Visualising herbivory and climate change literature

ggplot2 is a hugely powerful R package whuch enables the creation of high quality scientific charting and visualisation for communication.

This note walks through some basics for creating charts to illustrate the literature review but there are lots of resources for chart creation of which this course really showcases what is possible.

Load libraries and import data

Code

## load libraries

library(pacman)
pacman::p_load(tidyverse, readxl, here, skimr, overviewR, ggmap, gt, gtsummary, DataExplorer)       ## readxl is needed to load excel files into R
                                              ## the `here` package helps with file paths


path <- here::here("data")

xls <- list.files(path, "xls", full.names = TRUE)

data <- readxl::read_xlsx(xls[2])

New names:
• `Deer (cervine)` -> `Deer (cervine)...10`
• `Livestock (not stated)` -> `Livestock (not stated)...11`
• `Simulated grazing` -> `Simulated grazing...13`
• `Deer (cervine)` -> `Deer (cervine)...35`
• `Simulated grazing` -> `Simulated grazing...41`
• `Livestock (not stated)` -> `Livestock (not stated)...42`

Code

introduce(data)

# A tibble: 1 × 9
   rows columns discrete_columns conti…¹ all_m…² total…³ compl…⁴ total…⁵ memor…⁶
  <int>   <int>            <int>   <int>   <int>   <int>   <int>   <int>   <dbl>
1    45      99               82       0      17    1815       0    4455  176360
# … with abbreviated variable names ¹​continuous_columns, ²​all_missing_columns,
#   ³​total_missing_values, ⁴​complete_rows, ⁵​total_observations, ⁶​memory_usage

Basic template for plotting categorical variables

Select categorical variables

Code

## Select categorical variables
chr_vars <- select_if(data, is.character) |> 
  janitor::clean_names()          ## this function converts variable names to snake case which makes them much more consistent

glimpse(chr_vars) 

Rows: 45
Columns: 82
$ item                                                  <chr> "Abdalla (2009) …
$ title                                                 <chr> "Application of …
$ wildlife_trusts_relevance                             <chr> "-Yes", "-Yes", …
$ evidence_point                                        <chr> "-Evidence point…
$ herbivore_species_or_simulation_exposure              <chr> "Cows (bovines)"…
$ horses_equines                                        <chr> NA, NA, NA, NA, …
$ cows_bovines                                          <chr> "-Breed not stat…
$ sheep_ovines                                          <chr> NA, NA, NA, NA, …
$ livestock_not_stated_11                               <chr> NA, NA, NA, NA, …
$ simulated_grazing_13                                  <chr> NA, NA, NA, NA, …
$ mixed_herd_or_single_species_exposure                 <chr> "-Single species…
$ climate_effect_outcome                                <chr> "-Nitrous oxide"…
$ soil_carbon                                           <chr> NA, NA, "-No cha…
$ digestive_methane_emissions_production_or_live_weight <chr> NA, NA, NA, "-No…
$ digestive_methane_emissions_land_area                 <chr> NA, NA, NA, "-In…
$ digestive_methane_emissions_per_animal                <chr> NA, NA, NA, NA, …
$ methane_flux_emissions                                <chr> NA, NA, NA, "-No…
$ nitrous_oxide                                         <chr> "-Unclear", "-Un…
$ co2_flux_emissions                                    <chr> NA, NA, NA, "-De…
$ above_ground_biomass                                  <chr> NA, NA, NA, "-De…
$ total_ghg_emissions_co2_equiv                         <chr> NA, NA, NA, "-In…
$ root_biomass                                          <chr> NA, NA, "-Increa…
$ direction_of_climate_change_outcome                   <chr> "-Unclear or mul…
$ herbivore_species_or_other_comparator                 <chr> "-Not applicable…
$ sheep_ovine                                           <chr> NA, NA, NA, NA, …
$ cows_bovine                                           <chr> NA, NA, NA, "-Ho…
$ mowing                                                <chr> NA, NA, "-Mowing…
$ cutting                                               <chr> NA, NA, NA, NA, …
$ no_herbivore_or_simulation                            <chr> NA, NA, NA, NA, …
$ not_applicable                                        <chr> "-Not applicable…
$ simulated_grazing_41                                  <chr> NA, NA, NA, NA, …
$ livestock_not_stated_42                               <chr> NA, NA, NA, NA, …
$ mixed_herd_or_single_species_comparator               <chr> "-Not applicable…
$ herbivore_density_frequency_exposure                  <chr> "-Medium density…
$ herbivore_density_frequency_comparator                <chr> "-Not applicable…
$ continent_and_country                                 <chr> "-Europe", "-Eur…
$ australia_and_oceania                                 <chr> NA, NA, NA, NA, …
$ europe                                                <chr> "-Ireland", "-Ir…
$ north_america                                         <chr> NA, NA, NA, NA, …
$ latitude_n_s                                          <chr> "-Latitude (stat…
$ longitude_e_w                                         <chr> "-Longitude (sta…
$ elevation                                             <chr> "-Elevation (sta…
$ site_name                                             <chr> "-Site name (ple…
$ study_characteristics                                 <chr> NA, NA, NA, "-St…
$ soil_type                                             <chr> "-Sandy\r\n-Loam…
$ current_land_use                                      <chr> "-Livestock graz…
$ previous_land_use                                     <chr> "-Livestock graz…
$ vegetation_type                                       <chr> "-Dominant veget…
$ habitat_management_exposure                           <chr> "-Fertiliser app…
$ habitat_management_comparator                         <chr> "-Not applicable…
$ herbivory_season_exposure                             <chr> "-Summer\r\n-Aut…
$ herbivory_season_comparator                           <chr> "-Not applicable…
$ effect_on_plants_or_soil_exposure                     <chr> "-Grazing", "-Gr…
$ effect_on_plants_or_soil_comparator                   <chr> "-Not applicable…
$ herbivore_management_exposure                         <chr> "-Farmed for foo…
$ herbivore_management_comparator                       <chr> "-Not applicable…
$ supplementary_feeding_or_treatment_exposure           <chr> "-Not applicable…
$ supplementary_feeding_or_teatment_comparator          <chr> "-Not applicable…
$ forage_species_exposure                               <chr> "-Not applicable…
$ forage_species_comparator                             <chr> "-Not applicable…
$ other_comparator_differences_please_add               <chr> "-Not applicable…
$ introduced_status_exposure                            <chr> "-Farmed_domesti…
$ introduced_status_comparator                          <chr> "-Not applicable…
$ conservation_status                                   <chr> "-Not protected"…
$ modifiers                                             <chr> NA, NA, NA, "-Pr…
$ soil_temperature                                      <chr> "-Not stated", "…
$ air_temperature                                       <chr> "-Air Temperatur…
$ precipitation                                         <chr> "-Precipitation …
$ growing_season                                        <chr> "-Not stated", "…
$ permafrost_or_snow                                    <chr> "-Neither presen…
$ disturbance_events                                    <chr> "-None mentioned…
$ predators                                             <chr> "-None mentioned…
$ other_herbivores                                      <chr> "-None mentioned…
$ habitat_productivity                                  <chr> "-Not stated", "…
$ biome                                                 <chr> "-Temperate", "-…
$ lowland_or_upland_300m_exposure                       <chr> "-Not available"…
$ habitat_exposure                                      <chr> "-Improved grass…
$ acidity_exposure                                      <chr> "-Neutral", "-Ne…
$ lowland_or_upland_300m_comparator                     <chr> "-Not available"…
$ habitat_comparator                                    <chr> "-Improved grass…
$ acidity_comparator                                    <chr> "-Neutral", "-Ne…
$ comments                                              <chr> "Herbivore Speci…

Ordered bar charts (recommended)

We’ll use ggplot2 which is a hugely powerful and (hopefully) intuitive package for high quality production charting.

Lets plot climate_change_outcome

The first step is to count the frequency of each category within the variable:

Code

## the |> symbol is called a "pipe" . It says "do the instruction on the right hand side to the data on the left hand side. So... count categories in the variable climate_effect_outcome in the data set chr_vars

counts <- chr_vars  |>           
  count(climate_effect_outcome)

counts

# A tibble: 15 × 2
   climate_effect_outcome                                                      n
   <chr>                                                                   <int>
 1 "-CO2 flux_emissions"                                                       1
 2 "-CO2 flux_emissions\r\n-Soil carbon"                                       1
 3 "-Digestive methane emissions (Land Area)"                                  3
 4 "-Digestive methane emissions (per animal)"                                 1
 5 "-Digestive methane emissions (Production or Live Weight)"                  4
 6 "-Digestive methane emissions (Production or Live Weight)\r\n-Digestiv…     3
 7 "-Digestive methane emissions (Production or Live Weight)\r\n-Nitrous …     1
 8 "-Methane flux_emissions\r\n-Total GHG Emissions (CO2 equiv.)"              1
 9 "-Nitrous oxide"                                                           12
10 "-Nitrous oxide\r\n-CO2 flux_emissions\r\n-Methane flux_emissions"          6
11 "-Nitrous oxide\r\n-CO2 flux_emissions\r\n-Methane flux_emissions\r\n-…     3
12 "-Root biomass\r\n-Soil carbon"                                             1
13 "-Soil carbon"                                                              5
14 "-Soil carbon\r\n-Above ground biomass\r\n-Root biomass"                    2
15  <NA>                                                                       1

We can see there are 15 in the data.

We can now construct a bar (column) chart using gg plot

Code

counts |> 
  ggplot(aes(x = climate_effect_outcome, y = n)) +  ## we have to wrap x and y variables in aes()
  geom_col()                                        ## geom_col() plots bars 

It’s a bit of a mess…

Lets do 2 things:

1. Order the bars by size
2. Flip the chart from horizontal to vertical

Note that ggplot is built on the idea that charts are built in layers - axes, annotations, data, panels and plot areas and so on, and each layer we add needs a + sign -

In the code below we tell ggplot to add columns to represent the data on the chart by + geom_col()

That’s better but we can see a few issues:

1. Labels are ?duplicated and rather messy
2. The y axis label is redundant
3. The x axis needs to be integer and we need to label it correctly
4. We need to add titles etc
5. We should remove (or relabel) NAs.

Let’s tackle these.

Labelling or modifying axes labels, adding titles

This is controlled by labs()

Code

g <- counts |>
  ggplot(aes(reorder(climate_effect_outcome, n), n)) +      
  geom_col(fill = "blue") +                             ## (fill = ... controls the colour of the bars)
  labs(y = "No of studies", 
       x = NULL, 
       title = "Climate outcomes") +
  coord_flip()  

g

Lets move the title to the left, and reduce the font size of the y axis labels, and we’ll change the scale of the x-axis

Positions of titles, axes labels, font sizes and so on are controlled by theme()

Code

g <- g +
  theme(plot.title.position = "plot", 
        axis.text.x = element_text(size = .5))

g

Further modifications

The value labels still need tidying but that may best be done in the data. We can change the colour of the bars and the background.

Code

g +
  theme(panel.background = element_blank())      ## removes panel background

Putting it all together

Code

chr_vars |>              
  count(climate_effect_outcome) |>
  ggplot(aes(reorder(climate_effect_outcome, n), n)) +     
  geom_col(fill = "blue") +
  labs(y = "No of studies", 
       x = NULL, 
       title = "Climate outcomes") +
  ylim(c(0, 14)) +
  coord_flip() +
  theme(plot.title.position = "plot", 
        axis.text.y = element_text(size = 7), 
        panel.background = element_blank())

Making it generic - writing a function

Now we have a basic template, it would be useful to reuse this for other variables.

To do this we can write a function - like a macro - which in R is very easy - just need to wrap our code in function() and identify the input we want to change - which in this case is other variables. Lets call the function plot_ordered_bar_chart. The core looks like this…

Code

plot_ordered_bar_chart <- function(df, var){
  df = df
  var <- enquo(var)
  df |> 
    count(!!var) |>
  ggplot(aes(reorder(!!var, n), n)) +     
  geom_col(fill = "blue") +
  labs(y = "No of studies", 
       x = NULL, 
       title = var) +
  ylim(c(0, 14)) +
  coord_flip() +
  theme(plot.title.position = "plot", 
        axis.text.y = element_text(size = 7), 
        panel.background = element_blank())
  
}



plot_ordered_bar_chart(chr_vars, var= climate_effect_outcome)

Code

variables <- colnames(chr_vars)

plot_ordered_bar_chart(chr_vars, horses_equines)

Pie chart (not recommended

Pie charts are unexpectedly hard to to create in R - there is no geom in ggplot for example

Code

counts |>
  ggplot(aes(x="", y=n, fill=climate_effect_outcome)) +
  geom_bar(stat="identity", width=1) +
  coord_polar("y", start=0)    

Small multiples

We might want to compare frequencies across multiple variables, for example

Code

## lets create a frequency table of the number of breeds mentioned in studes for each herbivore group

grouped <- data |>
  select(contains("vine")) |>
  pivot_longer(names_to = "herbivore", values_to = "breed", cols = 1:6) |>
  group_by(herbivore) |>
  count(breed)

grouped

# A tibble: 32 × 3
# Groups:   herbivore [6]
   herbivore      breed                             n
   <chr>          <chr>                         <int>
 1 Cows (bovine)  "-Aberdeen Angus"                 1
 2 Cows (bovine)  "-Aberdeen Angus X Limousin"      2
 3 Cows (bovine)  "-Breed not stated"               6
 4 Cows (bovine)  "-Charolais"                      1
 5 Cows (bovine)  "-Holstein Fresian"               8
 6 Cows (bovine)  "-Limousin X"                     4
 7 Cows (bovine)  "-Limousin X\r\n-Welsh Black"     1
 8 Cows (bovine)   <NA>                            22
 9 Cows (bovines) "-Aberdeen Angus"                 1
10 Cows (bovines) "-Belted Galloway"                1
# … with 22 more rows
# ℹ Use `print(n = ...)` to see more rows

Code

grouped |>
  drop_na() |>
  ggplot(aes(herbivore, n, fill = breed)) +
  geom_col(position = "fill") +
  scale_y_continuous(labels = scales::percent_format())

Code

#| label: faceted (small multiples)

grouped |>
  drop_na() |>
  ggplot(aes(reorder(breed, n), n)) +
  geom_col(position = "dodge") +
  coord_flip() +
  labs(x = "", 
       y = "No of studies") +
  #scale_y_continuous(labels = scales::percent_format()) +
  facet_wrap(~herbivore)