# INBO CODING CLUB

29 February 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 | ***
Anja Leyman |
Emma Cartuyvels |**
Dirk Maes | **
Margot Vanhellemont | **
Pieter Huybrechts| **
Rhea Maesele | *
Nele Mullens | **
Jolien Van Malderen |**
Charlie Plasman | **
Heleen Deroo | *
Tina Tuerlings |
Adriaan Seynaeve | **
Ward Standaert | **
Leen Govaere |

## Challenge 1

### Damiano's solution (example)

Copy paste this section to show your solutions.

# dummy code
print("This is how to insert code.")
cat("ᓚᘏᗢ")

### Emma's solution

rodentia %>% 
  filter(year > 1999) %>% 
  ggplot(aes(x = year)) +
  stat_bin(binwidth = 5, fill = "blue", color = "red") +
  labs(x = "Year",
       y = "Number of observations",
       title = "Evolution of rodents in Belgium")

### Pieter's solution

# install ggthemes for more ggplot themes
if(!require("ggthemes", quietly = TRUE)){install.packages("ggthemes")}

# You could also parse eventDate, but year is provided :)
dplyr::filter(rodentia, year >= 2000) %>%
  ggplot() +
  aes(x = year) +
  geom_histogram(bins = 5L, fill = "powderblue", color = "plum2") +
  labs(x = "Year",
       y = "Number of observations",
       title = "Evolution of rodents in Belgium",) +
  ggthemes::theme_economist_white()

### Tina's solution

rodentia2000<-rodentia[rodentia$year>="2000",]

ggplot(data=rodentia2000,aes(x=year))+
  geom_bar(fill='blue',col="red")+
  labs(x="Year",y="number of observations",
       title="Evolution of rodents in Belgium")+
  scale_x_binned(n.breaks=5)

### Nele's solution
👍

# 1.1 Make a bar chart with the number of observations of rodents in Belgium per 
# year. Tip: check the difference between geom_bar() and geom_col(), e.g. via 
# help ?geom_bar.
ggplot(data=rodentia,
       mapping=aes(x=year))+ #y = indivindualCount
  geom_bar()

# 1.2 Change x and y labels to "Year" and "number of observations" respectively.
ggplot(data=rodentia,
       mapping=aes(x=year))+
  labs(x = "Year", y = "Number of observations")+
  geom_bar()

# 1.3 Add the title "Evolution of rodents in Belgium" to the plot.
ggplot(data=rodentia,
       mapping=aes(x=year))+
  labs(x = "Year", 
       y = "Number of observations",
       title = "Evolution of rodents in Belgium")+
  geom_bar()

# 1.4 Show only data from 2000.
#filter out lower years
filter(rodentia, year >= 2000) %>% 
ggplot(mapping=aes(x=year))+
  labs(x = "Year", 
       y = "Number of observations",
       title = "Evolution of rodents in Belgium")+
  geom_bar()

# 1.5 Fill all bars with color blue and set contour color to red.
filter(rodentia, year >= 2000) %>% ggplot(mapping=aes(x=year))+
  labs(x = "Year", 
       y = "Number of observations",
       title = "Evolution of rodents in Belgium")+
  geom_bar(color = "red", fill = "blue")

# 1.6 Sometimes, it is adviced to bin data to deal better with outliers and 
# show trends. In this case, group years in bins of 5 years.

filter(rodentia, year >= 2000) %>% ggplot(mapping=aes(x=year))+
  labs(x = "Year", 
       y = "Number of observations",
       title = "Evolution of rodents in Belgium")+
  stat_bin(binwidth = 5, color = "red", fill = "blue")

### Charlie's solution
👍

# Make a bar chart with the number of observations of rodents in Belgium per year.
# Change x and y labels to "Year" and "number of observations" respectively.
# Add the title "Evolution of rodents in Belgium" to the plot.
rodentia |> 
  filter(year > 1999) |> 
  ggplot(mapping = aes(x = year)) +
  geom_bar() +
  labs(title = "Evolution of rodents in Belgium", x = "Year", y = "Number of observations")
# Show only data from 2000.
# Fill all bars with color blue and set contour color to red.
# Bin data to deal better with outliers and show trends. In this case, group years in bins of 5 years.
rodentia |> 
  filter(year == 2000) |> 
  ggplot(mapping = aes(x = month)) +
  stat_bin(binwidth = 5, fill = "blue", color = "red") +
  labs(title = "Evolution of rodents in Belgium", x = "Year", y = "Number of observations") 

### Ward's solution
👍

ggplot(data = rodentia %>% filter(year >= 2000), aes(x = year)) +
  stat_bin(binwidth = 5, fill = "blue", color = "red") +
  labs(x = "Year") +
  labs(y = "number of observations") +
  ggtitle("Evolution of rodents in Belgium")

## Challenge 2

### Emma's solution
👍

## Challenge 2A
rodentia %>% 
  filter(year > 1999) %>% 
  ggplot(aes(x = year)) +
  stat_bin(binwidth = 5, position = "dodge") +
  labs(x = "Year",
       y = "Number of observations",
       title = "Evolution of rodents in Belgium") +
  facet_wrap(~ genus, scales = "free")


## Challenge 2B
rodentia_selection_n %>% 
  ggplot(aes(x = year, y = n, color = species)) +
  geom_point() +
  geom_line()

rodentia_selection_n %>% 
  ggplot(aes(x = year, y = n, color = species)) +
  geom_point() +
  geom_smooth(method = "gam")

### Pieter's Solution

## 2A -----------------------------------------------------------
filter(rodentia, year >= 2015) |>
  ggplot(mapping = aes(x = year, fill = genus)) +
  geom_bar(position = position_dodge2(preserve = "single"))

# different option with colours
count(rodentia, genus, year) |>
  ggplot() +
  aes(x = genus, y = n, fill = year) +
  geom_col(position = "stack") +
  scale_fill_viridis_c(option = "inferno", direction = 1) +
  theme_classic()

### Faceting
#### x is genus, subplot per year
dplyr::filter(rodentia, year >= 2009) |>
  ggplot() +
  aes(x = genus, fill = family) +
  geom_bar() +
  scale_fill_hue(direction = 1) +
  facet_wrap(vars(year), scales = "free_x") +
  theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))

#### subplot per family, x is year
filter(rodentia, year > 1999) |>
  ggplot(mapping = aes(x = year)) +
  geom_histogram(bins = 5L, fill = "wheat3") +
  facet_wrap(vars(family), scales = "free_x")
  
## 2B -----------------------------------------------------------

rodentia_selection <- rodentia %>%
  dplyr::filter(species %in% c("Ondatra zibethicus",
                               "Rattus norvegicus"))

rodentia_selection_n <- rodentia_selection %>%
  group_by(species,year) %>%
  count()

ggplot(rodentia_selection_n,
       mapping = aes(y = n,
                     x = year,
                     colour = species)) +
  geom_point() +
  geom_smooth(method = "gam")

### Charlie's solution

## Challenge 2A

# Make a bar chart plot similar to the ones in challenge 1.1 at genus level. 
rodentia |> 
  filter(year > 2000) |> 
  ggplot(mapping = aes(x = year, fill = genus, color = genus)) +
  geom_bar(position = "fill") +
  labs(title = "Evolution of rodents in Belgium", x = "Year", y = "Number of observations")
# How to split the bar chart in subplots based on family? Set x scale "free".
rodentia |> 
  filter(year > 2000) |> 
  ggplot(mapping = aes(x = year, fill = genus, color = genus)) +
  geom_bar(position = "fill") +
  labs(title = "Evolution of rodents in Belgium", x = "Genus", y = "Number of observations") +
  facet_wrap(~family)
  
## Challenge 2B

ggplot(data = rodentia_selection_n, 
       mapping = aes(x = year,y = n, color = species)) + 
  geom_line() +
  geom_smooth() +
  labs(title = "Evolution of 2 rodents sp. in Belgium", x = "Year", y = "Number of observations", color = "Rodent species") 

### Nele's solution
👍

# 2A.1 Make a bar chart plot similar to the ones in challenge 1.1 at genus level. 
# How are the bars displayed per genus, by default?

ggplot(data=rodentia,
       mapping=aes(x = year, fill = genus))+
  labs(x = "Genera", y = "Number of observations")+
  stat_bin(binwidth = 5, color = "black")

# 2A.2 Try other ways to "adjust" the bars. Tip: check the position adjustment 
# section section in ggplot2 reference website.

ggplot(data=rodentia,
       mapping=aes(x = year, fill = genus))+
  labs(x = "Genera", y = "Number of observations")+
  geom_bar(position = "jitter", color = "black")
  
# 2A.3 How to split the bar chart in subplots based on family? Set x scale "free".

ggplot(data=rodentia,
       mapping=aes(x = year, fill = genus))+
  labs(x = "Genera", y = "Number of observations")+
  stat_bin(binwidth = 5, color = "black") +
  facet_grid(cols = vars(family))
  
  # 2B.1 Create a plot showing the number of observations of Ondatra zibeticus and 
# Rattus norvegicus. Use both points and lines and distinguish the two species 
# via color.

ggplot(rodentia_selection_n,
       mapping=aes(x = year, y = n, color = species))+ #y = species,
  labs(x = "Years", y = "Number of observations")+
  geom_line()

# 2B.2 Typically, points are combined with a line showing the trend, calculated 
# via a smoother function. ggplot helps us enormously to model and smooth our 
# data. Try different smoother methods.

ggplot(rodentia_selection_n,
       mapping=aes(x = year, y = n, color = species))+ #y = species,
  labs(x = "Years", y = "Number of observations")+
  geom_point() + 
  geom_line() +
  geom_smooth()
  

### Dirk's solution
👍

p <- ggplot(rodentia,
            aes(x = year,
                group = genus,
                fill = genus)) +
  geom_bar(position = position_dodge2(preserve = "single")) + # to keep all bars in the same width
  xlab("Year") +
  ylab("number of observations") +
  ggtitle("Evolution of rodents in Belgium") +
  xlim(2000,2021) +
  theme_bw() +
  facet_wrap(~ family,
             scales = "free")
p

## Challenge 3

### Tina's solution

## showing the distribution of the observed species per year
library(viridis)
library(ggridges)

ggplot( rodentia, aes(x=month, y=species,col=family)) +
  geom_boxplot() +
  scale_fill_viridis(discrete = TRUE, alpha=0.6)

ggplot(rodentia, aes(x = month, y =species, fill = family)) +
  geom_density_ridges() +
  theme_ridges() + 
  theme(legend.position = "none")


##pie charts

# Create a new column to categorize genera
rodentia$genus_category <- ifelse(rodentia$genus %in% c("Rattus", "Ondatra"), rodentia$genus, "other")

# Plot the pie chart
ggplot(rodentia, aes(x = "", fill = genus_category)) +
  geom_bar(width = 1, stat = "count") +
  coord_polar("y", start = 0) +
  theme_void()