拿R來畫畫（五）：全面掌握條形圖

一一對應版

library(gcookbook)
library(ggplot2)
head(pg_mean)

A data.frame: 3 × 2

group	weight
<fct>	<dbl>
ctrl	5.032
trt1	4.661
trt2	5.526

ggplot(pg_mean, aes(x = group, y = weight)) + 
geom_bar(stat = 'identity')

改變填充色和邊框色

ggplot(pg_mean, aes(x = group, y = weight)) + 
geom_bar(stat = 'identity', fill = 'lightblue', color = 'green')

簇狀條形圖

head(cabbage_exp)

A data.frame: 6 × 6

Cultivar	Date	Weight	sd	n	se
<fct>	<fct>	<dbl>	<dbl>	<int>	<dbl>
c39	d16	3.18	0.9566144	10	0.30250803
c39	d20	2.80	0.2788867	10	0.08819171
c39	d21	2.74	0.9834181	10	0.31098410
c52	d16	2.26	0.4452215	10	0.14079141
c52	d20	3.11	0.7908505	10	0.25008887
c52	d21	1.47	0.2110819	10	0.06674995

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(position = 'dodge', stat = 'identity')

• geom_bar中的width位於0到1之間，默認爲0.9，可以通過調整這個來調整寬度。
• 通過令position_dodge的值大於width來調整組內條形圖之間的距離，否則就會重疊一部分

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(stat = 'identity', width = 0.4, position = position_dodge(0.3))

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(stat = 'identity', width = 0.4, position = position_dodge(0.5))

不加dodge條件就會生成堆積條形圖

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(stat = 'identity')

scale_fill_manual可以手動調整顏色

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(position = 'dodge', stat = 'identity') + 
scale_fill_manual(values = c('#8DD35F','#FFE680'))

分別在柱子頂端的上下位置加圖例

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(position = 'dodge', stat = 'identity') + 
scale_fill_manual(values = c('#8DD35F','#FFE680')) + 
geom_text(aes(label = Weight), vjust = -0.5, position = position_dodge(0.9), size = 4, color = 'green')

ggplot(cabbage_exp, aes(x = Date, y = Weight, fill = Cultivar)) + 
geom_bar(position = 'dodge', stat = 'identity') + 
scale_fill_manual(values = c('#8DD35F','#FFE680')) + 
geom_text(aes(label = Weight), vjust = 1.5, position = position_dodge(0.9), size = 5, color = 'white')

頻數條形圖

Note the documentation for each: they both use stat = “bin” (in current ggplot2 versions this stat has been split into stat_bin for continuous data and stat_count for discrete data) by default.

# 離散情況
ggplot(diamonds, aes(x = cut)) + geom_bar()
# 等價於ggplot(diamonds, aes(x = cut)) + geom_bar(stat = 'count')

# 等價寫法
ggplot(diamonds, aes(x = cut, y = 1)) + 
geom_bar(stat = 'identity')

# 連續情況
ggplot(diamonds, aes(x = carat)) + geom_bar()
# 等價於ggplot(diamonds, aes(x = cut)) + geom_bar(stat = 'count')
# ggplot(diamonds, aes(x = cut)) + geom_bar(stat = 'bin')會得到不一樣的結果

正負分開圖

head(climate)

A data.frame: 6 × 6

Source	Year	Anomaly1y	Anomaly5y	Anomaly10y	Unc10y
<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>
Berkeley	1800	NA	NA	-0.435	0.505
Berkeley	1801	NA	NA	-0.453	0.493
Berkeley	1802	NA	NA	-0.460	0.486
Berkeley	1803	NA	NA	-0.493	0.489
Berkeley	1804	NA	NA	-0.536	0.483
Berkeley	1805	NA	NA	-0.541	0.475

csub <- subset(climate, Source == 'Berkeley' & Year > 1900)
csub$pos  <- csub$Anomaly10y >= 0
head(csub)

A data.frame: 6 × 7

	Source	Year	Anomaly1y	Anomaly5y	Anomaly10y	Unc10y	pos
	<chr>	<dbl>	<dbl>	<dbl>	<dbl>	<dbl>	<lgl>
102	Berkeley	1901	NA	NA	-0.162	0.109	FALSE
103	Berkeley	1902	NA	NA	-0.177	0.108	FALSE
104	Berkeley	1903	NA	NA	-0.199	0.104	FALSE
105	Berkeley	1904	NA	NA	-0.223	0.105	FALSE
106	Berkeley	1905	NA	NA	-0.241	0.107	FALSE
107	Berkeley	1906	NA	NA	-0.294	0.106	FALSE

ggplot(csub, aes(x = Year, y = Anomaly10y, fill = pos)) + 
# 設定邊框顏色和寬度
geom_bar(stat = 'identity', color = 'black', size = 0.25) + 
# 手動移除pos圖例
scale_fill_manual(values = c('#8DD35F','#FFE680'), guide = FALSE)

比例堆積圖

• 查看所有調色板

RColorBrewer::display.brewer.all() 

• 以date爲切割變量對數據進行transform操作

library(plyr)
ce <- ddply(cabbage_exp, "Date", transform, person_weight = Weight / sum(Weight) * 100)
ggplot(ce, aes(x = Date, y = person_weight, fill = Cultivar)) + 
geom_bar(stat = 'identity', colour = 'black') + 
# 換個調色板
scale_fill_brewer(palette = "Set3")

• 繪製堆積圖的數字時，要先計算出兩段的高度

cce <- ddply(ce, "Date", transform, text_height = cumsum(person_weight))
# 調整一下堆積圖的順序使之對應
cce$Cultivar <- factor(cce$Cultivar, levels = c("c52", "c39"))
ggplot(cce, aes(x = Date, y = person_weight, fill = Cultivar)) + 
geom_bar(stat = 'identity', colour = 'black') + 
# 換個調色板
scale_fill_brewer(palette = "Set3") + 
geom_text(aes(y = text_height, label = person_weight), vjust = 1.5, color = "black")

• 進一步美化標註，比如文字放中間，固定位數，加上單位等等

cce <- ddply(ce, "Date", transform, text_height = cumsum(person_weight)-0.5*person_weight)
# 調整一下堆積圖的順序使之對應
cce$Cultivar <- factor(cce$Cultivar, levels = c("c52", "c39"))
ggplot(cce, aes(x = Date, y = person_weight, fill = Cultivar)) + 
geom_bar(stat = 'identity', colour = 'black') + 
# 換個調色板
scale_fill_brewer(palette = "Set3") + 
geom_text(aes(y = text_height, label = paste(round(person_weight, 2), "%")), vjust = 1.5, color = "black", size = 6)