関数を使う理由

R関数入門

Richie Cotton

Data Evangelist at DataCamp

mean() の引数

mean には引数が3つあります

  • x: 数値または日時ベクトル
  • trim: 計算前に両端から除外する外れ値の割合
  • na.rm: 計算前に NA を除去
R関数入門

mean() の呼び出し方

位置で渡す

mean(numbers, 0.1, TRUE)

名前で渡す

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

一般的な引数は位置、まれな引数は名前

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

R関数入門

テストスコアの分析

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)
R関数入門
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)
R関数入門
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)
R関数入門
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))
R関数入門
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))
R関数入門

関数作成の利点

関数はコードの重複をなくします。

  • 作業量を減らせます。
  • エラーを避けやすくなります。

また、再利用・共有が容易になります。

R関数入門

練習しましょう！

R関数入門

Preparing Video For Download...