📊 R 기초 | 벡터 만들기, 네이밍, 벡터 연산, 특정 원소 선택하기

📌R의 데이터 구조 

 

Image credit @Gaurav Tiwari (Medium) 

 

R에서 제공하는 데이터 구조는 벡터, 매트릭스, 배열, 데이터프레임, 리스트가 있다.  

 

 

📌 벡터 만들기

#벡터란, 하나 혹은 하나이상의 원소를 가질 수 있는 데이터 구조 형태이다. 
#하나의 벡터는 동일한 자료타입을 가져야 한다. 

vector <- "yeah!" 


#c(combine function)을 통해 여러 원소를 가진 벡터를 생성할 수 있다. 
numeric_vector <- c(1,50,60) 
character_vector <- c("s", "a","n")
boolean_vector <-c(TRUE,FALSE,TRUE)

 

 

📌 벡터 이름 지정하기 names() 

# Poker winnings from Monday to Friday
poker_vector <- c(140, -50, 20, -120, 240)

# Roulette winnings from Monday to Friday
roulette_vector <- c(-24, -50, 100, -350, 10)

# Assign days as names of poker_vector
names(poker_vector) <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")

# Assign days as names of roulette_vector
names(roulette_vector) <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")

 

📌 벡터 이름을 변수로 저장한 뒤 지정하기 

# Poker winnings from Monday to Friday
poker_vector <- c(140, -50, 20, -120, 240)

# Roulette winnings from Monday to Friday
roulette_vector <- c(-24, -50, 100, -350, 10)

# The variable days_vector #변수에 이름을 지정한다
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday") 
 
# Assign the names of the day to roulette_vector and poker_vector
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

 

📌 벡터 간 연산 

A_vector <- c(1, 2, 3)
B_vector <- c(4, 5, 6)

#위 두 벡터를 더하자 
total_vector <- A_vector + B_vector
  
# 더한 값을 출력하자 
total_vector

# console 
[1] 5 7 9 

# 포커와 룰렛 수익 (월-금) 
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Assign to total_daily how much you won/lost on each day
total_daily <- roulette_vector + poker_vector
total_daily


#console 
> total_daily
   Monday   Tuesday Wednesday  Thursday    Friday 
      116      -100       120      -470       250

 

📌 두 벡터의 원소의 합을 비교해보자 sum() 

# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Calculate total gains for poker and roulette
# sum()으로 하나의 벡터 내 원소를 모두 더한다
total_poker <-sum(poker_vector) 
total_roulette <-sum(roulette_vector)

# 어떤 벡터가 큰지 확인해보자! 
total_poker > total_roulette

 

📌벡터 특정 원소 선택하기 vector_name[n] | vector_name[n1:n2]

# Poker and roulette winnings from Monday to Friday:
poker_vector <- c(140, -50, 20, -120, 240)
roulette_vector <- c(-24, -50, 100, -350, 10)
days_vector <- c("Monday", "Tuesday", "Wednesday", "Thursday", "Friday")
names(poker_vector) <- days_vector
names(roulette_vector) <- days_vector

# Define a new variable based on a selection
poker_wednesday <-poker_vector[3]

 

#벡터 내 원소 여러개 선택하기

# 벡터 내 원소 여러개 선택하기 
# Define a new variable based on a selection
poker_midweek <- poker_vector[c(2,3,4)]
poker_midweek

#console 
#  Tuesday Wednesday  Thursday 
#      -50        20      -120

 

#[c(2,3,4)]는 너무 길다! [2:4]로 선택도 가능하다 (2,3,4번째 요소를 선택한다) 

# Define a new variable based on a selection
roulette_selection_vector <- roulette_vector[2:4]
roulette_selection_vector

 

 

#벡터에 지정한 이름으로 value를 선택할 수도 있다. 

poker_start <- poker_vector[c("Monday","Tuesday","Wednesday")]
poker_start   

#console
   Monday   Tuesday Wednesday 
      140       -50        20

 

📌벡터의 평균값 구하기 mean(vector_name) 

mean(poker_start)

#console
[1] 36.66667

 

 

📌  selection by comparison | Advanced selection 

# Which days did you make money on poker?
selection_vector <- poker_vector > 0 
  
# Print out selection_vector
selection_vector 

# console
   Monday   Tuesday Wednesday  Thursday    Friday 
     TRUE     FALSE      TRUE     FALSE      TRUE
  
  
 
 # Select from poker_vector these days
poker_winning_days <- poker_vector[selection_vector]
poker_winning_days

# console 
   Monday Wednesday    Friday 
      140        20       240
      

#R knows what to do when you pass a logical vector in square brackets: 
#it will only select the elements that correspond to TRUE in selection_vector.

 

Image credit datacamp.com