Collections by latitude

The collection by numbers (01/01/2024):

• 4143 samples across the Eastern Australian coastline

• Subtropical to tropical collections, spanning 20° of latitude (-11.4°S to -30.94°S)

• 54 host families

• 279 host species

library(tidyverse)
library(lubridate)
library(ggplot2)
library(plotly)

collections <- read.csv("https://raw.githubusercontent.com/symbiobase/symbioID/main/Symbiobase.csv") |>
  dplyr::select(sample_id, collection_date, location, site, longitude, latitude, host_family, host_genus, host_species) |> 
  mutate(latitude=round(latitude,3), longitude=round(longitude,3), collection_date=ymd(collection_date)) |> 
  mutate(location = gsub("_", " ", location),
         site = gsub("_", " ", site),
         host_genus = gsub("_", " ", host_genus),
         host_species = gsub("_", " ", host_species)) |> 
  # mutate(latitudinal_band = as.character(cut(latitude, breaks = seq(-34, -13, by = 1), include.lowest = TRUE))) %>%
  # mutate(latitudinal_band = gsub(",", " to ", latitudinal_band) %>%
  #                          gsub("\\]", ")", .) %>%
  #                          gsub("(-?\\d+)", "\\1°S", .)) %>%
  # filter(!host_species %in% c("sp1", "sp2")) %>%
  # mutate(host_family = factor(host_family, levels = sort(unique(host_family), decreasing = TRUE))) 
  # drop_na(lat) %>%
  mutate(latitude_groups = cut(latitude, breaks = seq(-34, -13, by = 1), include.lowest = TRUE)) %>%
  filter(!latitude_groups=="NA") |> 
  mutate(latitude_groups = gsub(",", " to ", latitude_groups) %>%
                           gsub("\\]", ")", .) %>%
                           gsub("(-?\\d+)", "\\1°S", .)) 
  
p <- ggplot() + theme_bw() +
  geom_histogram(data=collections |> drop_na(latitude_groups), aes(y=latitude_groups, fill=latitude_groups), 
                 show.legend=FALSE, stat="count", color="black", linewidth=0.2) +
  guides(fill=FALSE) + ylab(FALSE) +
  theme(axis.text.y = element_text(size=9)) + xlab("Number of samples") +
  scale_x_continuous(sec.axis = dup_axis(name = "Secondary X Axis")) +
  scale_fill_brewer(palette="RdBu") + ylab("Latitude")


p_plotly <- ggplotly(p, tooltip = c("latitude_groups", "count"))

layout(p_plotly,
        xaxis2 = list(overlaying = "x",
                      side = "bottom",
                      title = "Number of samples"))