Základné operácie v R – môj cvičebný notebook

Úvod

knitr::opts_chunk$set(echo = TRUE)

Skaláre

Numerické skaláre

a <- 10
b <- 3

a + b

[1] 13

a^2

[1] 100

a %% b

[1] 1

Text

Vytváranie textových premenných a práca s nimi

first <- "Livia"
last  <- "Pancikova"

full_name <- paste(first, last)      # spojí s medzerou
full_nospace <- paste0(first, last)  # spojí bez medzery

full_name

[1] "Livia Pancikova"

full_nospace

[1] "LiviaPancikova"

sentence <- "R Markdown mi pomaha robit pekne reporty."
nchar(sentence)

[1] 41

substr(sentence, 1, 10)

[1] "R Markdown"

Malé cvičenie

Vypíš časť emailu pred znakom @.

email <- "livia.pancikova@uniba.sk"
at_pos <- regexpr("@", email)
substr(email, 1, at_pos - 1)

[1] "livia.pancikova"

Logické hodnoty

Základy

p <- TRUE
q <- FALSE

!p

[1] FALSE

p & q

[1] FALSE

p | q

[1] TRUE

xor(p, q)

[1] TRUE

x <- 12
x > 10

[1] TRUE

x == 12

[1] TRUE

x != 5

[1] TRUE

Malé cvičenie

Over, či je t medzi 30 a 50 a zároveň nepárne.

v1 <- c(2, 4, 6, 8)
v2 <- 1:10
v3 <- seq(from = 0, to = 1, by = 0.2)
v4 <- rep(5, times = 4)

v1

[1] 2 4 6 8

v2

 [1]  1  2  3  4  5  6  7  8  9 10

v3

[1] 0.0 0.2 0.4 0.6 0.8 1.0

v4

[1] 5 5 5 5

Numerické vektory

Generovanie vektorov

v <- c(1, 3, 5, 7)

v + 2

[1] 3 5 7 9

v * 3

[1]  3  9 15 21

mean(v)

[1] 4

sum(v)

[1] 16

max(v)

[1] 7

sort(v, decreasing = TRUE)

[1] 7 5 3 1

Aritmetické operácie s vektormi

x <- c(10, 25, 8, 42, 17, 30)

x[1]

[1] 10

x[2:4]

[1] 25  8 42

x[x > 20]

[1] 25 42 30

which(x > 20)

[1] 2 4 6

Indexovanie a výber prvkov

w <- 1:20
div4 <- w[w %% 4 == 0]

sum(div4)

[1] 60

length(div4)

[1] 5

mean(div4)

[1] 12

Malé cvičenie

Vytvorte vektor w <- 1:20.

1. Spočítajte všetky čísla deliteľné 4.
   
2. Zistite ich počet.
   
3. Vypočítajte ich priemer.

M <- matrix(1:12, nrow = 3, ncol = 4)     # po stĺpcoch (default)
M

     [,1] [,2] [,3] [,4]
[1,]    1    4    7   10
[2,]    2    5    8   11
[3,]    3    6    9   12

dim(M)

[1] 3 4

Matice

Vytvorenie matice a rozmery

M[1, 2]     # 1. riadok, 2. stĺpec

[1] 4

M[, 3]      # celý 3. stĺpec

[1] 7 8 9

M[2, ]      # celý 2. riadok

[1]  2  5  8 11

M[1:2, 2:3] # podmatica

     [,1] [,2]
[1,]    4    7
[2,]    5    8

A <- matrix(c(1, 2, 3, 4), nrow = 2, byrow = TRUE)
B <- matrix(c(5, 6, 7, 8), nrow = 2, byrow = TRUE)

A + B

     [,1] [,2]
[1,]    6    8
[2,]   10   12

A * B        # Hadamardov súčin (po prvkoch)

     [,1] [,2]
[1,]    5   12
[2,]   21   32

A %*% B      # maticové násobenie

     [,1] [,2]
[1,]   19   22
[2,]   43   50

t(A)         # transpozícia

     [,1] [,2]
[1,]    1    3
[2,]    2    4

det(A)

[1] -2

solve(A)

     [,1] [,2]
[1,] -2.0  1.0
[2,]  1.5 -0.5

M2 <- matrix(1:25, nrow = 5, byrow = TRUE)
colSums(M2)

[1] 55 60 65 70 75

t(M2) %*% M2

     [,1] [,2] [,3] [,4] [,5]
[1,]  855  910  965 1020 1075
[2,]  910  970 1030 1090 1150
[3,]  965 1030 1095 1160 1225
[4,] 1020 1090 1160 1230 1300
[5,] 1075 1150 1225 1300 1375

set.seed(123)

# Vytvoríme si jednoduché "dáta o študentoch"
students <- data.frame(
  meno = c("Anna", "Boris", "Cecilia", "Dano", "Eva", "Filip"),
  skupina = sample(c("A", "B"), size = 6, replace = TRUE),
  body = sample(50:100, size = 6, replace = TRUE)
)

students

# Priemer bodov podľa skupiny (novinka: aggregate)
aggregate(body ~ skupina, data = students, FUN = mean)

Môj návrh použitia novinky

set.seed(123)

# Vytvoríme si jednoduché "dáta o študentoch"
students <- data.frame(
  meno = c("Anna", "Boris", "Cecilia", "Dano", "Eva", "Filip"),
  skupina = sample(c("A", "B"), size = 6, replace = TRUE),
  body = sample(50:100, size = 6, replace = TRUE)
)

students

# Priemer bodov podľa skupiny (novinka: aggregate)
aggregate(body ~ skupina, data = students, FUN = mean)