Why you should use functions

Introduction to Writing Functions in R

Richie Cotton

Data Evangelist at DataCamp

The arguments to mean()

Mean has 3 arguments

x: A numeric or date-time vector.
trim: The proportion of outliers from each end to remove before calculating
na.rm: Remove before calculating

Calling mean()

Pass arguments by position

mean(numbers, 0.1, TRUE)

Pass arguments by name

mean(na.rm = TRUE, trim = 0.1, x = numbers)

Common arguments by position, rare arguments by name

mean(numbers, trim = 0.1, na.rm = TRUE)

Analyzing test scores

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_english_raw <- read_csv("test_scores_english.csv")

library(dplyr)
test_scores_english_clean <- test_scores_english_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_art_raw <- read_csv("test_scores_art.csv")

library(dplyr)
test_scores_art_clean <- test_scores_art_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_spanish_raw <- read_csv("test_scores_spanish.csv")

library(dplyr)
test_scores_spanish_clean <- test_scores_spanish_raw %>% 
  select(person_id, first_name, last_name, test_date, score)

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
library(lubridate)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date))

library(readr)
test_scores_english_raw <- read_csv("test_scores_english.csv")

library(dplyr)
library(lubridate)
test_scores_english_clean <- test_scores_english_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date))

library(readr)
test_scores_art_raw <- read_csv("test_scores_art.csv")

library(dplyr)
library(lubridate)
test_scores_art_clean <- test_scores_art_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date))

library(readr)
test_scores_spanish_raw <- read_csv("test_scores_spanish.csv")

library(dplyr)
library(lubridate)
test_scores_spanish_clean <- test_scores_spanish_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date))

library(readr)
test_scores_geography_raw <- read_csv("test_scores_geography.csv")

library(dplyr)
library(lubridate)
test_scores_geography_clean <- test_scores_geography_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date)) %>%
  filter(!is.na(score))

library(readr)
test_scores_english_raw <- read_csv("test_scores_english.csv")

library(dplyr)
library(lubridate)
test_scores_english_clean <- test_scores_english_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date)) %>%
  filter(!is.na(score))

library(readr)
test_scores_art_raw <- read_csv("test_scores_art.csv")

library(dplyr)
library(lubridate)
test_scores_art_clean <- test_scores_art_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date)) %>%
  filter(is.na(score))

library(readr)
test_scores_spanish_raw <- read_csv("test_scores_spanish.csv")

library(dplyr)
library(lubridate)
test_scores_spanish_clean <- test_scores_spanish_raw %>% 
  select(person_id, first_name, last_name, test_date, score) %>%
  mutate(test_date = mdy(test_date)) %>%
  filter(!is.na(score))

Benefits of writing functions

Functions eliminate repetition from your code, which

can reduce your workload, and
help avoid errors.

Functions also allow code reuse and sharing.

Let's practice!

Introduction to Writing Functions in R