# INBO CODING CLUB

27 June 2024

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 | ***
Nele Mullens | **
Ward Standaert | **
Rhea Maesele | *
Dirk Maes |
Dirk Festraets |
Jo-Hannes Nowé |**
Heleen Deroo |
Sanne Govaert | **
Siebe Indestege | **
Anja Leyman | *
Soria Delva | *
Tina Tuerlings | ***
Katrijn Alaerts | **
Lotte Pohl | *
Lucia Manzanares | *

## Challenge 1

### Damiano's solution (example)

Copy paste this section to show your solutions.

# dummy code
a <- 1
print("This is how to insert text which looks like code.")

### Heleen's solution

map(swiss, mean)

map(iris, class)

list_with_dfs <- list(swiss = swiss, iris = iris)
map(list_with_dfs, nrow)

map_dbl(swiss, mean)
map_chr(iris, class)
map_dbl(list_with_dfs, nrow)

map_df(swiss, mean)
map_df(iris, class)
map_df(list_with_dfs, nrow)

### Nele's solution

#1.1 Compute the mean of every column in the swiss data.frame.

#swiss is a basic package in R base, just like iris

map(swiss, mean)


#1.2 Determine the type of each column in the iris data.frame.

map(iris, class)


#1.3 After creating the variable list_with_dfs as a named list with swiss and 
# iris (code provided), compute the number of rows of each data.frame.

list_with_dfs <- list(iris = iris, swiss = swiss) #list with dataframes

map(list_with_dfs, nrow)


#1.4 map() ALWAYS returns a list, ALWAYS. Apply the right map_*() variants to 
# the previous exercises to return a numeric vector (exercises 1 and 3), a 
# character vector (exercise 2) or a data.frame (exercises 1, 2 and 3). Hint: 
# use cheat sheet or the sections map-atomic and the-map-functions.

map_vec(swiss, mean)
map_vec(list_with_dfs, nrow)

map_chr(iris, class)

map_df(swiss, mean)
map_df(iris, class)
map_df(list_with_dfs, nrow)

### Jo-Hannes' solution

## CHALLENGE 1

#Write map() statements to:
#1.
map(swiss, mean)
#2. 
map(iris,typeof)

#3. 
list_with_dfs <- list(swiss = swiss, iris = iris)
map(list_with_dfs,nrow)

#4. 
map_dbl(swiss,mean)
map_dbl(list_with_dfs,nrow)

map_chr(iris,typeof)

map_df(swiss,mean)
map_df(iris,typeof)
map_df(list_with_dfs,nrow)

### Siebe's Solution

# 1.1

map(swiss, mean)

# 1.2

map(iris, class)

# 1.3

list_with_dfs <- list(swiss, iris)
names(list_with_dfs) <- c("swiss","iris")
map(list_with_dfs, nrow)

# 1.4

map_dbl(swiss, mean)
map_dbl(list_with_dfs, nrow)

map_chr(iris,class)

map_df(swiss, mean)
map_df(iris, class)
map_df(list_with_dfs, nrow)

## Challenge 2

### Sanne's solution

# 2.1
map(sensors, read_sensor_data)

# 2.2
sensor_dfs <- map(
  sensors,
  read_sensor_data,
  path_pattern = path_pattern_datafiles,
  extension = file_extension
  )

# 2.3
map2(means, st_dev, rnorm, n = 10) %>% str()

# 2.4 
datetimes <- function(sensor_df) {
  summarize(
    sensor_df,
    min_datetime = min(datetime),
    max_datetime = max(datetime)
    )
}
map_df(sensor_dfs, datetimes)

### Ward's solution

# 2.1

# Define the list with the sensor IDs
sensors <- list("A1", "G7", "H4")
names(sensors) <- sensors

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' read_sensor_data(sensor = "H4")
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0("./data/20240627/20240627_sensor_", sensor, ".txt")
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1")

sensor_list <- map(sensors, \(x) read_sensor_data(x))

# 2.2

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @param path_pattern character. The path common to all sensor files.
#' @param extension character. The file extension starting with `.`.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
#' file_extension <- ".txt"
#' read_sensor_data(sensor = "H4", path_pattern_datafiles, file_extension)
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0(path_pattern, sensor, extension)
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# If data files are where they should be, here the path_pattern and
# extension to use. Just copied from the @example above the function.
path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
file_extension <- ".txt"

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1",
                              path_pattern = path_pattern_datafiles,
                              extension = file_extension
)

map(sensors, read_sensor_data, 
        path_pattern = path_pattern_datafiles, 
        extension = file_extension)

# 2.3

# Define means and standard deviations
means <- c(-10, 0, 10, 20)
st_dev <- c(1, 3, 2, 1.5)

map2(means, st_dev, rnorm, n = 10)


# 2.4

max_min_fun <- \(x) summarize(x, min_datetime = min(datetime), max_datetime = max(datetime))
map_df(sensor_list, max_min_fun)

### Jo-Hannes' solution

# 2.1
# Define the list with the sensor IDs
sensors <- list("A1", "G7", "H4")
names(sensors) <- sensors

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' read_sensor_data(sensor = "H4")
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0("./data/20240627/20240627_sensor_", sensor, ".txt")
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1")

sensor_data <- map(sensors,read_sensor_data)


# 2.2 Now, you want to generalize your script 

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @param path_pattern character. The path common to all sensor files.
#' @param extension character. The file extension starting with `.`.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
#' file_extension <- ".txt"
#' read_sensor_data(sensor = "H4", path_pattern_datafiles, file_extension)
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0(path_pattern, sensor, extension)
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# If data files are where they should be, here the path_pattern and
# extension to use. Just copied from the @example above the function.
path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
file_extension <- ".txt"

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1",
                              path_pattern = path_pattern_datafiles,
                              extension = file_extension
)

sensor_data <- map(sensors, \(x) read_sensor_data(x,path_pattern= path_pattern_datafiles,
                                                  extension=file_extension))


# 2.3 
# Define means and standard deviations
means <- c(-10, 0, 10, 20)
st_dev <- c(1, 3, 2, 1.5)

#for one example
rnorm(n=10, mean = -10, sd=1)

#map to all elements
map2(means,st_dev, \(x,y) rnorm(n=10,mean=x,sd=y))

# 2.4 
#sensor_data is a list of the sensor data.frames

#Try it for one example
summarize(sensor_data[[1]], min_datetime = min(datetime), max_datetime = max(datetime))

#map it to all elements of the list (so each dataframe)
map(sensor_data, \(x) summarize(x, min_datetime = min(datetime), max_datetime = max(datetime)))



# 2.3

# Define means and standard deviations
means <- c(-10, 0, 10, 20)
st_dev <- c(1, 3, 2, 1.5)

#for one example
rnorm(n=10, mean = -10, sd=1)

#map to all elements
map2(means,st_dev, \(x,y) rnorm(n=10,mean=x,sd=y))

# 2.4

#sensor_data is a list of the sensor data.frames

#Try it for one example
summarize(sensor_data[[1]], min_datetime = min(datetime), max_datetime = max(datetime))

#map it to all elements of the list (so each dataframe)
map(sensor_data, \(x) summarize(x, min_datetime = min(datetime), max_datetime = max(datetime)))

### Nele's solution

# 2.1 

# Define the list with the sensor IDs
sensors <- list("A1", "G7", "H4")
names(sensors) <- sensors

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' read_sensor_data(sensor = "H4")
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0("./data/20240627/20240627_sensor_", sensor, ".txt")
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1")

all_sensors <- map(sensors, read_sensor_data)


# 2.2

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @param path_pattern character. The path common to all sensor files.
#' @param extension character. The file extension starting with `.`.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
#' file_extension <- ".txt"
#' read_sensor_data(sensor = "H4", path_pattern_datafiles, file_extension)
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0(path_pattern, sensor, extension)
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# If data files are where they should be, here the path_pattern and
# extension to use. Just copied from the @example above the function.
path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
file_extension <- ".txt"

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1",
                              path_pattern = path_pattern_datafiles,
                              extension = file_extension
)

map(sensors, read_sensor_data, path_pattern_datafiles, file_extension)
# er zijn drie argumenten in de functie, de eerste vult ze vanzelf in, de tweede 
# en derde niet, deze moeten na de functie (hier read_sensor_data) zelf nog in-
# gevuld worden


# 2.3 Calculate 10 random numbers from a normal distribution (rnorm(n = 10)) for
# each pair of the 4 provided means and standard deviations and return it as a list of 4

# Define means and standard deviations
means <- c(-10, 0, 10, 20)
st_dev <- c(1, 3, 2, 1.5)

map2(means, st_dev, function(x, y) rnorm(n = 10, mean = x, sd = y))

# 2.4 

# get sensor data ready
sensor_data <- map(sensors, read_sensor_data, path_pattern_datafiles, file_extension)

# we need to get a function to do what we want
function(x) summarize(x, min_datetime = min(datetime), max_datetime = max(datetime))


# apply the function, output a dataframe
min_max_time <- map_df(sensor_data, function(x) summarize(x, min_datetime = min(datetime), max_datetime = max(datetime)))

# but I want to see what dates are from what sensor. Add names:

min_max_time <- map2_df(sensor_data, sensors, function(x, sensors) summarize(x, sensor = sensors, min_datetime = min(datetime), max_datetime = max(datetime)))

### Pieter's solution

# 2.1

# Define the list with the sensor IDs
sensors <- list("A1", "G7", "H4")
names(sensors) <- sensors

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' read_sensor_data(sensor = "H4")
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0("./data/20240627/20240627_sensor_", sensor, ".txt")
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1")

### 2.1
map(sensors, read_sensor_data)


# 2.2

#' Function to read a comma separated sensor data file.
#'
#' @param sensor character. A sensor ID.
#' @param path_pattern character. The path common to all sensor files.
#' @param extension character. The file extension starting with `.`.
#' @return A tibble data.frame as returned by `readr::read_csv()`.
#' @examples
#' # example code
#' library(readr)
#' path_pattern_datafiles <- "./data/20240627/20240627_sensor_"
#' file_extension <- ".txt"
#' read_sensor_data(sensor = "H4", path_pattern_datafiles, file_extension)
read_sensor_data <- function(
    sensor,
    path_pattern,
    extension) {
  path <- paste0(path_pattern, sensor, extension)
  readr::read_csv(path,
                  na = "NA",
                  col_types = cols(
                    datetime = col_datetime(format = "%d/%m/%Y %H:%M:%S")
                  )
  )
}

# If data files are where they should be, here the path_pattern and
# extension to use. Just copied from the @example above the function.
path_pattern_datafiles <- "./data/20200630/20200630_sensor_"
file_extension <- ".txt"

# Apply function to one sensor ID as check.
sensor_df <- read_sensor_data(sensor = "A1",
                              path_pattern = path_pattern_datafiles,
                              extension = file_extension
)

all_sensor_dfs <- map(
  sensors,
  ~ read_sensor_data(.x,
    path_pattern = "./data/20240627/20240627_sensor_",
    extension = ".txt"
  )
)

map(
  sensors,
  read_sensor_data,
  path_pattern = "./data/20240627/20240627_sensor_",
  extension = ".txt"
)

# 2.3

# Define means and standard deviations
means <- c(-10, 0, 10, 20)
st_dev <- c(1, 3, 2, 1.5)

map2(means,
     st_dev,
     \(mean_to_calc, sd_to_calc) rnorm(n = 10,
                                       mean = mean_to_calc,
                                       sd = sd_to_calc)
     )

# 2.4

get_min_max_dtime <- function(df) {
  summarize(df, min_datetime = min(datetime), max_datetime = max(datetime)) |>
    ungroup()
}

all_sensor_dfs |>
  map(get_min_max_dtime)

## Challenge 3

### Sanne's solution

# 3.1
lepidoptera_in_prot_areas <- readRDS("./data/20240627/20240627_lepidoptera_in_prot_areas.RData")
map(lepidoptera_in_prot_areas, length) %>% str()

# 3.2
obs <- readr::read_tsv("./data/20240627/20240627_lepidoptera_2024.tsv", na = "")
slice(obs, unlist(lepidoptera_in_prot_areas))

 3.3

# Species data.frames
species_1 <- tibble(
  species = c("Balanus tintinnabulum",
              "Callinectes sapidus",
              "Mnemiopsis leidyi"),
  is_marine = c(TRUE, TRUE, TRUE)
)

species_2 <- tibble(
  species = c("Leuciscus aspius",
              "Rhithropanopeus harrisii",
              "Mnemiopsis leidyi"),
  genus = c("Leuciscus",
            "Rhithropanopeus",
            "Mnemiopsis leidyi")
)

species_3 <- tibble(
  species = c("Rhithropanopeus harrisii","Potamopyrgus antipodarum"),
  informal_group = c("mollusca", "mollusca")
)

reduce(list(species_1, species_2, species_3), full_join, by = "species")

### Tina's solution

#### CHALLENGE 3A####

# Load lepidoptera_in_prot_areas
lepidoptera_in_prot_areas <- readRDS("./data/20240627/20240627_lepidoptera_in_prot_areas.RData")
lepidoptera_in_prot_areas
#list with the (row numbers of the) lepidoptera observations taken in protected areas.


# It's a kind of "special" list, but still a list! So, you can apply all purrr
# functions to it.
class(lepidoptera_in_prot_areas)


# 3.1 how many observations for each protected area?

map_int(lepidoptera_in_prot_areas, length)

# 3.2 Given obs, the data.frame with the GBIF observations 
#(see the provided code), how to get a data.frame with only the observations 
#taken in protected areas?

obs <- readr::read_tsv("./data/20240627/20240627_lepidoptera_2024.tsv", na = "")
str(obs)

protected <- map_df(lepidoptera_in_prot_areas, ~slice(obs,.x))
slice(iris,c(1,3,6))

# 3.3 purrr is more than the map family. To join the data.frames species_1, 
#species_2 and species_3 (code provided) you could apply full_join() twice:

# Species data.frames
species_1 <- tibble(
  species = c("Balanus tintinnabulum",
              "Callinectes sapidus",
              "Mnemiopsis leidyi"),
  is_marine = c(TRUE, TRUE, TRUE)
)

species_2 <- tibble(
  species = c("Leuciscus aspius",
              "Rhithropanopeus harrisii",
              "Mnemiopsis leidyi"),
  genus = c("Leuciscus",
            "Rhithropanopeus",
            "Mnemiopsis leidyi")
)

species_3 <- tibble(
  species = c("Rhithropanopeus harrisii","Potamopyrgus antipodarum"),
  informal_group = c("mollusca", "mollusca")
)

full_join(species_1, species_2, by = "species") %>%
  full_join(species_3, by = "species")

reduce(list(species_1,species_2,species_3),full_join)


#### Challenge 3B####

# Height of 5 giraffes
height_giraffe <- runif(n = 6, min = 4.3, max = 5.7)
# Weight of 5 giraffes
weight_giraffe <- rnorm(n = 6, mean = 1192, sd = 300)
# GPS tracker ID
gps_tracker_giraffe <- c("A31", "E4T", "RT4", "YU7", "3G1", "ON9")
# Data.frame with weight, height and GPS tracker IDs.
df <- tibble::tibble(
  "weight" = weight_giraffe,
  "height" = height_giraffe,
  "gpsID" = gps_tracker_giraffe
)


# 3B.1 FOR EACH column OF df and class numeric, APPLY FUNCTION floor(). 
#Modify the columns.
df <- df %>%
  mutate(across(where(is.numeric), ~ map_dbl(., ~ floor(.))))

# 3B.2 FOR EACH column OF df ending with ight (height, weight), 
#APPLY FUNCTION floor(). Modify the columns. Same result of exercise 1 expected.

df <- df %>%
  mutate(across(ends_with("ight"), ~ floor(.)))

# 3B.3 Instead of modifying the columns, how to add new ones?

df <- df %>%
  mutate(across(ends_with("ight"), list(floored=~ floor(.))))

### Pieter's solution

# 3.1

map_vec(lepidoptera_in_prot_areas, length)

# 3.2

obs <- readr::read_tsv("./data/20240627/20240627_lepidoptera_2024.tsv", na = "")
str(obs)
glimpse(obs)

map(lepidoptera_in_prot_areas, ~ slice(obs, .x))

# 3.3

# Species data.frames
species_1 <- tibble(
  species = c("Balanus tintinnabulum",
              "Callinectes sapidus",
              "Mnemiopsis leidyi"),
  is_marine = c(TRUE, TRUE, TRUE)
)

species_2 <- tibble(
  species = c("Leuciscus aspius",
              "Rhithropanopeus harrisii",
              "Mnemiopsis leidyi"),
  genus = c("Leuciscus",
            "Rhithropanopeus",
            "Mnemiopsis leidyi")
)

species_3 <- tibble(
  species = c("Rhithropanopeus harrisii","Potamopyrgus antipodarum"),
  informal_group = c("mollusca", "mollusca")
)

# Not DRY solution (hardcoded)
full_join(species_1, species_2, by = "species") %>%
  full_join(species_3, by = "species")


reduce(
  list(
    species_1,
    species_2,
    species_3
  ),
  ~ full_join(.x , .y, by = join_by(species))
)


## Challenge 3B

# Height of 5 giraffes
height_giraffe <- runif(n = 6, min = 4.3, max = 5.7)
# Weight of 5 giraffes
weight_giraffe <- rnorm(n = 6, mean = 1192, sd = 300)
# GPS tracker ID
gps_tracker_giraffe <- c("A31", "E4T", "RT4", "YU7", "3G1", "ON9")
# Data.frame with weight, height and GPS tracker IDs.
df <- tibble::tibble(
  "weight" = weight_giraffe,
  "height" = height_giraffe,
  "gpsID" = gps_tracker_giraffe
)


# 3B.1

mutate(df, across(where(is.numeric), floor))


# 3B.2

mutate(df, across(ends_with('ight'), floor))


# 3B.3

summarise(df, .by = where(is.numeric), across(everything()))

## Bonus Challange

### Pieter's solution

# BC.1
penguin_plot_tbl <-
  penguins %>%
  group_by(species) %>%
  nest() %>%
  mutate(plot = map(data, ~ ggplot(.x) +
                      geom_point(aes(
                        x = bill_length_mm,
                        y = bill_depth_mm,
                        colour = sex
                        )
                        ) + ggtitle(species)
                    )
         )



# BC.2

paths <- paste0(penguin_plot_tbl$species, ".png")
plots <- pull(penguin_plot_tbl, plot)

pwalk(list(paths, plots), ggsave, path = "./data/20240627")
`