如何在 R 中使用 facet_wrap 并排绘制箱线图？
How to draw side by side boxplot using facet_wrap in R?
我正在寻找一种解决方案，可以在 R 中使用 facet_wrap 并排绘制 boxplot。虽然有很多好的解决方案，但是，我没有遇到任何我想要的。我决定画一张我想看到的 plot 我的两个 data.frame 的照片。 Data.frame C 有我的 校准 四种不同计量模型（即 KGE、NSE、PBIAS 和 R-Sq）的数据) 而 Data.frame V 有我的 validation 数据。我想使用 ggplot2 功能的 facet_wrap 查看每个指标的单独 plot。以下是我到目前为止所做的，但它并没有让我更接近。
graphics.off()
rm(list = ls())
library(tidyverse)
C = data.frame(KGE_M1 = runif(3, 0, 0.5), NSE_M1 = runif(3,0,0.5), R_Sq_M1 = runif(3,-1,0.3), PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7), NSE_M2 = runif(3,0.2,0.7), R_Sq_M2 = runif(3,-0.5,0.7), PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8), NSE_M3 = runif(3,0.3,0.8), R_Sq_M3 = runif(3,0.3,0.8), PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1), NSE_M4 = runif(3,0.5,1), R_Sq_M4 = runif(3,0.5,1), PBIAS_M4 = runif(3, -0.05, 0.05),
Cal = rep("Calibration", 3))
V = data.frame(KGE_M1 = runif(3, 0, 0.5), NSE_M1 = runif(3,0,0.5), R_Sq_M1 = runif(3,-1,0.3), PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7), NSE_M2 = runif(3,0.2,0.7), R_Sq_M2 = runif(3,-0.5,0.7), PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8), NSE_M3 = runif(3,0.3,0.8), R_Sq_M3 = runif(3,0.3,0.8), PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1), NSE_M4 = runif(3,0.5,1), R_Sq_M4 = runif(3,0.5,1), PBIAS_M4 = runif(3, -0.05, 0.05),
Val = rep("Validation", 3))
C = gather(C, key = "Variable", value = "Value", -Cal)
V = gather(V, key = "Variable", value = "Value", -Val)
ggplot(data = C)+
geom_boxplot(aes(x= Variable, y = Value))
+ facet_wrap(~Variable)
我想看下面这样的情节
我认为您需要在绘图之前拆分 Variable，以便为 M1、M2、M3 M4 设置一个变量，并为您的条件设置一个变量：
library(tidyverse)
C2 <- C %>% pivot_longer(., -Cal, names_to = "Variable", values_to = "Value") %>%
group_by(Variable) %>%
mutate(Variable2 = unlist(strsplit(Variable, "_M"))[2]) %>%
mutate(Variable2 = paste0("Cal_M",Variable2)) %>%
mutate(Variable1 = unlist(strsplit(Variable,"_M"))[1]) %>%
rename(., Type = Cal)
# A tibble: 6 x 5
# Groups: Variable [6]
Type Variable Value Variable2 Variable1
<fct> <chr> <dbl> <chr> <chr>
1 Calibration KGE_M1 0.246 Cal_M1 KGE
2 Calibration NSE_M1 0.476 Cal_M1 NSE
3 Calibration R_Sq_M1 -0.978 Cal_M1 R_Sq
4 Calibration PBIAS_M1 0.117 Cal_M1 PBIAS
5 Calibration KGE_M2 0.544 Cal_M2 KGE
6 Calibration NSE_M2 0.270 Cal_M2 NSE
现在，我们对数据集做同样的事情V
V2 <- V %>% pivot_longer(., -Val, names_to = "Variable", values_to = "Value") %>%
group_by(Variable) %>%
mutate(Variable2 = unlist(strsplit(Variable, "_M"))[2]) %>%
mutate(Variable2 = paste0("Val_M",Variable2)) %>%
mutate(Variable1 = unlist(strsplit(Variable,"_M"))[1]) %>%
rename(., Type = Val)
# A tibble: 6 x 5
# Groups: Variable [6]
Type Variable Value Variable2 Variable1
<fct> <chr> <dbl> <chr> <chr>
1 Validation KGE_M1 0.459 Val_M1 KGE
2 Validation NSE_M1 0.105 Val_M1 NSE
3 Validation R_Sq_M1 -0.435 Val_M1 R_Sq
4 Validation PBIAS_M1 0.0281 Val_M1 PBIAS
5 Validation KGE_M2 0.625 Val_M2 KGE
6 Validation NSE_M2 0.332 Val_M2 NSE
我们现在可以将它们绑定在一起：
DF <- rbind(C2,V2)
然后，我们可以绘制：
ggplot(DF, aes(x = Variable2, y = Value))+
geom_boxplot()+
facet_wrap(.~Variable1, scales = "free")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
编辑：重命名 x 轴，添加空列以分隔校准值和验证值
要在校准和验证之间添加一个空 space，您可以简单地为 Variable1 的每个条件添加空行，如下所示：
DF <- as.data.frame(DF) %>% add_row(Type = rep("Empty",4),
Variable = rep("Empty",4),
Value = rep(NA,4),
Variable2 = rep("Empty",4),
Variable1 = unique(DF$Variable1))
此外，如果要重命名 x 轴标签，可以使用 scale_x_discrete
ggplot(DF, aes(x = Variable2, y = Value, fill = Type))+
geom_boxplot()+
facet_wrap(.~Variable1, scales = "free")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))+
scale_x_discrete(labels = c("M1","M2","M3","M4","","M1","M2","M3","M4"))
是否符合您的预期？
所以这里有一种方法可以用来完成所需的工作；
首先我们创建您拥有的数据；
library(tidyverse)
# Creating first dataframe
C <-
data.frame(
KGE_M1 = runif(3, 0, 0.5),
NSE_M1 = runif(3,0,0.5),
R_Sq_M1 = runif(3,-1,0.3),
PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7),
NSE_M2 = runif(3,0.2,0.7),
R_Sq_M2 = runif(3,-0.5,0.7),
PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8),
NSE_M3 = runif(3,0.3,0.8),
R_Sq_M3 = runif(3,0.3,0.8),
PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1),
NSE_M4 = runif(3,0.5,1),
R_Sq_M4 = runif(3,0.5,1),
PBIAS_M4 = runif(3, -0.05, 0.05),
Cal = rep("Calibration", 3),
stringsAsFactors = FALSE)
# Creating second dataframe
V <-
data.frame(
KGE_M1 = runif(3, 0, 0.5),
NSE_M1 = runif(3,0,0.5),
R_Sq_M1 = runif(3,-1,0.3),
PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7),
NSE_M2 = runif(3,0.2,0.7),
R_Sq_M2 = runif(3,-0.5,0.7),
PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8),
NSE_M3 = runif(3,0.3,0.8),
R_Sq_M3 = runif(3,0.3,0.8),
PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1),
NSE_M4 = runif(3,0.5,1),
R_Sq_M4 = runif(3,0.5,1),
PBIAS_M4 = runif(3, -0.05, 0.05),
Val = rep("Validation", 3),
stringsAsFactors = FALSE)
现在我们更改数据格式并将其可视化；
# Rename the variable to make it same
C <- rename(C, Identifier = Cal)
V <- rename(V, Identifier = Val)
data <-
# First we bind the two datasets
bind_rows(C, V) %>%
# We convert from wide format to long format
gather(key = "Variable", value = "Value", -Identifier) %>%
# We separate Variable into 2 columns at the last underscore
separate(Variable, into = c("Variable", "Number"), sep = "_(?=[^_]+$)")
data %>%
ggplot()+
geom_boxplot(aes(x = Number, y = Value,
group = interaction(Identifier, Number), fill = Identifier)) +
facet_wrap(~Variable)
我正在寻找一种解决方案，可以在 R 中使用 facet_wrap 并排绘制 boxplot。虽然有很多好的解决方案，但是，我没有遇到任何我想要的。我决定画一张我想看到的 plot 我的两个 data.frame 的照片。 Data.frame C 有我的 校准 四种不同计量模型（即 KGE、NSE、PBIAS 和 R-Sq）的数据) 而 Data.frame V 有我的 validation 数据。我想使用 ggplot2 功能的 facet_wrap 查看每个指标的单独 plot。以下是我到目前为止所做的，但它并没有让我更接近。
graphics.off()
rm(list = ls())
library(tidyverse)
C = data.frame(KGE_M1 = runif(3, 0, 0.5), NSE_M1 = runif(3,0,0.5), R_Sq_M1 = runif(3,-1,0.3), PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7), NSE_M2 = runif(3,0.2,0.7), R_Sq_M2 = runif(3,-0.5,0.7), PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8), NSE_M3 = runif(3,0.3,0.8), R_Sq_M3 = runif(3,0.3,0.8), PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1), NSE_M4 = runif(3,0.5,1), R_Sq_M4 = runif(3,0.5,1), PBIAS_M4 = runif(3, -0.05, 0.05),
Cal = rep("Calibration", 3))
V = data.frame(KGE_M1 = runif(3, 0, 0.5), NSE_M1 = runif(3,0,0.5), R_Sq_M1 = runif(3,-1,0.3), PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7), NSE_M2 = runif(3,0.2,0.7), R_Sq_M2 = runif(3,-0.5,0.7), PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8), NSE_M3 = runif(3,0.3,0.8), R_Sq_M3 = runif(3,0.3,0.8), PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1), NSE_M4 = runif(3,0.5,1), R_Sq_M4 = runif(3,0.5,1), PBIAS_M4 = runif(3, -0.05, 0.05),
Val = rep("Validation", 3))
C = gather(C, key = "Variable", value = "Value", -Cal)
V = gather(V, key = "Variable", value = "Value", -Val)
ggplot(data = C)+
geom_boxplot(aes(x= Variable, y = Value))
+ facet_wrap(~Variable)
我想看下面这样的情节
我认为您需要在绘图之前拆分 Variable，以便为 M1、M2、M3 M4 设置一个变量，并为您的条件设置一个变量：
library(tidyverse)
C2 <- C %>% pivot_longer(., -Cal, names_to = "Variable", values_to = "Value") %>%
group_by(Variable) %>%
mutate(Variable2 = unlist(strsplit(Variable, "_M"))[2]) %>%
mutate(Variable2 = paste0("Cal_M",Variable2)) %>%
mutate(Variable1 = unlist(strsplit(Variable,"_M"))[1]) %>%
rename(., Type = Cal)
# A tibble: 6 x 5
# Groups: Variable [6]
Type Variable Value Variable2 Variable1
<fct> <chr> <dbl> <chr> <chr>
1 Calibration KGE_M1 0.246 Cal_M1 KGE
2 Calibration NSE_M1 0.476 Cal_M1 NSE
3 Calibration R_Sq_M1 -0.978 Cal_M1 R_Sq
4 Calibration PBIAS_M1 0.117 Cal_M1 PBIAS
5 Calibration KGE_M2 0.544 Cal_M2 KGE
6 Calibration NSE_M2 0.270 Cal_M2 NSE
现在，我们对数据集做同样的事情V
V2 <- V %>% pivot_longer(., -Val, names_to = "Variable", values_to = "Value") %>%
group_by(Variable) %>%
mutate(Variable2 = unlist(strsplit(Variable, "_M"))[2]) %>%
mutate(Variable2 = paste0("Val_M",Variable2)) %>%
mutate(Variable1 = unlist(strsplit(Variable,"_M"))[1]) %>%
rename(., Type = Val)
# A tibble: 6 x 5
# Groups: Variable [6]
Type Variable Value Variable2 Variable1
<fct> <chr> <dbl> <chr> <chr>
1 Validation KGE_M1 0.459 Val_M1 KGE
2 Validation NSE_M1 0.105 Val_M1 NSE
3 Validation R_Sq_M1 -0.435 Val_M1 R_Sq
4 Validation PBIAS_M1 0.0281 Val_M1 PBIAS
5 Validation KGE_M2 0.625 Val_M2 KGE
6 Validation NSE_M2 0.332 Val_M2 NSE
我们现在可以将它们绑定在一起：
DF <- rbind(C2,V2)
然后，我们可以绘制：
ggplot(DF, aes(x = Variable2, y = Value))+
geom_boxplot()+
facet_wrap(.~Variable1, scales = "free")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))
编辑：重命名 x 轴，添加空列以分隔校准值和验证值
要在校准和验证之间添加一个空 space，您可以简单地为 Variable1 的每个条件添加空行，如下所示：
DF <- as.data.frame(DF) %>% add_row(Type = rep("Empty",4),
Variable = rep("Empty",4),
Value = rep(NA,4),
Variable2 = rep("Empty",4),
Variable1 = unique(DF$Variable1))
此外，如果要重命名 x 轴标签，可以使用 scale_x_discrete
ggplot(DF, aes(x = Variable2, y = Value, fill = Type))+
geom_boxplot()+
facet_wrap(.~Variable1, scales = "free")+
theme(axis.text.x = element_text(angle = 45, hjust = 1))+
scale_x_discrete(labels = c("M1","M2","M3","M4","","M1","M2","M3","M4"))
是否符合您的预期？
所以这里有一种方法可以用来完成所需的工作；
首先我们创建您拥有的数据；
library(tidyverse)
# Creating first dataframe
C <-
data.frame(
KGE_M1 = runif(3, 0, 0.5),
NSE_M1 = runif(3,0,0.5),
R_Sq_M1 = runif(3,-1,0.3),
PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7),
NSE_M2 = runif(3,0.2,0.7),
R_Sq_M2 = runif(3,-0.5,0.7),
PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8),
NSE_M3 = runif(3,0.3,0.8),
R_Sq_M3 = runif(3,0.3,0.8),
PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1),
NSE_M4 = runif(3,0.5,1),
R_Sq_M4 = runif(3,0.5,1),
PBIAS_M4 = runif(3, -0.05, 0.05),
Cal = rep("Calibration", 3),
stringsAsFactors = FALSE)
# Creating second dataframe
V <-
data.frame(
KGE_M1 = runif(3, 0, 0.5),
NSE_M1 = runif(3,0,0.5),
R_Sq_M1 = runif(3,-1,0.3),
PBIAS_M1 = runif(3, -0.25, 0.25),
KGE_M2 = runif(3, 0.2, 0.7),
NSE_M2 = runif(3,0.2,0.7),
R_Sq_M2 = runif(3,-0.5,0.7),
PBIAS_M2 = runif(3, -0.15, 0.15),
KGE_M3 = runif(3, 0.3, 0.8),
NSE_M3 = runif(3,0.3,0.8),
R_Sq_M3 = runif(3,0.3,0.8),
PBIAS_M3 = runif(3, -0.10, 0.10),
KGE_M4 = runif(3, 0.5, 1),
NSE_M4 = runif(3,0.5,1),
R_Sq_M4 = runif(3,0.5,1),
PBIAS_M4 = runif(3, -0.05, 0.05),
Val = rep("Validation", 3),
stringsAsFactors = FALSE)
现在我们更改数据格式并将其可视化；
# Rename the variable to make it same
C <- rename(C, Identifier = Cal)
V <- rename(V, Identifier = Val)
data <-
# First we bind the two datasets
bind_rows(C, V) %>%
# We convert from wide format to long format
gather(key = "Variable", value = "Value", -Identifier) %>%
# We separate Variable into 2 columns at the last underscore
separate(Variable, into = c("Variable", "Number"), sep = "_(?=[^_]+$)")
data %>%
ggplot()+
geom_boxplot(aes(x = Number, y = Value,
group = interaction(Identifier, Number), fill = Identifier)) +
facet_wrap(~Variable)