Penguins EDA

1 Penguin Size and Mass by Sex and Species

library(palmerpenguins) 
library(dplyr)
library(ggplot2)
library(tidyr)
library(DBI)
library(duckdb)

# df <- palmerpenguins::penguins%>% drop_na()
# query data from duckdb database
con = DBI::dbConnect(duckdb::duckdb(), dbdir = "my-db.duckdb")
df = dplyr::tbl(con, "penguins")

  df %>%
  group_by(species, sex) %>%
  summarise(
    across(
        ends_with("mm") | ends_with("g"),
      \(x) mean(x, na.rm = TRUE)
      )
    ) %>%
  # not required, but illustrates that work has been pushed off to duckdb
  dplyr::collect() %>%
  knitr::kable()

species	sex	bill_length_mm	bill_depth_mm	flipper_length_mm	body_mass_g
Adelie	NA	37.84000	18.32000	185.6000	3540.000
Gentoo	female	45.56379	14.23793	212.7069	4679.741
Adelie	male	40.39041	19.07260	192.4110	4043.493
Chinstrap	male	51.09412	19.25294	199.9118	3938.971
Adelie	female	37.25753	17.62192	187.7945	3368.836
Gentoo	NA	45.62500	14.55000	215.7500	4587.500
Gentoo	male	49.47377	15.71803	221.5410	5484.836
Chinstrap	female	46.57353	17.58824	191.7353	3527.206

2 Penguin Size vs Mass by Species

# shifting backend to duckdb required refactoring pipe to keep operations
# together
df %>%
  filter(!is.na(species), !is.na(bill_length_mm), !is.na(body_mass_g)) %>%
  mutate(colour = case_when(
    (species == "Adelie") ~ "#ff7400",
    (species == "Chinstrap") ~ "#c35ccc",
    (species == "Gentoo") ~ "#057275",
    TRUE ~ ""
  )) %>%
  ggplot(aes(x = bill_length_mm, y = body_mass_g, colour = colour)) +
  geom_point() +
  geom_smooth(method = "lm") +
  scale_color_manual(
    values = c("#ff7400", "#c35ccc", "#057275"),
    labels = c("Adelie", "Chinstrap", "Gentoo")
  ) +
  theme_bw()

DBI::dbDisconnect(con, shutdown = TRUE)