# INBO CODING CLUB

25 May 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 |
Anja Leyman |***
Lynn Pallemaerts |***
Dirk Maes | **
Hans Van Calster | ***
Emma Cartuyvels |***
Patrik Oosterlynck |**
An Leyssen |**
Raïsa Carmen |***
Adriaan Seynaeve |
Pieterjan Verhelst | *
Jasmijn Hillaert | *
Amber Mertens |***
Jeroen Vanden Borre | **
Lucia Manzanares |
Matthieu Chastel |
Joost Vanoverbeke | ***
Els De Bie |***
Frank Huysentruyt | **
Suzanna Lettens |

## Challenge 1

Emma:

tabel1 <- left_join(coding_club_core_team, 
          bmk_team, 
          by = "name")

tabel2 <- right_join(bmk_team, 
                     coding_club_core_team,
                     by = "name")

tabel3 <- inner_join(coding_club_core_team, 
                     bmk_team, 
                     by = "name")

tabel4 <- inner_join(bmk_team, 
                    coding_club_core_team,
                    by = "name")

tabel5 <- full_join(coding_club_core_team, 
                    bmk_team, 
                    by = "name")

Raïsa:

coding_club_core_team %>%
  left_join(bmk_team, by = "name")

bmk_team %>%
  right_join(coding_club_core_team, by = "name")
  
coding_club_core_team %>%
  inner_join(bmk_team, by = "name")

#Invert order of the columns
bmk_team %>%
  inner_join(coding_club_core_team, by = "name")

coding_club_core_team %>%
  full_join(bmk_team, by = "name")

Joost:

# kan ook zonder expliciet 'by = "name"'

coding_club_core_team_orcid <-
  coding_club_core_team %>% 
  left_join(bmk_team)

coding_club_core_team_orcid <-
  bmk_team %>% 
  right_join(coding_club_core_team)

coding_club_core_team_orcid <-
  bmk_team %>% 
  inner_join(coding_club_core_team)

coding_club_core_team_orcid <-
  coding_club_core_team %>% 
  inner_join(bmk_team)

coding_club_core_team_orcid <-
  coding_club_core_team %>% 
  full_join(bmk_team)

## INTERMEZZO

In 5 of 1st challenge, we do not only add columns (_variables_), but also rows (_cases_). Why cannot we do it then by functions which combine rows?

try this?

union_all(coding_club_core_team, bmk_team)

or this?

union(coding_club_core_team, bmk_team)

or this?

bind_rows(coding_club_core_team, bmk_team)

## Challenge 2

Anja

# 1) Distributions from Belgium, Netherlands and Luxembourg should not overlap. How can you check it? There are several ways to do it, but try to use a data joining technique, which is likely the shortest and more readable way

str(distribution_BE)

# country_code
distr_all <- distribution_BE %>%
  full_join(distribution_LU) %>%
  full_join(distribution_NL)

nrow(distr_all) - nrow(distribution_BE) - nrow(distribution_LU) - nrow(distribution_NL)


# 2) Merge the three distribution_* dataframes into a data.frame called distribution

distribution <- rbind(distribution_BE, distribution_LU, distribution_NL)
nrow(distribution)


# 3) Check that all taxa in vernacularname point to taxa in taxon
vernacularname %>%
  left_join(taxon, by = c("taxon_id" = "taxonID")) %>%
  filter(is.na(scientificName)) %>%
  nrow()


# 4) Which taxa in taxon do not have vernacular names?
check <- taxon %>%
  left_join(vernacularname, by = c("taxonID" = "taxon_id")) %>%
  filter(is.na(vernacularName))

check$scientificName

# Dirk

distribution <- rbind(distribution_BE, distribution_LU, distribution_NL)
n1 <- nrow(distribution)

distribution <- distribution %>% 
	distinct()
n2 <- nrow(distribution)
n1 - n2

Emma:

intersect(distribution_BE, distribution_NL,
          distribution_LU) #this ignores one of the tables?

intersect(distribution_BE, distribution_NL)
intersect(distribution_BE, distribution_LU)
intersect(distribution_LU, distribution_NL)

distribution <- union(distribution_BE, distribution_NL) %>%
  union(distribution_LU)

vernacularname %>%
  anti_join(taxon, by = c("taxon_id" = "taxonID"))

taxon %>% 
  anti_join(vernacularname, by = c("taxonID" = "taxon_id"))

## Challenge 3

anja

# 1) 
extended_taxon <- taxon %>%
  full_join(vernacularname, by = c("taxonID" = "taxon_id"), suffix = c("_taxon", "_vernacular"))

names(extended_taxon)


# 2) Add distribution to extended_taxon and retain only the taxa found in Belgium, Netherlands or Luxembourg, i.e. only taxa in distribution

distr_taxon <- extended_taxon %>%
  right_join(distribution, by = c("taxonID" = "taxon_id"))


# 3) 
species_albania <- distribution_AL %>% distinct(taxon_id)
species_europe <- distribution %>% distinct(taxon_id)

albania <- setdiff(species_albania, species_europe, by = c("taxon_id"))

europe <- setdiff(species_europe, species_albania, by = c("taxon_id"))

head(distribution_AL)
head(distribution)

# 4) Which species are found both in Albania (taxon_AL) and in West-Europe?
alb_eur <- intersect(species_albania, species_europe, by = c("taxon_id"))

# 5) Help him to merge taxon_AL, distribution_AL and vernacularname_AL to taxon, distribution and vernacularname respecitvely

taxon2 <-  union(taxon, taxon_AL)

distribution2 <-  union(distribution, distribution_AL)

vernacularname2 <-  union(vernacularname, vernacularname_AL)

Emma:

#1,2
extended_taxon <- taxon %>% 
  left_join(vernacularname,
            by = c("taxonID" = "taxon_id"),
            suffix = c("_taxon", "_vernacular")) %>% 
  right_join(distribution,
             by = c("taxonID" = "taxon_id"),
             suffix = c("_taxon", "_distribution"))

#3
distribution_AL %>% 
  anti_join(extended_taxon, by = c("taxon_id" = "taxonID"))

extended_taxon %>% 
  anti_join(distribution_AL, by = c("taxonID" = "taxon_id"))

#4
extended_taxon %>% 
  inner_join(distribution_AL, by = c("taxonID" = "taxon_id"))

#5
union(taxon, taxon_AL)
union(distribution, distribution_AL)
union(vernacularname, vernacularname_AL)

## Nice to know

How to get ORCID ID of somebody via R directly? Dirk found this:

library(rorcid)
hvc <- orcid(query = "hans van calster")
hvc