Birds

# Load dplyr for data manipulation
library(dplyr)

create_bird_dataset <- function(seed = 50, samples_per_species = 1000) {
  set.seed(seed)
  
  species <- c("Peregrine Falcon", "Mallard Duck", "American Robin", "Bald Eagle", "House Sparrow",
               "Great Horned Owl", "Northern Cardinal", "Canada Goose", "European Starling", "Ruby-throated Hummingbird")
  
  bird_attributes <- list(
    "Peregrine Falcon" = list(weight = c(700, 1500), speed = c(320, 390), beak = c(20, 25), wing = c(350, 400), diet = "Carnivore", max_age = 20),
    "Mallard Duck"     = list(weight = c(700, 1300), speed = c(80, 100),  beak = c(30, 45), wing = c(250, 300), diet = "Omnivore", max_age = 15),
    "American Robin"   = list(weight = c(75, 85),    speed = c(30, 50),   beak = c(12, 15), wing = c(150, 180), diet = "Omnivore", max_age = 6),
    "Bald Eagle"       = list(weight = c(3000, 6300),speed = c(120, 160), beak = c(40, 50), wing = c(1800, 2300), diet = "Carnivore", max_age = 25),
    "House Sparrow"    = list(weight = c(24, 40),    speed = c(40, 50),   beak = c(7, 10),  wing = c(80, 110), diet = "Omnivore", max_age = 5),
    "Great Horned Owl" = list(weight = c(900, 1600), speed = c(40, 55),   beak = c(25, 30), wing = c(400, 500), diet = "Carnivore", max_age = 18),
    "Northern Cardinal"= list(weight = c(40, 50),    speed = c(30, 50),   beak = c(13, 16), wing = c(110, 140), diet = "Omnivore", max_age = 7),
    "Canada Goose"     = list(weight = c(3000, 6000),speed = c(65, 90),   beak = c(40, 60), wing = c(400, 550), diet = "Herbivore", max_age = 25),
    "European Starling"= list(weight = c(70, 100),   speed = c(50, 60),   beak = c(14, 17), wing = c(150, 180), diet = "Omnivore", max_age = 6),
    "Ruby-throated Hummingbird" = list(weight = c(2, 4), speed = c(40, 50), beak = c(10, 12), wing = c(50, 60), diet = "Omnivore", max_age = 5)
  )
  
  generate_bird_data <- function(species_name, n) {
    attrs <- bird_attributes[[species_name]]
    
    weight <- runif(n, attrs$weight[1], attrs$weight[2])
    speed <- runif(n, attrs$speed[1], attrs$speed[2])
    beak_depth <- runif(n, attrs$beak[1], attrs$beak[2])
    wing_length <- runif(n, attrs$wing[1], attrs$wing[2])
    
    gender <- sample(c("Male", "Female"), n, replace = TRUE)
    
    age <- runif(n, 0, attrs$max_age)
    
    diet <- rep(attrs$diet, n)
    
    data.frame(
      Species = species_name,
      Weight_g = round(weight, 1),
      Top_Speed_kmh = round(speed, 1),
      Beak_Depth_mm = round(beak_depth, 1),
      Wing_Length_mm = round(wing_length, 1),
      Gender = gender,
      Age_years = round(age, 1),
      Diet = diet
    )
  }
  
  bird_dataset <- do.call(rbind, lapply(species, generate_bird_data, n = samples_per_species))
  
  # Convert categorical columns to factors for better handling
  bird_dataset$Species <- as.factor(bird_dataset$Species)
  bird_dataset$Gender <- as.factor(bird_dataset$Gender)
  bird_dataset$Diet <- as.factor(bird_dataset$Diet)
  
  return(bird_dataset)
}

# Generate the full bird dataset
birds <- create_bird_dataset()

# Sample 20 rows per species for display
sampled_birds <- birds %>%
  group_by(Species) %>%
  slice_sample(n = 20) %>%
  ungroup()

# Print the sampled data table
print(sampled_birds)

NA

data("sampled_birds")

Warning in data("sampled_birds") : data set ‘sampled_birds’ not found

library(tidyverse)
library(ggplot2)

ggplot(sampled_birds,aes(Top_Speed_kmh))+
  geom_histogram()

`stat_bin()` using `bins = 30`. Pick better value with
`binwidth`.

NA

This graph shows that the majority of birds are in the

0-200 kilometers per hours range

ggplot(sampled_birds,aes(Beak_Depth_mm,fill = Species))+
  geom_histogram()

`stat_bin()` using `bins = 30`. Pick better value with
`binwidth`.

This graph shows the different species and how they have different beak depth.

ggplot(sampled_birds,aes(Top_Speed_kmh,fill = Gender))+
  geom_histogram()

`stat_bin()` using `bins = 30`. Pick better value with
`binwidth`.

This shows that there is no correlation between genders and top speed.

ggplot(sampled_birds,aes(Wing_Length_mm,fill = Species))+
  geom_histogram()

ggplot(sampled_birds,aes(Beak_Depth_mm,fill = Diet))+
  geom_histogram()

ggplot(sampled_birds, aes(x = Weight_g, y = Wing_Length_mm)) +
  geom_point() +
  geom_smooth(method = "lm", se = FALSE) +
  labs(title = "Birds", x = "Weight", y = "Wing Length")

model <- lm(Top_Speed_kmh ~ Wing_Length_mm, data = sampled_birds)
summary(model)

ggplot(sampled_birds, aes(x = Top_Speed_kmh, y = Wing_Length_mm)) +
  geom_point(color = "blue") +
  geom_smooth(method = "lm", se = FALSE)+
  theme_minimal() +
  labs(title = "Top Speed VS Wing Length")

I used code to generate data about birds

ggplot(sampled_birds, aes(x = Beak_Depth_mm, y = Wing_Length_mm)) +
  geom_point(color = "blue") +
  geom_smooth(method = "lm", se = FALSE) +
  theme_minimal() +
  labs(title = "Beak Depth VS Wing Length")

`geom_smooth()` using formula = 'y ~ x'

This shows that the larger the beak the wider the wing length and the opposite should also be true.

ggplot(sampled_birds, aes(x = Weight_g, y = Wing_Length_mm)) +
  geom_point(color = "blue") +
  geom_smooth(method = "lm", se = FALSE)+
  theme_minimal() +
  labs(title = "Weight VS Wing Length")

`geom_smooth()` using formula = 'y ~ x'

This signifies that the weight affects the wing length.

ggplot(sampled_birds, aes(x = Beak_Depth_mm, y = Age_years)) +
  geom_point(color = "blue") +
  geom_smooth(method = "lm", se = FALSE)+
  theme_minimal() +
  labs(title = "Beak Depth VS Age")

`geom_smooth()` using formula = 'y ~ x'

this shows that the correlation between beak depth and age have a possitive slope.