library(tidyverse)

# Joins, summarise and plot ----------------------------------------------------
station <- 
  read_csv("https://heima.hafro.is/~einarhj/data/is_smb_stations.csv")
biological <- 
  read_csv("https://heima.hafro.is/~einarhj/data/is_smb_biological.csv")
station %>% select(id:lat1) %>%  arrange(id) %>% glimpse()
biological %>% arrange(id) %>% glimpse()

d <- 
  station %>% 
  select(id, date, lon1, lat1) |> 
  left_join(biological |> 
              filter(species == "monkfish"),
            by = join_by(id))

d <- 
  d |> 
  mutate(species = replace_na(species, "monkfish"),
         kg = replace_na(kg, 0),
         n = replace_na(n, 0))
d

d_sum <-
  d |> 
  mutate(year = year(date)) |> 
  group_by(year) |> 
  summarise(n = n(),
            min_kg = min(kg),
            max_kg = max(kg),
            mean_kg = mean(kg),
            sd_kg = sd(kg),
            se_kg = sd_kg / sqrt(n),
            error = se_kg * 1.96,
            sum_kg = sum(kg))
d_sum
d_sum |> 
  mutate(se_lower = mean_kg - error, 
         se_upper = mean_kg + error) |> 
  ggplot() +
  geom_pointrange(aes(year, mean_kg, ymin = se_lower, ymax = se_upper),
                  size = 0.5)

# joins ------------------------------------------------------------------------
x <- tibble(A = c("a", "b", "c"),
            B = c("t", "u", "v"),
            C = c(1, 2, 3))
y <- tibble(A = c("a", "b", "d"),
            B = c("t", "u", "w"),
            D = c(3, 2, 1))
x
y
left_join(x, y)
right_join(x, y)
left_join(y, x)
inner_join(x, y)
full_join(x, y)

# binds and things ----------------------------------------
x <- tibble(A = c("a", "b", "c"),
            B = c("t", "u", "v"),
            C = c(1, 2, 3))

y <- tibble(A = c("c", "d"),
            B = c("v", "w"),
            C = c(3, 4))
x
y
bind_rows(x, y)
union(x, y)
intersect(x, y)
setdiff(x, y)
setdiff(y, x)