Module 12: Apply it to your data 11

Chapter 19 Functions

Import your data

plastic_data <- read_excel("GDP_vs_PlasticWaste_Analysis.xlsx")

glimpse(plastic_data)

## Rows: 150
## Columns: 6
## $ Country                                                                    <chr> …
## $ `GDP per Capita (USD)`                                                     <dbl> …
## $ `Plastic Waste per Capita (kg)`                                            <dbl> …
## $ `Total Plastic Waste Generation (tonnes)`                                  <dbl> …
## $ `Mismanaged Plastic Waste (tonnes)`                                        <dbl> …
## $ `Managed Plastic Waste (tonnes) (recycled, incinerated, sealed landfills)` <dbl> …

Create Data Frame Functions

Example 1: Count numeric columns

Code Snippet

ncol_num <- plastic_data %>%
  select(where(is.numeric)) %>%
  ncol()

ncol_num

## [1] 5

Turn into a Function

count_numeric_columns <- function(df) {
  df %>%
    select(where(is.numeric)) %>%
    ncol()
}

count_numeric_columns(plastic_data)

## [1] 5

Add Arguments for Detail

count_columns_by_type <- function(df, col_type = "numeric") {
  if (col_type == "numeric") {
    return(df %>% select(where(is.numeric)) %>% ncol())
  } else if (col_type == "character") {
    return(df %>% select(where(is.character)) %>% ncol())
  } else {
    stop("Unsupported column type")
  }
}

count_columns_by_type(plastic_data, "character")

## [1] 1

---

Example 2: Count Rows that Meet a Condition

Code Snippet

n_high_gdp <- plastic_data %>%
  filter(`GDP per Capita (USD)` > 20000) %>%
  nrow()

n_high_gdp

## [1] 51

Turn into a Function

count_high_gdp <- function(df, threshold = 20000) {
  df %>%
    filter(`GDP per Capita (USD)` > threshold) %>%
    nrow()
}

count_high_gdp(plastic_data, 25000)

## [1] 43

---

Example 3: Create Your Own

Code Snippet

high_impact_countries <- plastic_data %>%
  filter(`Plastic Waste per Capita (kg)` > 0.5,
         `GDP per Capita (USD)` > 15000) %>%
  select(Country, `GDP per Capita (USD)`, `Plastic Waste per Capita (kg)`) %>%
  arrange(desc(`Plastic Waste per Capita (kg)`))

high_impact_countries

## # A tibble: 4 × 3
##   Country               `GDP per Capita (USD)` `Plastic Waste per Capita (kg)`
##   <chr>                                  <dbl>                           <dbl>
## 1 Kuwait                                 75204                           0.686
## 2 Antigua and Barbuda                    19213                           0.66 
## 3 Saint Kitts and Nevis                  21412                           0.654
## 4 Barbados                               16418                           0.57

Turn into a Function

identify_high_impact_countries <- function(df, waste_threshold = 0.5, gdp_threshold = 15000) {
  df %>%
    filter(`Plastic Waste per Capita (kg)` > waste_threshold,
           `GDP per Capita (USD)` > gdp_threshold) %>%
    select(Country, `GDP per Capita (USD)`, `Plastic Waste per Capita (kg)`) %>%
    arrange(desc(`Plastic Waste per Capita (kg)`))
}

identify_high_impact_countries(plastic_data)

## # A tibble: 4 × 3
##   Country               `GDP per Capita (USD)` `Plastic Waste per Capita (kg)`
##   <chr>                                  <dbl>                           <dbl>
## 1 Kuwait                                 75204                           0.686
## 2 Antigua and Barbuda                    19213                           0.66 
## 3 Saint Kitts and Nevis                  21412                           0.654
## 4 Barbados                               16418                           0.57

Additional Function

average_waste_by_gdp <- function(df, gdp_split = 20000) {
  df %>%
    mutate(GDP_Level = if_else(`GDP per Capita (USD)` > gdp_split, "High GDP", "Low GDP")) %>%
    group_by(GDP_Level) %>%
    summarise(Average_Waste = mean(`Plastic Waste per Capita (kg)`, na.rm = TRUE))
}

average_waste_by_gdp(plastic_data)

## # A tibble: 2 × 2
##   GDP_Level Average_Waste
##   <chr>             <dbl>
## 1 High GDP          0.232
## 2 Low GDP           0.142