Lecture 22 Code

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.1     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.2     ✔ tibble    3.2.1
✔ lubridate 1.9.2     ✔ tidyr     1.3.0
✔ purrr     1.0.1     
── 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(palmerpenguins)
knn_distance <- \(x, y, p){
  (sum(abs(x-y)^p))^(1/p)
}

new_penguin <- c(40, 19, 185, 3345)
penguins_df <- penguins %>% drop_na()
penguins_mat <- penguins_df[,c(3:6)]
penguins_df$manhattan <- penguins_mat %>% 
  apply(1, knn_distance, y = new_penguin, p = 1)

penguins_df$euclidean <- penguins_mat %>% 
  apply(1, knn_distance, y = new_penguin, p = 2)

penguins_df$m5 <- penguins_mat %>% 
  apply(1, knn_distance, y = new_penguin, p = 5)

penguins_df %>% arrange(manhattan) %>% 
  select(species, manhattan) %>% head(8)

# A tibble: 8 × 2
  species   manhattan
  <fct>         <dbl>
1 Chinstrap      11.2
2 Chinstrap      11.8
3 Adelie         14.9
4 Adelie         15.3
5 Adelie         22.3
6 Adelie         25.5
7 Adelie         27.2
8 Adelie         27.6

penguins_df %>% arrange(euclidean) %>% 
  select(species, manhattan) %>% head(8)

# A tibble: 8 × 2
  species   manhattan
  <fct>         <dbl>
1 Chinstrap      11.2
2 Chinstrap      11.8
3 Adelie         15.3
4 Adelie         14.9
5 Adelie         22.3
6 Adelie         25.5
7 Adelie         27.6
8 Adelie         27.2

penguins_df %>% arrange(m5) %>% 
  select(species, manhattan) %>% head(8)

# A tibble: 8 × 2
  species   manhattan
  <fct>         <dbl>
1 Chinstrap      11.2
2 Chinstrap      11.8
3 Adelie         15.3
4 Adelie         14.9
5 Adelie         22.3
6 Adelie         25.5
7 Adelie         27.6
8 Adelie         27.2