# INBO CODING CLUB

25 February 2021

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 |
Dirk Maes | **
Lynn Pallemaerts | **
An Leyssen |
Amber Mertens |
Hans Van Calster | ***
Adriaan Seynaeve |
Luc De Bruyn |*
Anja Leyman |

## Challenge 1

Hans:

#' read a set of research grade observations from text file
#' `20210125_occurrence_iNaturalist_researchgrade_obs.txt`

inat <- read_tsv(file = "./data/20210225/20210125_occurrence_iNaturalist_researchgrade_obs.txt")

#' read data file  `20210225_gent_groeiperwijk.csv` containing the demographic evolution of Ghent districts from 1999 to 2009
# of here() gebruiken om  path te definiëren (install.packages("here"))
gent <- read_csv2(here::here("data", "20210225", "20210225_gent_groeiperwijk.csv"),
                  quote = "'")


#' read sheet `ALL DATA` from Excel datafile `20210225_manta_2014_2015.xlsx` with
#' manta related data.
#'

manta <- read_excel("data/20200121/20200121_manta_master_database_2014_2015.xlsx",
                    sheet = "ALL DATA",
                    skip = 1)


#' Read butterfly related data file `20210225_butterflies_counts.txt` with
#' semicolon (;) as delimiter, dot (.) as decimal mark and question mark (?) as
#' NA. Read only the first 500 rows. Be sure column `Date` is parsed as
#' datetime by using `format = "%d/%m/%Y %H:%M:%S"`.

butterfly <- read_delim("data/20210225/20210225_butterflies_counts.txt",
                        delim = ";",
                        locale = locale(decimal_mark = "."),
                        na = "?",
                        n_max = 500,
                        col_types = cols(Date = col_datetime(format = "%d/%m/%Y %H:%M:%S")))

#' How to examine the column specifications for the dataframes you have just read?

spec(butterfly)
spec(gent)
purrr::map(manta,class)

## Challenge 2

Lynn

hyacint <- read_sheet("https://docs.google.com/spreadsheets/d/1Tc8U-ud4dEcxgOojS80w7gdQQ-Ac85A4dN-u47NSmYg",
                      sheet='HyaHoVrBl',
                      na=c("NA","na","NaN"))
                      
sheets_get("https://docs.google.com/spreadsheets/d/1Tc8U-ud4dEcxgOojS80w7gdQQ-Ac85A4dN-u47NSmYg")
                      
hyacint_cov_link <- "https://docs.google.com/spreadsheets/d/e/2PACX-1vRFAWYrZmgBRPXQnw3Io5T_29ZrGkH-Ds4yulFd02MIPcalGPtzyQ3cujgAdwzfnRNYIWQFf1oKjgM3/pub?gid=1007047746&single=true&output=csv"

hyacint_offline <- read_csv(file = hyacint_cov_link,
                            na=c("NA","na"))

Hans:

#' 1. Read the sheet `HyaHoVrBl` from a googlesheet about [hyacint coverage in Ename](https://docs.google.com/spreadsheets/d/1Tc8U-ud4dEcxgOojS80w7gdQQ-Ac85A4dN-u47NSmYg)(https://docs.google.com/spreadsheets/d/1Tc8U-ud4dEcxgOojS80w7gdQQ-Ac85A4dN-u47NSmYg) paying attention to import all columns correctly

hyacinth <- read_sheet(ss= "1Tc8U-ud4dEcxgOojS80w7gdQQ-Ac85A4dN-u47NSmYg",
                       sheet = "HyaHoVrBl",
                       na = c('na', 'NA', 'NaN'))
hyacinth
#get rid of spaces in column names
library(janitor)
hyacinth <- hyacinth %>%
  clean_names()


#' 2. Get metadata of the googlesheet in 1

gs4_get(ss = "1Tc8U-ud4dEcxgOojS80w7gdQQ-Ac85A4dN-u47NSmYg")

#' 3. But what if you don't want to allow tidyverse API to get access to your INBO
#' Google account? Well, you can publish the sheet to the web as csv and then
#' import it via `read_delim()` or `read_csv()`. Note: This method is useful if you
#' don't have to import a lot of Googlesheets and they can be publicly available.
#' Read the csv generated in this way by using this link:
#'
hyacint_cov_link <- "https://docs.google.com/spreadsheets/d/e/2PACX-1vRFAWYrZmgBRPXQnw3Io5T_29ZrGkH-Ds4yulFd02MIPcalGPtzyQ3cujgAdwzfnRNYIWQFf1oKjgM3/pub?gid=1007047746&single=true&output=csv"

hyacinth_from_csv <- read_csv(hyacint_cov_link,
                              na = c('NA', 'na', 'NaN')) %>%
  clean_names()

## INTERMEZZO

## Challenge 3

Hans:

days_walloon <- c("londi", "mårdi", "mierkidi", "djudi", "vénrdi",
  "semdi", "dimegne")
months_walloon <- c("djanvî","fevrî", "måss", "avri", "may", "djun", "djulete",
                    "awousse","setimbre", "octôbe", "nôvimbe", "decimbe")
days_abbr_walloon <- c("lon", "mår", "mie", "dju", "vén", "sem", "dim")
months_abbr_walloon <- c("djan","fev", "mås", "avr", "may", "djun", "djul",
                         "awou","set", "oct", "nôv", "dec")


walloon <- read_csv(file = "data/20210225/20210225_rainfall_waterloo.csv",
                    skip = 6,
                    locale = locale(grouping_mark = "'", 
                                    date_names = date_names(
                                      mon = months_walloon,
                                      mon_ab = months_abbr_walloon,
                                      day = days_walloon,
                                      day_ab = days_abbr_walloon
                                    ), 
                                    date_format = "%a %d %B %Y"),
                    col_types = cols(`AV Quality Code` = col_number(),
                                     Hour  = col_number())
                    )
walloon

## Bonus challenge