TAPPONNIER Data Visualization Code
2024-12-16
MODULE 2:Practice Assignment
MODULE 3: Box and Violin
MODULE 4: Bar Plots 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 1mtcars_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 0.684#Task 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
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
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 6.187712ggplot(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()## Warning: The dot-dot notation (`..level..`) was deprecated in ggplot2 3.4.0.
## ℹ Please use `after_stat(level)` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
library(ggExtra)
library(tidyverse)
library(dplyr)
library(ggplot2)
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>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)