library(ggExtra)
library(tidyverse)
## Warning: package 'lubridate' was built under R version 4.3.3
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dplyr)
library(ggplot2)
#First Plot
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
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 = "viridis")+
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.
#Second Plot
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 cathemeral
long <- longevity_data %>% #create a new dataframe called "long" that contains all your newly calculated variables
mutate( #mutate tells the program to perform new calculations
log_mass = log10(mass_g), # create a new column called "log_mass" which Log-transforms mass values
log_lifespan = log10(maximum_lifespan_yr)) %>% # create a new colummn called "log_lifespan" that Log-transforms lifespan value
group_by(order) %>% # this tells it that after "mutate", you are going to start a new function. for each "order" or group of animals
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)
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
## `geom_smooth()` using formula = 'y ~ x'
#Create your own
data("diamonds")
library(ggplot2)
head(diamonds)
## # A tibble: 6 × 10
## carat cut color clarity depth table price x y z
## <dbl> <ord> <ord> <ord> <dbl> <dbl> <int> <dbl> <dbl> <dbl>
## 1 0.23 Ideal E SI2 61.5 55 326 3.95 3.98 2.43
## 2 0.21 Premium E SI1 59.8 61 326 3.89 3.84 2.31
## 3 0.23 Good E VS1 56.9 65 327 4.05 4.07 2.31
## 4 0.29 Premium I VS2 62.4 58 334 4.2 4.23 2.63
## 5 0.31 Good J SI2 63.3 58 335 4.34 4.35 2.75
## 6 0.24 Very Good J VVS2 62.8 57 336 3.94 3.96 2.48
summary(diamonds)
## carat cut color clarity depth
## Min. :0.2000 Fair : 1610 D: 6775 SI1 :13065 Min. :43.00
## 1st Qu.:0.4000 Good : 4906 E: 9797 VS2 :12258 1st Qu.:61.00
## Median :0.7000 Very Good:12082 F: 9542 SI2 : 9194 Median :61.80
## Mean :0.7979 Premium :13791 G:11292 VS1 : 8171 Mean :61.75
## 3rd Qu.:1.0400 Ideal :21551 H: 8304 VVS2 : 5066 3rd Qu.:62.50
## Max. :5.0100 I: 5422 VVS1 : 3655 Max. :79.00
## J: 2808 (Other): 2531
## table price x y
## Min. :43.00 Min. : 326 Min. : 0.000 Min. : 0.000
## 1st Qu.:56.00 1st Qu.: 950 1st Qu.: 4.710 1st Qu.: 4.720
## Median :57.00 Median : 2401 Median : 5.700 Median : 5.710
## Mean :57.46 Mean : 3933 Mean : 5.731 Mean : 5.735
## 3rd Qu.:59.00 3rd Qu.: 5324 3rd Qu.: 6.540 3rd Qu.: 6.540
## Max. :95.00 Max. :18823 Max. :10.740 Max. :58.900
##
## z
## Min. : 0.000
## 1st Qu.: 2.910
## Median : 3.530
## Mean : 3.539
## 3rd Qu.: 4.040
## Max. :31.800
##
ggplot(diamonds, aes(x = price)) +
geom_histogram(aes(y = ..density..), bins = 30, fill = "skyblue", alpha = 0.7) +
geom_density(color = "darkblue", size = 1) +
ggtitle("Diamond Prices") +
xlab("Price") +
ylab("Density") +
theme_minimal()
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
#Interpretation Questions
#1 density plots in the margins show the distribution of individual variables, this makes it easier to see patterns, clusters, or outliers without overcrowding the main graphic
#2 The x-axis represents the logarithmic scale of body mass, in grams, for different species. The y-axis represents the logarithmic scale of maximum lifespan, in years, for different species. Each bubble's color tells the viewer whether this point is about mammals or aves. The top marginal density plot shows the distribution of the logarithmic body mass for both categories. The right marginal density plot shows the distribution of the logarithmic maximum lifespan and the point size represents the number of species in each order
#3 The relationship is positive, indicating that larger animals live longer. Aves have a steeper slope than mammals, meaning the relationship between longevity and body mass is stronger in birds
#4 The data is more biased towards shorter lived smaller animals, this is apparent because the points are more clustered in the lower left corner. This is most likely because smaller shorter lived animals, like mice, tend to have more offspring compared to larger longer lived animals.
#5 The plot is missing a legend. A legend would make it easier to decipher what the graphics on the plot represent.