Pourquoi utiliser des fonctions

Introduction à l'écriture de fonctions en R

Richie Cotton

Data Evangelist at DataCamp

Les arguments de mean()

mean a 3 arguments

x : Un vecteur numérique ou date-heure.
trim : Proportion à retrancher aux deux extrémités avant le calcul
na.rm : Retirer les valeurs manquantes avant le calcul

Appeler mean()

Transmettre par position

mean(numbers, 0.1, TRUE)

Transmettre par nom

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

Arguments courants par position, rares par nom

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

Analyser les résultats de test

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))

Pourquoi écrire des fonctions

Les fonctions éliminent les répétitions dans votre code, ce qui

peut réduire votre charge de travail, et
aide à éviter les erreurs.

Elles favorisent aussi la réutilisation et le partage du code.

Passons à la pratique !

Introduction à l'écriture de fonctions en R