TAPPONNIER Data Visualization Code
Ezra Tapponnier
2025-01-05
Module 1: GGplot Basics
Loading Packages and Data
#Loading all of the packages I might need during this project
packages<-c("ggplot2","readr","tidyverse","dplyr","ggpubr","see")
check_install_packages<-function(pkg){
if (!require(pkg, character.only = TRUE)){
install.packages(pkg,dependencies = TRUE)
library(pkg,character.only = TRUE)
}
}
sapply(packages,check_install_packages)## $ggplot2
## NULL
##
## $readr
## NULL
##
## $tidyverse
## NULL
##
## $dplyr
## NULL
##
## $ggpubr
## NULL
##
## $see
## NULL#learning how to retrieve data sets from with in r
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
#The USArrests data looks at four different statistics related to arrests in six states. The different variables that can be used are Murder, Assault, UrbanPop, and Rape. Assault, Murder, and Rape are in number of arrest per 100,000 residents. UrbanPop is the percentage of the population living in urban areas. All variables are numerical.GGplot Graphic Code: Basics
Part 1
#Coding basics
ggplot(mtcars, aes(x=mpg, y=hp, color=cyl))+
geom_point(size=2.4, shape=8)+
ggtitle("Effect of Horsepower on Fuel Efficiency", subtitle="Categorized by Number of Cylinders")+
ylab("Fuel Efficiency (MPG)")+
xlab("Horsepower")+
theme_minimal()+
theme(
legend.position = "bottom",
legend.box = "horizontal",
plot.margin = margin(t = 10, r = 10, b = 10, l = 10)
)
Part 2: Playing Around
data("ChickWeight")
head(ChickWeight)## weight Time Chick Diet
## 1 42 0 1 1
## 2 51 2 1 1
## 3 59 4 1 1
## 4 64 6 1 1
## 5 76 8 1 1
## 6 93 10 1 1?ChickWeight
#Basics of code, part 2: it gets more complicated now
ggplot(ChickWeight, aes(x=weight, y=Time, color=Diet))+
geom_point(shape=16, size=2)+
scale_color_manual(values = c("#56B4E9", "#CC79A7", "#E69F00","#009E73"))+
ggtitle("Effect of Time on Fuel Chick Weight", subtitle="Categorized by Diet")+
ylab("Chick Weight (gm)")+
xlab("Time (days since hatch)")+
theme_minimal()+
theme(
legend.position = "bottom",
legend.box = "horizontal",
plot.margin = margin(t = 10, r = 10, b = 10, l = 10)
)
Module 2:Practice Assignment
Task 1: Scatter Plot with Regression Line
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)
#Scatter Plot with Regression line, yay!
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 PLot
library(dplyr)
##Mean: creating 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 Plot
Downloading Data
#Using data from the outside world
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)
#Setting up the data so it can be used properly
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 0.716Figure Recreation
#Figure recreation: the most difficult thing I've ever done
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$values), by = 0.02),labels = scales::number_format(accuracy = 0.02)) +
theme_minimal()+
theme(legend.title = element_text(face = "bold", size = 14),axis.text.y = element_blank(),axis.ticks.y = element_blank(),axis.title.y = element_blank(), axis.line.x = element_line(size = 2, color = "black"), plot.title = element_text(hjust=0.5,face="bold"),panel.grid.major.y = element_blank(), panel.grid.minor.x=element_blank(),panel.grid.major.x = element_line(color = "grey", linetype = "dashed", size = 1.5),legend.position = "none")+
geom_text(aes(x="SVMWithGradCAMMaps",label="SVM + GRAD-CAM++",y=0.64),vjust=-4.5,color="darkorange2",size=4.5)+
geom_text(aes(x = "SVMWithDeepShapMaps", y = 0.6, label = "SVM + Deep SHAP"),vjust = -3.5, color = "magenta4", size = 4.5)+
ylab("F1")+
ggtitle("Fig.7.Grad-CAM++saliency maps capture unique predictive information.")
Half-Violin
#Half-Violin!
ggplot(data_long, aes(x=F1Performance, y=values,fill=F1Performance))+
geom_jitter(position=position_jitter(0.1),aes(color = F1Performance), size =6, alpha = 0.8) +
geom_violinhalf(size=2, alpha=0.5,draw_quantiles = c(0.25, 0.5, 0.75), quantile.size = 2)+
coord_flip()+
scale_fill_manual(values = c("magenta4", "darkorange2")) +
scale_color_manual(values = c("magenta4", "darkorange2")) +
stat_summary(fun=median,geom="point",shape=21,size=3,fill="white",color="black",stroke=1.5)+
scale_y_continuous(limits = c(min(data_long$values), max(data_long$values)),breaks = seq(min(data_long$values), max(data_long$values), by = 0.02),labels = scales::number_format(accuracy = 0.02)) +
theme_minimal()+
theme(legend.title = element_text(face = "bold", size = 14),axis.text.y = element_blank(),axis.ticks.y = element_blank(),axis.title.y = element_blank(), axis.line.x = element_line(size = 2, color = "black"), plot.title = element_text(hjust=0.5,face="bold"),panel.grid.major.y = element_blank(), panel.grid.minor.x=element_blank(),panel.grid.major.x = element_line(color = "grey", linetype = "dashed", size = 1.5),legend.position = "none")+
geom_text(aes(x="SVMWithGradCAMMaps",label="SVM + GRAD-CAM++",y=0.64),vjust=-4.5,color="darkorange2",size=4.5)+
geom_text(aes(x = "SVMWithDeepShapMaps", y = 0.6, label = "SVM + Deep SHAP"),vjust = -3.5, color = "magenta4", size = 4.5)+
ylab("F1")+
ggtitle("Fig.7.Grad-CAM++saliency maps capture unique predictive information.")
Box+Half-Violin Plot
#Half-violin and box remix
ggplot(data_long, aes(x=F1Performance, y=values,fill=F1Performance))+
geom_jitter(position=position_jitter(0.1),aes(color = F1Performance), size =6, alpha = 0.8) +
geom_violinhalf(size=2, alpha=0.5,draw_quantiles = c(0.25, 0.5, 0.75), quantile.size = 2)+
geom_boxplot(aes(color = F1Performance), width = 0.4, alpha = 0.3, outlier.shape = NA) +
coord_flip()+
scale_fill_manual(values = c("magenta4", "darkorange2")) +
scale_color_manual(values = c("magenta4", "darkorange2")) +
stat_summary(fun=median,geom="point",shape=21,size=3,fill="white",color="black",stroke=1.5)+
scale_y_continuous(limits = c(min(data_long$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.")
Module 4: Barplots and Error Bars
Challenge Yourself 2, Task 1: Data Prep.
library(ggplot2)
library(dplyr)
data("mtcars")
head(mtcars)## mpg cyl disp hp drat wt qsec vs am gear carb
## Mazda RX4 21.0 6 160 110 3.90 2.620 16.46 0 1 4 4
## Mazda RX4 Wag 21.0 6 160 110 3.90 2.875 17.02 0 1 4 4
## Datsun 710 22.8 4 108 93 3.85 2.320 18.61 1 1 4 1
## Hornet 4 Drive 21.4 6 258 110 3.08 3.215 19.44 1 0 3 1
## Hornet Sportabout 18.7 8 360 175 3.15 3.440 17.02 0 0 3 2
## Valiant 18.1 6 225 105 2.76 3.460 20.22 1 0 3 1#just summarizing the data, no big deal
mtcars_summary <- mtcars %>%
group_by(cyl) %>%
summarise(mean_mpg = mean(mpg),
se_mpg = sd(mpg) / sqrt(n()))
head(mtcars_summary)## # A tibble: 3 × 3
## cyl mean_mpg se_mpg
## <dbl> <dbl> <dbl>
## 1 4 26.7 1.36
## 2 6 19.7 0.549
## 3 8 15.1 0.684Task 2: Bar Plot Creation
ggplot(mtcars_summary,aes(x=factor(cyl),y=mean_mpg))+
geom_bar(stat="identity")+
geom_errorbar(aes(ymin=mean_mpg, ymax=mean_mpg+se_mpg), width=0.3)
Task 3: Customize the Plot
#Making it pretty
ggplot(mtcars_summary,aes(x=factor(cyl),y=mean_mpg))+
geom_bar(stat="identity",fill="skyblue", color="black", width=0.9)+
geom_errorbar(aes(ymin=mean_mpg-se_mpg, ymax=mean_mpg+se_mpg), width=0.4, color="red")+
ggtitle("Bar Plot of Mean MPG by Cylinders")+
xlab("Number of Cylinders")+
ylab("Mean MPG")+
theme_minimal()
Module 5: Depictions of Frequency
Downloading the Data:2D Density Plot
#Pulling more data
population_data<-read.csv("log_population_data.csv")
head(population_data)## Log10_Current_Population Log10_Past_Population
## 1 4.288032 5.674204
## 2 3.817497 5.908109
## 3 4.671286 6.095078
## 4 3.538305 5.200114
## 5 4.602143 6.388435
## 6 4.839555 6.187712#Density Plot: shout out to viridis
ggplot(population_data, aes(x = Log10_Current_Population, y = Log10_Past_Population)) +
stat_density_2d(geom = "polygon", aes(fill = ..level..), color = "white") +
scale_fill_viridis_c(option = "plasma")+
ggtitle("2D Density Plot of Population Sizes")+
xlab("Log10(Current population size N0")+
ylab("Log10(Past population size N1")+
theme_minimal()
Adding Density to Margins
library(ggExtra)
library(tidyverse)
library(dplyr)
library(ggplot2)
#Pulling and formating more data
longevity_data<-read.csv("longevity_data.csv")
head(longevity_data)## species class order maximum_lifespan_yr mass_g
## 1 Dicrostonyx_groenlandicus Mammalia Rodentia 3.3 66.0
## 2 Didelphis_virginiana Mammalia Didelphimorphia 6.6 3000.0
## 3 Diphylla_ecaudata Mammalia Chiroptera 8.0 28.0
## 4 Dipodillus_campestris Mammalia Rodentia 7.3 28.4
## 5 Dipodomys_merriami Mammalia Rodentia 9.7 42.0
## 6 Dendrolagus_goodfellowi Mammalia Diprotodontia 23.6 7400.0
## volancy fossoriallity foraging_environment daily_activity
## 1 nonvolant semifossorial terrestrial cathemeral
## 2 nonvolant nonfossorial semiarboreal nocturnal
## 3 volant nonfossorial terrestrial nocturnal
## 4 nonvolant semifossorial terrestrial nocturnal
## 5 nonvolant semifossorial terrestrial nocturnal
## 6 nonvolant nonfossorial semiarboreal cathemerallong <- longevity_data %>%
mutate(
log_mass = log10(mass_g),
log_lifespan = log10(maximum_lifespan_yr)) %>%
group_by(order) %>%
mutate(order_size = n())
head(long)## # A tibble: 6 × 12
## # Groups: order [4]
## species class order maximum_lifespan_yr mass_g volancy fossoriallity
## <chr> <chr> <chr> <dbl> <dbl> <chr> <chr>
## 1 Dicrostonyx_groe… Mamm… Rode… 3.3 66 nonvol… semifossorial
## 2 Didelphis_virgin… Mamm… Dide… 6.6 3000 nonvol… nonfossorial
## 3 Diphylla_ecaudata Mamm… Chir… 8 28 volant nonfossorial
## 4 Dipodillus_campe… Mamm… Rode… 7.3 28.4 nonvol… semifossorial
## 5 Dipodomys_merria… Mamm… Rode… 9.7 42 nonvol… semifossorial
## 6 Dendrolagus_good… Mamm… Dipr… 23.6 7400 nonvol… nonfossorial
## # ℹ 5 more variables: foraging_environment <chr>, daily_activity <chr>,
## # log_mass <dbl>, log_lifespan <dbl>, order_size <int>#Density on the sides of the figure, cool stuff!
p=ggplot(long, aes(x=log_mass,y=log_lifespan, color=class))+
geom_point(aes(size=order_size),alpha=0.3)+
geom_smooth(method = "lm", aes(group = class), se = FALSE, linetype = "solid")+
scale_color_manual(values = c("lightgreen", "darkslategray"))+
ggtitle("Bubble Chart of Longevity and Body Mass")+
xlab("Log(Body Mass[g])")+
ylab("Log(Maximum Lifespan [yr])")+
theme_minimal()+
theme(
legend.position = "none",plot.title = element_text(size = 14, face = "bold"),axis.title = element_text(size = 12, face = "bold"))+
annotate("text", x=5.5, y=1.9, label="Aves",color="lightgreen", size=5, fontface= "bold")+
annotate("text", x=6, y=1.2, label="Mammals",color="darkslategray", size=5,fontface= "bold")
ggExtra::ggMarginal(p, type = "density", groupFill = TRUE, alpha = 0.4)
##Interpretation Questions
#1.Density plots are useful in the margins of your graphics to show exactly where density is occurring. In our figure we can see that the mammals density is highest at approximately x=4 and y=1.3.
#2.We are able to depict 6 different measures in a single graphic because we able to depict the two logs, maximum lifespan and body mass, as well as showing those values for both Aves and Mammals. We also made a new category by calculating the sample size of each order (order_size), which we also displayed in the figure. We also displayed the density using ggExtra.
#3.The relationship between Longevity and Body mass is positive, body mass increasing as the animals gets older. This relationship is more extreme in Aves, displayed by the steeper slope of it's related line.
#4.I believe the bias depends on which type of organism you're looking at. Mammals have a biased for larger, longer lived individuals, this is shown by the clumping together of dots closer to the line in that area while the dots get farther from the line when the body mass is smaller. Aves bias seems to favor those that are smaller and long lived birds which can be seen with the line but also with the density portion of the figure.
#5.The only element that I could think to add would be a key for the size variation, but I assume that type of thing could be added into the caption when it would be added to the paper, though you should be able to read a figure without a caption.Design it Yourself: Body condition, Inc. Duration, Treatment
scelop<-read.csv("Scelop_Data.csv")
head(scelop)## Egg OvipDate Cage Treatment Temperature Moisture EggMass HatchingSuccess
## 1 1 6/10/2022 5 1 High High 0.377 1
## 2 10 6/10/2022 5 2 Low High 0.391 1
## 3 11 6/10/2022 5 3 High Low 0.358 1
## 4 16 6/15/2022 9 4 Low Low 0.364 1
## 5 17 6/15/2022 9 1 High High 0.309 0
## 6 19 6/15/2022 9 3 High Low 0.330 0
## HatchDate IncDuration Sex SVL TL HatchMass BodyConPCA OffMassPCA
## 1 7/27/2022 47 M 26 30 0.502 1.4168605 0.9954916
## 2 8/12/2022 63 F 22 24 0.543 0.5651503 1.6654549
## 3 7/26/2022 46 M 25 29 0.501 1.0706865 0.7334526
## 4 8/15/2022 61 F 22 22 0.331 -1.9458048 -1.2010403
## 5 NA NA NA NA NA NA
## 6 NA NA NA NA NA NAscelop$Treatment <- factor(scelop$Treatment)
levels(scelop$Treatment)## [1] "1" "2" "3" "4"liz<-ggplot(scelop, aes(x=BodyConPCA,y=IncDuration, color=Treatment))+
geom_point(alpha=0.4,aes(size=4))+
scale_color_manual(values = c("blue3", "steelblue1", "darkorange4", "goldenrod2")) +
ggtitle("Body Condition and Incubation Duration by Treatment")+
xlab("Body Condition")+
ylab("Incubation Duration (days)")+
theme_minimal()+
theme(legend.position = "left",plot.title = element_text(size = 14, face = "bold"),axis.title = element_text(size = 12, face = "bold"))+
guides(size = "none")
ggExtra::ggMarginal(liz, type = "density", groupFill = TRUE, alpha = 0.4)
Module 6: Multipanel Graphics
Figure 1: Facet Wrap
data("esoph")
head(esoph)## agegp alcgp tobgp ncases ncontrols
## 1 25-34 0-39g/day 0-9g/day 0 40
## 2 25-34 0-39g/day 10-19 0 10
## 3 25-34 0-39g/day 20-29 0 6
## 4 25-34 0-39g/day 30+ 0 5
## 5 25-34 40-79 0-9g/day 0 27
## 6 25-34 40-79 10-19 0 7?esoph
#Learning some "facet_wrap()"
alc<-ggplot(esoph, aes(x = agegp, y = ncases, group = alcgp, color = alcgp)) +
geom_line(size=1) +
facet_wrap(~ alcgp) +
ggtitle("Line Plot of Esophageal Cancer Cases by Age and Alcohol Consumption") +
xlab("Age Group") +
ylab("Number of Cases") +
theme_minimal()
alc
Figure 2: Facet Wrap
head(ChickWeight)## Grouped Data: weight ~ Time | Chick
## weight Time Chick Diet
## 1 42 0 1 1
## 2 51 2 1 1
## 3 59 4 1 1
## 4 64 6 1 1
## 5 76 8 1 1
## 6 93 10 1 1?ChickWeight
#Learning more "facet_wrap()" but add some more stuff like more lines and se
chi<-ggplot(ChickWeight, aes(x = Time, y = weight, color = factor(Chick))) +
geom_line(alpha = 0.9, size=0.8)+
geom_smooth(aes(group = factor(Diet)), se = TRUE, fill = "darkgray", color = "black", size=1.2) +
facet_wrap(~Diet, ncol= 4)+
ggtitle("Chick Growth by Diet Type") +
xlab("Time (Days)") +
ylab("Weight (Grams)") +
theme_minimal() +
theme(legend.position ="none",plot.title = element_text(size = 14),axis.title = element_text(size=12),strip.text = element_text(size = 12, face = "bold"))
chi
Figure 3: Adding Seperate Plots to one Figure
library(ggpubr)
library(grid)
library(gridExtra)
#The actual most difficult thing I've ever had to do
head(CO2)## Grouped Data: uptake ~ conc | Plant
## Plant Type Treatment conc uptake
## 1 Qn1 Quebec nonchilled 95 16.0
## 2 Qn1 Quebec nonchilled 175 30.4
## 3 Qn1 Quebec nonchilled 250 34.8
## 4 Qn1 Quebec nonchilled 350 37.2
## 5 Qn1 Quebec nonchilled 500 35.3
## 6 Qn1 Quebec nonchilled 675 39.2?CO2
###Multi Panel data("CO2") head(CO2) ?CO2
CO2$TreatmentType <- interaction(CO2$Treatment, CO2$Type)
CO2$PlantType <- interaction(CO2$Plant, CO2$Type)
##Violin, uptake(uptake) by treatment, grouped by type
vn<-ggplot(CO2, aes(x=uptake, y=Treatment,fill=TreatmentType))+ geom_jitter(position=position_jitter(0.1),aes(color = TreatmentType)) + geom_violin(alpha=0.5)+ scale_fill_manual(values = c("cyan3", "darkorange1", "goldenrod2", "tan4")) + scale_color_manual(values = c("cyan3", "darkorange1", "goldenrod2", "tan4")) + theme(legend.position="right",plot.title.position = "plot",plot.margin = margin(t = 50, r = 20, b = 20, l = 20))+ xlab("Uptake Rates (μmol/m2sec)")+ ggtitle("CO2 Uptake of Grass Plants in Chilled and Unchilled Conditions")
vn
##Line plot, ambient CO2(conc) uptake, colored and grouped by treatment
ln<-ggplot(CO2, aes(x=conc,y=uptake,fill=Treatment))+ geom_point(aes(color = Treatment))+ geom_smooth(aes(color = Treatment),method=lm, alpha=0.3)+ facet_wrap(~Type, ncol= 4)+ scale_fill_manual(values = c("tomato", "steelblue2")) + scale_color_manual(values = c("tomato", "steelblue2")) + ggtitle("Ambient CO2 Concentration by Uptake Rates and Treatment")+ ylab("Uptake Rates(μmol/m2sec)")+ xlab("C02 Concentration (mL/L")+ theme_minimal()
ln
##Additional plot of your choice that shows a new element: Boxplot
bx<-ggplot(CO2, aes(x = Treatment, y = uptake, fill = Treatment)) + geom_boxplot() + ggtitle("CO2 Uptake Rates by Treatment Type")+ xlab("Treatment")+ ylab("Uptake Rates (μmol/m2sec)") + scale_fill_manual(values = c("nonchilled" = "tomato", "chilled" = "steelblue2")) + theme_minimal()
bx
##Add them together!
vn<- vn +theme(plot.margin = margin(5, 5, 5, 5), aspect.ratio = 1,axis.title.y=element_blank(),axis.title.x=element_text(size=7),plot.title = element_blank(),legend.position = "bottom",legend.key.size = unit(0.3, "cm"),legend.text = element_text(size = 5),legend.title = element_blank(),legend.box = "horizontal",legend.direction = "horizontal", legend.key.height = unit(0.3, "cm"), legend.key.width = unit(1, "cm"),legend.box.spacing = unit(0.2, "cm")) + guides(fill = guide_legend(ncol = 2))
ln<- ln + theme(plot.margin = margin(5, 5, 5, 5), aspect.ratio = 1, plot.title = element_blank(), legend.position = "bottom", axis.title.y = element_text(size=7),axis.text.x = element_text(size = 7), axis.text.y = element_text(size=7),legend.key.size = unit(0.3, "cm"),legend.text = element_text(size = 5),legend.title = element_blank(),legend.box = "horizontal",legend.direction = "horizontal", legend.key.height = unit(0.3, "cm"), legend.key.width = unit(0.5, "cm"),legend.box.spacing = unit(0.2, "cm")) + guides(fill = guide_legend(ncol = 2))
bx<- bx + theme(plot.margin = margin(5, 5, 5, 5), aspect.ratio = 1, plot.title = element_blank(),axis.title.y = element_text(size=5),axis.title.x=element_text(size=7), legend.position = "right",legend.key.size = unit(0.3, "cm"),legend.text = element_text(size = 5),legend.title = element_blank(),legend.box = "horizontal",legend.direction = "horizontal", legend.key.height = unit(0.5, "cm"), legend.key.width = unit(0.5, "cm"),legend.box.spacing = unit(0.3, "cm")) + guides(fill = guide_legend(ncol = 2))
combined<-ggarrange(bx, ln, vn, labels = c("A", "B", "C"),ncol = 2, nrow = 2,heights = c(1, 1), widths = c(1, 1), align = "hv")
grid.arrange(
combined,
top = textGrob("Carbon Dioxide Uptake in Grass Plants by Orgin and in Chilled and Nonchilled Conditions",
gp = gpar(fontsize = 10, fontface = "bold"))
)
Final Project: Going Crazy
Figure 1: Hatch Success & Treatment
##The data!
##Same data set as used in Mod. 5: Design it yourself
head(scelop)## Egg OvipDate Cage Treatment Temperature Moisture EggMass HatchingSuccess
## 1 1 6/10/2022 5 1 High High 0.377 1
## 2 10 6/10/2022 5 2 Low High 0.391 1
## 3 11 6/10/2022 5 3 High Low 0.358 1
## 4 16 6/15/2022 9 4 Low Low 0.364 1
## 5 17 6/15/2022 9 1 High High 0.309 0
## 6 19 6/15/2022 9 3 High Low 0.330 0
## HatchDate IncDuration Sex SVL TL HatchMass BodyConPCA OffMassPCA
## 1 7/27/2022 47 M 26 30 0.502 1.4168605 0.9954916
## 2 8/12/2022 63 F 22 24 0.543 0.5651503 1.6654549
## 3 7/26/2022 46 M 25 29 0.501 1.0706865 0.7334526
## 4 8/15/2022 61 F 22 22 0.331 -1.9458048 -1.2010403
## 5 NA NA NA NA NA NA
## 6 NA NA NA NA NA NA#Hatching Success by Treatment: Density
first<-ggplot(scelop, aes(x = HatchingSuccess, fill = Treatment)) +
geom_density(alpha = 0.6) +
facet_wrap(~Treatment, ncol= 4)+
scale_fill_manual(values = c("#56B4E9", "#009E73", "#F0E442", "#D55E00")) +
ggtitle("Density Plot of Hatching Success by Treatment") +
xlab("Hatching Success") +
ylab("Density") +
theme(legend.position="none", axis.text.x = element_text(size = 6),plot.title = element_text(size = 12, face = "bold"))
first
Figure 2: Clutch size & body con., Treatment & Body con., Inc Dur. & Body Con.
##Still don't know how clutch size is calculated for this first part
##Treatment and Body Con (Box plot)
BCT<-ggplot(scelop, aes(x = Treatment, y = BodyConPCA, fill = Treatment)) +
geom_violin(color = "black") +
geom_jitter(width = 0.2, alpha = 0.5) +
labs(x = "Treatment", y = "Body Condition") +
scale_fill_manual(values = c("#56B4E9","#009E73","#F0E442","#D55E00"))+
theme(legend.position="bottom")
BCT
##IncDur and Body Con (point with lines for treatment)
IDBC<-ggplot(scelop, aes(x=IncDuration,y=BodyConPCA, color=Treatment))+
geom_point(size=2)+
geom_smooth(method=lm,aes(group = Treatment), se=FALSE)+
scale_color_manual(values = c("#56B4E9","#009E73","#F0E442","#D55E00")) +
labs(y="Body Condition",x="Incubation Duration")+
theme(legend.position="bottom")
IDBC
##Put it together!!
two<-ggarrange(BCT,IDBC, labels = c("A", "B"),ncol = 2, nrow = 1,heights = c(1, 1), widths = c(1, 1), align = "hv")
second<-grid.arrange(two, top = textGrob("Body Condition by Treatment and Incubation Duration", gp = gpar(fontsize = 12, fontface = "bold")))
Figure 3: Inc. Dur. & Treatment, SVL & Treatment
#box-plot, incubation duration by treatment
scelop$Treatment <- as.factor(scelop$Treatment)
IncTreat<-ggplot(scelop, aes(x = Treatment, y = IncDuration, fill = Treatment)) +
geom_boxplot(color = "black") +
geom_jitter(width = 0.2, alpha = 0.5) +
labs(x = "Treatment", y = "Incubation Duration (Days)") +
scale_fill_manual(values = c("#56B4E9","#009E73","#F0E442","#D55E00")) +
theme(legend.position="bottom")
IncTreat
#line-histogram combo situation, svl by treatment
LnSVL<-ggplot(scelop, aes(x = SVL, y = IncDuration, group = Treatment, color = Treatment)) +
geom_point(size=2)+
geom_smooth(method = "lm", aes(group = Treatment), se = FALSE, linetype = "solid")+
labs(x= "Snout Vent Length", y="Incubation Duration") +
scale_color_manual(values = c("#56B4E9","#009E73","#F0E442","#D55E00")) +
theme(legend.position = "bottom")
HLS<-ggExtra::ggMarginal(LnSVL, type = "histogram", groupFill = TRUE, alpha = 0.4)
HLS
#multipanel that shit!
three<-ggarrange(IncTreat,HLS, labels = c("A", "B"),ncol = 2, nrow = 1,heights = c(1, 1), widths = c(1, 1), align = "hv")
third<-grid.arrange(three, top = textGrob("Incubation Duration by Treatment Group and SVL", gp = gpar(fontsize = 12, fontface = "bold")))
Figure 4.HatchMass & IncDuration by Treatment
four<-ggplot(scelop, aes(x=HatchMass,y=IncDuration, color=Treatment))+
geom_point(size=5, alpha=0.8)+
scale_color_manual(values = c("#56B4E9","#009E73","#F0E442","#D55E00")) +
labs(title="Hatchling Mass by Incubation Duration",y="Incubation Duration",x="Hatchling Mass")+
theme(legend.position="bottom", plot.title = element_text(size = 12, face = "bold"))
fourth<-ggExtra::ggMarginal(four, type = "density", groupFill = TRUE, alpha = 0.4)
fourth