Blog Post - Function Best Practices

function_best_practices.r

# R Function Best Practices used in blog post:
# https://towardsdatascience.com/writing-better-r-functions-best-practices-and-tips-d48ef0691c24

library(ggplot2)

#----------------------------------#

# Function Indentation

# Proper Indentation - Bad Example
print_names <- function(vector_names) {
for (name in vector_names) {
print(paste('Hello',name))
}
}

# Proper Indentation - Good Example
print_names <- function(vector_names) {
  for (name in vector_names) {
    print(paste('Hello',name))
  }
}

print_names(c('Joe','Mary','Anne'))

# Get Car Brand - Not Indented
get_car_brand <- function(car_model) {
  car_brand <- sapply(strsplit(car_model, ' '), '[', 1)
  return (car_brand)
}

# Get Car Brand - Indented
get_car_brand <- function(car_model) {
  car_brand <- sapply(
      strsplit(car_model, ' '), 
      '[', 
      1
    )
  return (car_brand)
}

get_car_brand(rownames(mtcars))

# Shorter Functions over Long Functions

plot_average_horsepower_brand <- function(cars_df) {
  
  cars_df_copy <- cars_df
  
  cars_df_copy['car_brand'] <- sapply(
    strsplit(rownames(cars_df_copy), ' '), 
    '[', 
    1
  )
  
  aggregate_brand <- aggregate(
    cars_df_copy$hp,
    by = list(cars_df_copy$car_brand),
    FUN = mean
  )
  
  sort_order <- factor(
    aggregate_brand[order(aggregate_brand[,'x']),]$Group.1
  )
  
  ggplot(
    data = aggregate_brand,
    aes(x=factor(Group.1, levels=sort_order), y=x, color='darkred')
  ) + geom_point() + theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
  
}
  
plot_average_horsepower_brand(mtcars)

# Breaking down our function into multiple blocks

create_brand <- function(cars_df) {
  
  brands <- sapply(
    strsplit(rownames(cars_df), ' '), 
    '[', 
    1
  )
  
  return (brands)
}
mean_by_variable <- function(df, agg_var, by_var) {
  
  aggregate_brand <- aggregate(
    df[,agg_var],
    by = list(df[,by_var]),
    FUN = mean
  )
  
  return (aggregate_brand)
  
}
plot_sorted_scatter <- function(cars_data, agg_var, by_var) {
  
  # Add Brand
  cars_data$brand <- create_brand(cars_data)
  
  # Create Aggregation
  agg_data <- mean_by_variable(cars_data, agg_var, by_var)
  
  # Sort 
  sort_order <- factor(
    agg_data[order(agg_data[,'x']),]$Group.1
  )
  
  ggplot(
    data = agg_data,
    aes(x=factor(Group.1, levels=sort_order), y=x, color='darkred')
  ) + geom_point() + theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust=1))
  
}
plot_sorted_scatter(mtcars, 'hp', 'brand')

# Doc Strings

return_inverse <- function(x) {
  #' Computes the multiplicative inverse of the input
  return(1/x)
  
}

?return_inverse

library(docstring)

?return_inverse

# Return Inverse with Title
return_inverse <- function(x) {
  #' Multiplicative Inverse of Number
  #' 
  #' @description Computes the multiplicative inverse of the input
  #' 
  #' @param x: Real number.
  return(1/x)
  
}

?return_inverse

# Explicit vs. Implicit Returns
create_brand_explicit <- function(cars_df) {
  brands <- sapply(
    strsplit(rownames(cars_df), ' '), 
    '[', 
    1
  )
  return (brands)
}
create_brand_implicit <- function(cars_df) {
  sapply(
    strsplit(rownames(cars_df), ' '), 
    '[', 
    1
  )  
}