TAPPONNIER Data Visualization Code
2024-12-16
MODULE 2:Practice Assignment
#Task 1: Scatter with Reg
data("USArrests")
head(USArrests)## Murder Assault UrbanPop Rape
## Alabama 13.2 236 58 21.2
## Alaska 10.0 263 48 44.5
## Arizona 8.1 294 80 31.0
## Arkansas 8.8 190 50 19.5
## California 9.0 276 91 40.6
## Colorado 7.9 204 78 38.7?USArrests
library(ggplot2)
ggplot(USArrests, aes(x=Murder,y=Assault))+
geom_point(color="#660000", size=2)+
geom_smooth(aes(color="#660000"),method=lm)+
ggtitle("Scatter Plot of Assault vs. Murder Rate")+
ylab("Assault Rate")+
xlab("Murder Rate")+
theme_minimal()+
theme(legend.position="none")
#Task 2: Line
library(dplyr)
##Mean
USArrests$state <- rownames(USArrests)
USArrests$AVGCrimeRate <- rowMeans(USArrests[, c("Murder", "Assault", "Rape")])
head(USArrests)## Murder Assault UrbanPop Rape state AVGCrimeRate
## Alabama 13.2 236 58 21.2 Alabama 90.13333
## Alaska 10.0 263 48 44.5 Alaska 105.83333
## Arizona 8.1 294 80 31.0 Arizona 111.03333
## Arkansas 8.8 190 50 19.5 Arkansas 72.76667
## California 9.0 276 91 40.6 California 108.53333
## Colorado 7.9 204 78 38.7 Colorado 83.53333##Line Plot
ggplot(data=USArrests, aes(x=state,y=AVGCrimeRate, group=1))+
geom_line(size=1, color="black")+
geom_point(color = "steelblue", size = 2.5, shape = 16)+
ggtitle("Line Plot of Average Crime Rate by State")+
xlab("State")+
ylab("Average Crime Rate")+
theme_classic()+
theme(axis.text.x = element_text(angle = 90, hjust = 1))
MODULE 3: Box and Violin
##downloading the data
CAM<-read.csv("Violin_Plot_Data.csv")
print(CAM)## F1Performance Repeat1 Repeat2 Repeat3 Repeat4 Repeat5 Repeat6
## 1 SVMWithGradCAMMaps 0.670051 0.701571 0.680628 0.710660 0.648649 0.715686
## 2 SVMWithDeepShapMaps 0.673913 0.610390 0.630872 0.618357 0.662577 0.608696
## Repeat7 Repeat8 Repeat9 Repeat10 Repeat11 Repeat12 Repeat13 Repeat14
## 1 0.713568 0.684932 0.699029 0.687500 0.720812 0.716418 0.666667 0.683417
## 2 0.623529 0.642857 0.607477 0.645833 0.631579 0.660099 0.662420 0.610778
## Repeat15 Repeat16 Repeat17 Repeat18 Repeat19 Repeat20
## 1 0.666667 0.663317 0.691943 0.680412 0.686869 0.686551
## 2 0.701754 0.659091 0.577540 0.666667 0.678571 0.596685##Installing new packages
packages<-c("ggplot2","readr","tidyverse","dplyr","ggpubr","see")
install.packages("ggplot2")
library(ggplot2)
library(readr)
library(tidyverse)
library(dplyr)
library(ggpubr)
install.packages("see")
library(see)
head(CAM)## F1Performance Repeat1 Repeat2 Repeat3 Repeat4 Repeat5 Repeat6
## 1 SVMWithGradCAMMaps 0.670051 0.701571 0.680628 0.710660 0.648649 0.715686
## 2 SVMWithDeepShapMaps 0.673913 0.610390 0.630872 0.618357 0.662577 0.608696
## Repeat7 Repeat8 Repeat9 Repeat10 Repeat11 Repeat12 Repeat13 Repeat14
## 1 0.713568 0.684932 0.699029 0.687500 0.720812 0.716418 0.666667 0.683417
## 2 0.623529 0.642857 0.607477 0.645833 0.631579 0.660099 0.662420 0.610778
## Repeat15 Repeat16 Repeat17 Repeat18 Repeat19 Repeat20
## 1 0.666667 0.663317 0.691943 0.680412 0.686869 0.686551
## 2 0.701754 0.659091 0.577540 0.666667 0.678571 0.596685data_long <- CAM %>%
pivot_longer(
cols = starts_with("Repeat"),
names_to = "Repeat",
values_to = "values")
head(data_long)## # A tibble: 6 × 3
## F1Performance Repeat values
## <chr> <chr> <dbl>
## 1 SVMWithGradCAMMaps Repeat1 0.670
## 2 SVMWithGradCAMMaps Repeat2 0.702
## 3 SVMWithGradCAMMaps Repeat3 0.681
## 4 SVMWithGradCAMMaps Repeat4 0.711
## 5 SVMWithGradCAMMaps Repeat5 0.649
## 6 SVMWithGradCAMMaps Repeat6 0.716##Figure recreation
ggplot(data_long, aes(x=F1Performance, y=values,fill=F1Performance))+
geom_jitter(position=position_jitter(0.1),aes(color = F1Performance), size =6, alpha = 0.8) +
geom_violin(size=2, alpha=0.5,draw_quantiles = c(0.25, 0.5, 0.75), quantile.size = 2)+
coord_flip()+
scale_fill_manual(values = c("magenta4", "darkorange2")) +
scale_color_manual(values = c("magenta4", "darkorange2")) +
stat_summary(fun=median,geom="point",shape=21,size=3,fill="white",color="black",stroke=1.5)+
scale_y_continuous(limits = c(min(data_long$values), max(data_long$values)),breaks = seq(min(data_long$values), max(data_long$values), by = 0.02),labels = scales::number_format(accuracy = 0.02)) +
theme_minimal()+
theme(legend.title = element_text(face = "bold", size = 14),axis.text.y = element_blank(),axis.ticks.y = element_blank(),axis.title.y = element_blank(), axis.line.x = element_line(size = 2, color = "black"), plot.title = element_text(hjust=0.5,face="bold"),panel.grid.major.y = element_blank(), panel.grid.minor.x=element_blank(),panel.grid.major.x = element_line(color = "grey", linetype = "dashed", size = 1.5),legend.position = "none")+
geom_text(aes(x="SVMWithGradCAMMaps",label="SVM + GRAD-CAM++",y=0.64),vjust=-4.5,color="darkorange2",size=4.5)+
geom_text(aes(x = "SVMWithDeepShapMaps", y = 0.6, label = "SVM + Deep SHAP"),vjust = -3.5, color = "magenta4", size = 4.5)+
ylab("F1")+
ggtitle("Fig.7.Grad-CAM++saliency maps capture unique predictive information.")
##Half-Violin
ggplot(data_long, aes(x=F1Performance, y=values,fill=F1Performance))+
geom_jitter(position=position_jitter(0.1),aes(color = F1Performance), size =6, alpha = 0.8) +
geom_violinhalf(size=2, alpha=0.5,draw_quantiles = c(0.25, 0.5, 0.75), quantile.size = 2)+
coord_flip()+
scale_fill_manual(values = c("magenta4", "darkorange2")) +
scale_color_manual(values = c("magenta4", "darkorange2")) +
stat_summary(fun=median,geom="point",shape=21,size=3,fill="white",color="black",stroke=1.5)+
scale_y_continuous(limits = c(min(data_long$values), max(data_long$values)),breaks = seq(min(data_long$values), max(data_long$values), by = 0.02),labels = scales::number_format(accuracy = 0.02)) +
theme_minimal()+
theme(legend.title = element_text(face = "bold", size = 14),axis.text.y = element_blank(),axis.ticks.y = element_blank(),axis.title.y = element_blank(), axis.line.x = element_line(size = 2, color = "black"), plot.title = element_text(hjust=0.5,face="bold"),panel.grid.major.y = element_blank(), panel.grid.minor.x=element_blank(),panel.grid.major.x = element_line(color = "grey", linetype = "dashed", size = 1.5),legend.position = "none")+
geom_text(aes(x="SVMWithGradCAMMaps",label="SVM + GRAD-CAM++",y=0.64),vjust=-4.5,color="darkorange2",size=4.5)+
geom_text(aes(x = "SVMWithDeepShapMaps", y = 0.6, label = "SVM + Deep SHAP"),vjust = -3.5, color = "magenta4", size = 4.5)+
ylab("F1")+
ggtitle("Fig.7.Grad-CAM++saliency maps capture unique predictive information.")
#Box+violin Plot
ggplot(data_long, aes(x=F1Performance, y=values,fill=F1Performance))+
geom_jitter(position=position_jitter(0.1),aes(color = F1Performance), size =6, alpha = 0.8) +
geom_violinhalf(size=2, alpha=0.5,draw_quantiles = c(0.25, 0.5, 0.75), quantile.size = 2)+
geom_boxplot(aes(color = F1Performance), width = 0.4, alpha = 0.3, outlier.shape = NA) +
coord_flip()+
scale_fill_manual(values = c("magenta4", "darkorange2")) +
scale_color_manual(values = c("magenta4", "darkorange2")) +
stat_summary(fun=median,geom="point",shape=21,size=3,fill="white",color="black",stroke=1.5)+
scale_y_continuous(limits = c(min(data_long$values), max(data_long$values)),breaks = seq(min(data_long$values), max(data_long$values), by = 0.02),labels = scales::number_format(accuracy = 0.02)) +
theme_minimal()+
theme(legend.title = element_text(face = "bold", size = 14),axis.text.y = element_blank(),axis.ticks.y = element_blank(),axis.title.y = element_blank(), axis.line.x = element_line(size = 2, color = "black"), plot.title = element_text(hjust=0.5,face="bold"),panel.grid.major.y = element_blank(), panel.grid.minor.x=element_blank(),panel.grid.major.x = element_line(color = "grey", linetype = "dashed", size = 1.5),legend.position = "none")+
geom_text(aes(x="SVMWithGradCAMMaps",label="SVM + GRAD-CAM++",y=0.64),vjust=-4.5,color="darkorange2",size=4.5)+
geom_text(aes(x = "SVMWithDeepShapMaps", y = 0.6, label = "SVM + Deep SHAP"),vjust = -3.5, color = "magenta4", size = 4.5)+
ylab("F1")+
ggtitle("Fig.7.Grad-CAM++saliency maps capture unique predictive information.")