Explorativ dataanalys

penguins_summary <- penguins|> 
  group_by(species, sex)|> 
  summarize(
    bill_length_mm_mean = mean(bill_length_mm, na.rm = TRUE),
    bill_length_mm_sd   = sd(bill_length_mm, na.rm = TRUE),
    bill_depth_mm_mean  = mean(bill_depth_mm, na.rm = TRUE),
    bill_depth_mm_sd    = sd(bill_depth_mm, na.rm = TRUE),
    flipper_length_mm_mean = mean(flipper_length_mm, na.rm = TRUE),
    flipper_length_mm_sd   = sd(flipper_length_mm, na.rm = TRUE),
    body_mass_g_mean     = mean(body_mass_g, na.rm = TRUE),
    body_mass_g_sd       = sd(body_mass_g, na.rm = TRUE),
    n = n(),
    .groups = "drop"
  )|> 
  # Runda medelvärden och standardavvikelser till 1 decimal
  mutate(
    across(contains("_mean"), ~ round(.x, 1)),
    across(contains("_sd"), ~ round(.x, 1))
  )|> 
  # Byt namn på kolumnerna 
  rename(
    "Art"                        = species,
    "Kön"                        = sex,
    "Näbblängd (mm) Medel"       = bill_length_mm_mean,
    "Näbblängd (mm) SD"          = bill_length_mm_sd,
    "Näbbdjup (mm) Medel"        = bill_depth_mm_mean,
    "Näbbdjup (mm) SD"           = bill_depth_mm_sd,
    "Simfenslängd (mm) Medel"    = flipper_length_mm_mean,
    "Simfenslängd (mm) SD"       = flipper_length_mm_sd,
    "Kroppsvikt (g) Medel"       = body_mass_g_mean,
    "Kroppsvikt (g) SD"          = body_mass_g_sd,
    "Antal"                      = n
  )

penguins_summary

# filtrera manligapingviner och skapa en tabell för dom
tbl_male <- penguins|> 
  filter(sex == "male")|> 
  tbl_summary(
    by = species,
    statistic = list(
      all_continuous() ~ "{mean} ({sd})",
      all_categorical() ~ "{n} ({p}%)"
    ),
    missing = "always"
  )|> 
  bold_labels()


# filtrera kvinligapingviner och skapa en tabell för dom
tbl_female <- penguins|> 
  filter(sex == "female")|> 
  tbl_summary(
    by = species,
    statistic = list(
      all_continuous() ~ "{mean} ({sd})",
      all_categorical() ~ "{n} ({p}%)"
    ),
    missing = "always"
  )|> 
  bold_labels()

# Sätta ihop tabellerna
tbl_merged <- tbl_merge(
  tbls = list(tbl_male, tbl_female),
  tab_spanner = c("**Male**", "**Female**")
)

tbl_merged

penguins_long_c <- penguins |> 
   select(where(is.factor)) |> 
  pivot_longer(cols = c(everything()), 
               names_to = "variable", 
               values_to = "category")

penguins_long_c |> 
  ggplot(aes(y = category)) +
  geom_bar() +
  facet_wrap(~variable, scales = "free")

penguins|> 
  filter(!is.na(bill_length_mm))|> 
  ggplot(aes(x = bill_length_mm)) +
  geom_histogram(binwidth = 2, fill = "steelblue", color = "white") 

penguins |> 
  filter(!is.na(bill_depth_mm)) |> 
  ggplot(aes(x = bill_depth_mm)) +
  geom_density(fill = "gold3", color = "gold4", alpha = 0.7) 

penguins_long <- penguins |> 
   select(where(is.numeric)) |> 
  pivot_longer(cols = everything(), 
               names_to = "variable", 
               values_to = "value")


penguins_long |> 
  ggplot(aes(x = value)) +
  geom_density(fill = "indianred", alpha = 0.7)  +
  facet_wrap(~ variable, scales = "free") +
  labs(
    title = "Histogram över kontinuerliga variabler i penguins-datat",
    x = "Värde",
    y = "Densitet"
  )

ggplot(data = penguins_long, 
       aes(
           y = value)) +
  geom_boxplot()  +
  facet_wrap(~ variable, scales = "free")

library(patchwork)

# Skapa histogram
hist_plot <- penguins |> 
  filter(!is.na(flipper_length_mm)) |> 
  ggplot(aes(x = flipper_length_mm)) +
  geom_histogram(binwidth = 5, fill = "steelblue", color = "white") +
  labs(
    title = "Histogram över Simmfenslängd"
  )

# Skapa Q-Q-plot
qq_plot <- penguins|> 
  filter(!is.na(flipper_length_mm))|> 
  ggplot(aes(sample = flipper_length_mm)) +
  geom_qq(color = "navy") +
  geom_qq_line(color = "red") +
  labs(
    title = "Q-Q-plot för Simmfenslängd",
    x = "Teoretiska kvintiler",
    y = "Verkliga kvantiler"
  )

# Kombinera med patchwork
hist_plot + qq_plot