# Load package
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.4.4 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(lubridate)
library(nycflights13)
Ch20 Vectors
Introduction
Vector Basics
Important types of automic vectors
Using atomic vectors
sample(10) + 10
## [1] 20 17 13 16 11 19 14 18 12 15
1:10 + 1:2
## [1] 2 4 4 6 6 8 8 10 10 12
1:10 + 1:3
## Warning in 1:10 + 1:3: longer object length is not a multiple of shorter object
## length
## [1] 2 4 6 5 7 9 8 10 12 11
data.frame(a = 1:10, b = 1:2)
## a b
## 1 1 1
## 2 2 2
## 3 3 1
## 4 4 2
## 5 5 1
## 6 6 2
## 7 7 1
## 8 8 2
## 9 9 1
## 10 10 2
# data.frame(a = 1:10, b = 1:3)
x <- 1:10
x
## [1] 1 2 3 4 5 6 7 8 9 10
x[5]
## [1] 5
x[c(5, 7)]
## [1] 5 7
x[x>5]
## [1] 6 7 8 9 10
Recursive vectors (lists)
a <- list(a = 1:3, b = "a string", c = pi, d = list(-1, -5))
a
## $a
## [1] 1 2 3
##
## $b
## [1] "a string"
##
## $c
## [1] 3.141593
##
## $d
## $d[[1]]
## [1] -1
##
## $d[[2]]
## [1] -5
a[1:2]
## $a
## [1] 1 2 3
##
## $b
## [1] "a string"
a[[4]]
## [[1]]
## [1] -1
##
## [[2]]
## [1] -5
a[[4]][2]
## [[1]]
## [1] -5
a[[4]][[2]]
## [1] -5
Attributes
x <- 1:10
attr(x, "greeting")
## NULL
#> NULL
attr(x, "greeting") <- "Hi!"
attr(x, "farewell") <- "Bye!"
attributes(x)
## $greeting
## [1] "Hi!"
##
## $farewell
## [1] "Bye!"
Augmented vectors
Ch21 Iteration
Introduction
For loops
# example from the cheatsheet
for (i in 1:4) {
j <- i + 10
print(j)
}
## [1] 11
## [1] 12
## [1] 13
## [1] 14
j
## [1] 14
# example 1: numeric calculation - add 10
x <- 11:15
for (i in seq_along(x)) {
j <- x[i] + 10
print(j)
}
## [1] 21
## [1] 22
## [1] 23
## [1] 24
## [1] 25
# save output
y <- vector("integer", length(x))
for (i in seq_along(x)) {
y[i] <- x[i] + 10
print(y[i])
}
## [1] 21
## [1] 22
## [1] 23
## [1] 24
## [1] 25
# example 2: string operation - extract first letter
x <- c("abc", "xyz")
y <- vector("character", length(x))
for (i in seq_along(x)) {
y[i] <- x[i] %>% str_extract("[a-z]")
print(y[i])
}
## [1] "a"
## [1] "x"
# Output
y
## [1] "a" "x"
3 The map functions
# example 1: numeric calculation - add 10
x <- 11:15
y <- vector("integer", length(x))
for (i in seq_along(x)) {
y[i] <- x[i] + 10
print(y[i])
}
## [1] 21
## [1] 22
## [1] 23
## [1] 24
## [1] 25
# Output
y
## [1] 21 22 23 24 25
# using map function with atomic vector
x
## [1] 11 12 13 14 15
map(.x = x, .f = ~.x + 10)
## [[1]]
## [1] 21
##
## [[2]]
## [1] 22
##
## [[3]]
## [1] 23
##
## [[4]]
## [1] 24
##
## [[5]]
## [1] 25
map_dbl(.x = x, .f = ~.x + 10)
## [1] 21 22 23 24 25
add_10 <- function(x) {x +10}
11 %>% add_10
## [1] 21
map_dbl(.x = x, .f = add_10)
## [1] 21 22 23 24 25
df <- tibble(
a = rnorm(10),
b = rnorm(10),
c = rnorm(10),
d = rnorm(10)
)
map_dbl(df, mean)
## a b c d
## -0.06828501 0.46202750 0.26185692 0.07610149
map_dbl(df, median)
## a b c d
## -0.4353763 0.4869967 0.2736563 -0.1809387
map_dbl(df, sd)
## a b c d
## 1.0629285 0.6664766 0.7259644 0.9055626
df %>% map_dbl(mean)
## a b c d
## -0.06828501 0.46202750 0.26185692 0.07610149
df %>% map_dbl(median)
## a b c d
## -0.4353763 0.4869967 0.2736563 -0.1809387
df %>% map_dbl(sd)
## a b c d
## 1.0629285 0.6664766 0.7259644 0.9055626
Dealing failure
Mapping over multiple arguments