, showtext)

# 2 数据获取和理解data(airquality)glimpse(airquality)summary(airquality)
# 3 逐步画散点图# 1）基础散点图# 选择需要绘制图形的数据集aq_trim <- airquality %>%  filter(Month %in% c(7,8,9)) %>%  mutate(Month = factor(Month,                        labels = c("July", "August", "September")))p1 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +  geom_point()p1
# 2）修改点的形状p2 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +   geom_point(shape = 21)p2
# 3）调整x周的刻度p3 <- p2 +   scale_x_continuous(breaks = seq(1, 31, 5))p3
# 4）调整轴标签和标题p4 <- p3 +   labs(title = "Air Quality in New York by Day") +  labs(x = "Day of the month", y = "Ozone (ppb)")p4
# 5）调整调色板p5 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +  geom_point(shape = 21, colour = "mediumvioletred", fill = "springgreen") +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)") +  scale_x_continuous(breaks = seq(1, 31, 5))p5
# 或者p5 <- ggplot(aq_trim, aes(x = Day, y = Ozone)) +  geom_point(shape = 21, colour = "#000000", fill = "#40b8d0") +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)") +  scale_x_continuous(breaks = seq(1, 31, 5))p5
# 或者p5 <- ggplot(aq_trim, aes(x = Day, y = Ozone, fill = Month)) +  geom_point(shape = 21) +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)") +  scale_x_continuous(breaks = seq(1, 31, 5))p5
fill <- c("steelblue", "yellowgreen", "violetred1")p5 <- p5 + scale_fill_manual(values = fill)p5
# 6）图例管理p6 <- p5 + theme(legend.position = "bottom",                  legend.direction = "horizontal")p6
# 7) 字体设置font_add("Tahoma","Tahoma.ttf")showtext_auto()
# 8）配置主题风格# 8.1）使用经济学杂志主题p8_1 <- ggplot(aq_trim, aes(x = Day, y = Ozone, fill = Month)) +  geom_point(shape = 21) +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)", fill = "Months ") +  scale_x_continuous(breaks = seq(1, 31, 5)) +  scale_size(range = c(1, 10)) +  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.text = element_text(size = 10),        plot.title = element_text(family = "Tahoma"),        text = element_text(family = "Tahoma"))p8_1
# 2) 自定义主题fill <- c("#56B4E9","#F0E442","violetred1")p8_2 <- ggplot(aq_trim, aes(x = Day, y = Ozone, fill = Month)) +  geom_point(shape = 21) +  labs(title = "Air Quality in New York by Day",       subtitle = "Source: New York State Department of Conservation") +  labs(x = "Day of the month", y = "Ozone (ppb)", fill = "Months ") +  scale_x_continuous(breaks = seq(1, 31, 5)) +  scale_fill_manual(values = fill) +  scale_size(range = c(1, 10)) +  theme(axis.line.x = element_line(size = .5, colour = "black"),        axis.line.y = element_line(size = .5, 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.key = element_blank(),        panel.grid.major = element_blank(),        panel.grid.minor = element_blank(),        panel.background = element_blank(),        plot.title = element_text(family = "Tahoma"),        text = element_text(family = "Tahoma"))p8_2