# INBO CODING CLUB

26 September 2023

Welcome!

## Share your code snippet

If you want to share your code snippet, copy paste your snippet within a section of three backticks (```):

As an **example**:

library(tidyverse)

(*you can copy paste this example and add your code further down*)

## Yellow sticky notes

No yellow sticky notes online. Put your name + " | " and add a "*" each time you solve a challenge (see below).

## Participants

Name | Challenges
--- | ---
Damiano Oldoni |
Pieter Huybrechts | **
Adriaan Seynaeve |
Anja Leyman | **
Nele Mullens | *
Margot Vanhellemont | **

## Challenge 1

### Pieter's solution

# 1.1 ---------------------------------------------------------------------



get_obs_2010 <- function(species) {
  assertthat::assert_that(assertthat::is.string(species))

  ## read observations -------------------------------------------------------

  # STEP 1: read observations
  species_formatted <-
    stringr::str_replace_all(
      tolower(species),
      pattern = " ",
      replacement = "_"
    )
  ## compose filename
  file_name <- paste0("20230926_", species_formatted, "_2010", ".txt")
  ## read file
  ha_2010_raw <- readr::read_tsv(file.path("data", "20230926", file_name),
    show_col_types = FALSE
  )


  return(ha_2010_raw)
}

# 1.2 ---------------------------------------------------------------------


get_obs <- function(species, year) {
  assertthat::assert_that(assertthat::is.string(species))
  assertthat::assert_that(assertthat::is.count(year))

  ## read observations -------------------------------------------------------

  # STEP 1: read observations
  species_formatted <-
    stringr::str_replace_all(
      tolower(species),
      pattern = " ",
      replacement = "_"
    )
  ## compose filename
  file_name <- paste0("20230926_", species_formatted, "_", year, ".txt")
  ## read file
  ha_raw <- readr::read_tsv(file.path("data", "20230926", file_name),
    show_col_types = FALSE
  )
  
  return(ha_raw)
}

### Nele's solution

species_input <- "Harmonia axyridis"

get_obs_2010 <- function(species){
  species <- tolower(species)
  species <- str_replace_all(
    species,
    pattern = " ",
    replacement = "_"
  )
  file_name <- paste0("20230926_", species, "_2010", ".txt")
  ha_2010 <- read_tsv(paste0("./data/", file_name), show_col_types = FALSE)
  return(as.data.frame(ha_2010))
}

output_2010 <- get_obs_2010(species_input)
output_2010

get_obs <- function(species, year){
  species <- tolower(species)
  species <- str_replace_all(
    species,
    pattern = " ",
    replacement = "_"
  )
  file_name <- paste0("20230926_", species, "_", year, ".txt")
  datafile <- read_tsv(paste0("./data/", file_name), show_col_types = FALSE)
  return(as.data.frame(datafile))
}

input_sp <- "Harmonia axyridis"
input_yr <- "2010"
obs_2010_Ha <- get_obs(input_sp, input_yr)
obs_2010_Ha

## Challenge 2

### Pieter's solution

# 2A ----------------------------------------------------------------------


clean_data <-
  function(df,
           max_coord_uncertain = 1000,
           issues_to_discard = c(
             "ZERO_COORDINATE",
             "COORDINATE_OUT_OF_RANGE",
             "COORDINATE_INVALID",
             "COUNTRY_COORDINATE_MISMATCH"
           ),
           occurrenceStatus_to_discard = c(
             "absent",
             "excluded"
           )) {
    #' Clean Data from inventory
    #'
    #' @param df data.frame. In the shape i expect and should describe here.
    #' @param max_coord_uncertain Numeric. Max coordinate uncertainty in meters to filter on.
    #' @param issues_to_discard Character vector. What GBIF issues should be discarded? List of allowed values via `rgbif::gbif_issues()$issue`.
    #' @param occurrenceStatus_to_discard Character vector. What occurrenceStatuses should be discarded?
    #'
    #' @return A cleaned dataframe.
    #'
    #' @examples
    #' get_obs("Harmonia axyridis", year = 2010) |> clean_data()

    ## make sure our input variables are as we expect --------------------------

    # only allow our input variables to be of certain classes
    assertthat::assert_that(is.data.frame(df))
    assertthat::assert_that(assertthat::is.count(max_coord_uncertain))
    assertthat::assert_that(is.character(issues_to_discard))
    assertthat::assert_that(is.character(occurrenceStatus_to_discard))
    # only allow certain values, which we get from a different package
    assertthat::assert_that(all(issues_to_discard %in% rgbif::gbif_issues()$issue),
      msg = "`issues_to_discard` should be one of the issues from `rgbif::gbif_issues()$issue`"
    )

    ## clean the input dataframe -----------------------------------------------
    cleaned_df <-
      df |>
      dplyr::filter(
        coordinateUncertaintyInMeters < max_coord_uncertain |
          is.na(coordinateUncertaintyInMeters)
      ) |>
      dplyr::filter(!issue %in% issues_to_discard) |>
      dplyr::filter(!occurrenceStatus %in% occurrenceStatus_to_discard)

    return(cleaned_df)
  }

calc_grid_cell <- function(df,
                           lon_size_degrees = 0.1,
                           lat_size_degrees = 0.05) {
  # make sure the input dataframe is a dataframe, and has the right columns
  assertthat::assert_that(is.data.frame(df))
  assertthat::assert_that("decimalLongitude" %in% colnames(df))
  assertthat::assert_that("decimalLatitude" %in% colnames(df))
  # add a column with the cell_size
  df_with_cell_size <-
    df |>
    dplyr::mutate(cell_code = paste0(
      "01x005",
      "E", floor(decimalLongitude / lon_size_degrees),
      "N", floor(decimalLatitude / lat_size_degrees)
    ))
  return(df_with_cell_size)
}




# 2B ----------------------------------------------------------------------

calc_n_obs_ind <- function(df) {
  df |>
    dplyr::group_by(cell_code) |>
              # number of observations (rows)
    dplyr::summarise(n_observations = dplyr::n(),
              # number of individuals
              n_individuals = sum(individualCount))
}

plot_distr_cells <- function(df, binwidth = 5) {
  p <- ggplot2::ggplot(df) +
    ggplot2::geom_histogram(ggplot2::aes(x = n, fill = indicator),
                   position = "dodge",
                   binwidth = binwidth) +
    ggplot2::xlab(glue::glue("n (binwidth: {binwidth})")) +
    ggplot2::ggtitle(label = "Grid cells distribution")
  return(p)
}

## INTERMEZZO

## Challenge 3

## Bonus challenge

There is no bonus challange!