ggplot2包|柱形图

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4篇

文 | RUser

2515字 |5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。

本文介绍ggplot2包绘制柱形图。柱形图是一种常用的数据可视化图形，使用垂直的柱子显示类别之间数值分布，x轴表示对比的分类维度，y轴表示相应的数值。柱形图的功能对比分类数据的数值大小，适合的数据是一个分类数据字段和一个连续数据字段，柱子的条数建议不要超过12条。若是条数太多，可以采用条形图（水平方向展示）或者把一些类别合并为一种情况来处理。

利用ggplot2包绘制柱形图，步骤如下：

首先，R包管理

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

接下来，数据准备和加载

chilean_exports <- "year,product,export,percentage2006,copper,4335009500,812006,others,1016726518,192007,copper,9005361914,862007,others,1523085299,142008,copper,6907056354,802008,others,1762684216,202009,copper,10529811075,812009,others,2464094241,192010,copper,14828284450,852010,others,2543015596,152011,copper,15291679086,822011,others,3447972354,182012,copper,14630686732,802012,others,3583968218,202013,copper,15244038840,792013,others,4051281128,212014,copper,14703374241,782014,others,4251484600,222015,copper,13155922363,782015,others,3667286912,22"exports_data <- read_csv(chilean_exports)

第三，数据理解

# 数据结构str(exports_data)# 数据概况summary(exports_data)# 数据检视head(exports_data)

第四、逐步创建柱状图

1）基础柱形图

p1 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = product)) +  geom_col()p1

2）调整柱状的堆叠顺序

p2 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col()p2

3）给柱子添加相应的数值

exports_data <- exports_data %>%  mutate(export_label = paste(round(export/1000000000,2), "B"))p3 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col() +  geom_text(data = exports_data, aes(x = year, y = export,                                     label = export_label), size = 3)p3

4）调整数据标签的位置

# 垂直居中p4 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col() +  geom_text(aes(label = export_label),             position = position_stack(vjust = 0.5),            size = 3)p4

5) 图例管理

exports_data <- exports_data %>%  mutate(product = factor(product, levels = c("copper","others"),                          labels = c("Copper ","Pulp wood, Fruit, Salmon & Others")))

p5 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col() +  geom_text(aes(label = export_label),             position = position_stack(vjust = 0.5),            size = 3) +  theme(legend.position = "bottom", legend.direction = "horizontal",                   legend.title = element_blank()) +  theme(legend.position = "bottom", legend.direction = "horizontal",        legend.title = element_blank()) +  guides(fill = guide_legend(reverse = TRUE))p5

6）调整x轴刻度

p6 <- p5 + scale_x_continuous(breaks = seq(2006,2015,1))p6

7）添加轴标签和标题

p7 <- p6 + labs(title = "Composition of Exports to China ($)",                subtitle = "Source: The Observatory of Economic Complexity") +  labs(x = "Year", y = "USD million")p7

8）柱子的填充色美化

fill <- c("#E1B378","#5F9EA0")p8 <- p7 + scale_fill_manual(values = fill)p8

9）配置主题

使用经济学杂志的主题

p_load(showtext)font_add("Tahoma","Tahoma.ttf")showtext_auto()fill <- c("#00a3dc","#01526d")p8 <- ggplot(aes(y = export, x = year, fill = fct_rev(product)), data = exports_data) +  geom_col() +  geom_text(aes(label = export_label), position = position_stack(vjust = 0.5),            colour = "white", size = 3, family = "Tahoma",            show.legend = F) +  scale_x_continuous(breaks = seq(2006,2015,1)) +  labs(title = "Composition of Exports to China ($)",       subtitle = "Source: The Observatory of Economic Complexity") +  labs(x = "Year", y = "USD million") +  theme_economist() +   scale_fill_manual(values = fill) +  theme(axis.line.x = element_line(size = .5, colour = "black"),        legend.position = "bottom",        legend.direction = "horizontal",        legend.title = element_blank(),        plot.title = element_text(family = "Tahoma"),        text = element_text(family = "Tahoma")) +  guides(fill = guide_legend(reverse = TRUE))p8

附录：完整代码

################柱形图#2021-03-16##############
# 1 R包管理if(!require("pacman")) {  install.packages("pacman")  require("pacman")}p_load(ggplot2, ggthemes, dplyr, readr, scales, forcats)
# 2 数据准备和加载chilean_exports <- "year,product,export,percentage2006,copper,4335009500,812006,others,1016726518,192007,copper,9005361914,862007,others,1523085299,142008,copper,6907056354,802008,others,1762684216,202009,copper,10529811075,812009,others,2464094241,192010,copper,14828284450,852010,others,2543015596,152011,copper,15291679086,822011,others,3447972354,182012,copper,14630686732,802012,others,3583968218,202013,copper,15244038840,792013,others,4051281128,212014,copper,14703374241,782014,others,4251484600,222015,copper,13155922363,782015,others,3667286912,22"exports_data <- read_csv(chilean_exports)
# 3 数据理解# 数据结构str(exports_data)# 数据概况summary(exports_data)# 数据检视head(exports_data)
# 4 逐步创建柱形图# 1）基础柱形图p1 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = product)) +  geom_col()p1
# 2) 调整柱状堆叠顺序p2 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col()p2
# 3) 给柱子添加相应的数值# 新增标签变量exports_data <- exports_data %>%  mutate(export_label = paste(round(export/1000000000,2), "B"))p3 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col() +  geom_text(data = exports_data, aes(x = year, y = export,                                     label = export_label), size = 3)p3
# 4）调整数据标签的位置# 垂直居中p4 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col() +  geom_text(aes(label = export_label),             position = position_stack(vjust = 0.5),            size = 3)p4
# 5) 图例管理exports_data <- exports_data %>%  mutate(product = factor(product, levels = c("copper","others"),                          labels = c("Copper ","Pulp wood, Fruit, Salmon & Others")))

p5 <- ggplot(data = exports_data,             aes(x = year, y = export, fill = fct_rev(product))) +  geom_col() +  geom_text(aes(label = export_label),             position = position_stack(vjust = 0.5),            size = 3) +  theme(legend.position = "bottom", legend.direction = "horizontal",                   legend.title = element_blank()) +  theme(legend.position = "bottom", legend.direction = "horizontal",        legend.title = element_blank()) +  guides(fill = guide_legend(reverse = TRUE))p5
# 6) 调整x轴刻度p6 <- p5 + scale_x_continuous(breaks = seq(2006,2015,1))p6
# 7) 添加轴标签和标题p7 <- p6 + labs(title = "Composition of Exports to China ($)",                subtitle = "Source: The Observatory of Economic Complexity") +  labs(x = "Year", y = "USD million")p7
# 8) 柱子填充色美化fill <- c("#E1B378","#5F9EA0")p8 <- p7 + scale_fill_manual(values = fill)p8
# 9）配置主题# 使用经济学杂志主题p_load(showtext)font_add("Tahoma","Tahoma.ttf")showtext_auto()fill <- c("#00a3dc","#01526d")p8 <- ggplot(aes(y = export, x = year, fill = fct_rev(product)), data = exports_data) +  geom_col() +  geom_text(aes(label = export_label), position = position_stack(vjust = 0.5),            colour = "white", size = 3, family = "Tahoma",            show.legend = F) +  scale_x_continuous(breaks = seq(2006,2015,1)) +  labs(title = "Composition of Exports to China ($)",       subtitle = "Source: The Observatory of Economic Complexity") +  labs(x = "Year", y = "USD million") +  theme_economist() +   scale_fill_manual(values = fill) +  theme(axis.line.x = element_line(size = .5, colour = "black"),        legend.position = "bottom",        legend.direction = "horizontal",        legend.title = element_blank(),        plot.title = element_text(family = "Tahoma"),        text = element_text(family = "Tahoma")) +  guides(fill = guide_legend(reverse = TRUE))p8