Note_Tech

All technological notes.

Project maintained by simonangel-fong Hosted on GitHub Pages — Theme by mattgraham

R - Function

Back

Function

function_name <- function(arg1, arg2, arg3, ...) {
    ## do any code in here when called
    return(return_object)
}

## Define a function that adds two numbers
add_numbers <- function(x, y) {
    return(x + y)
}

Conditions

if-else

if(condition){
    ## do any code here
}

if(condition){
    ## do any code here
}
else{
    ## do any code here
}

## Sequential stacking of if-else statements
if(condition){
    ## do any code here
}
else if(condition){
    ## do any code here
}
else{
    ## do any code here
}

for loop

for(loop_index in loop_vector) {
    ## do any code in here
}


for(i in c(1:5)) {
    print(i) ## Print the value of i
}

while loop

while(condition) {
    ## do any code in here
}

a=1
while(a <= 5) {
    print(a) ## Print the value of a
    a = a + 1 ## Increment the value of a
}

repeat loop

a=1
repeat {
    if(a == 5){
        break ## if the value of a is 5, terminate the loop
    }
    else {
        print(a)
        a = a+1
    }
}

Looping Functions

Function Output Data Type Description
apply() Array or Matrix Applies a function over the margins of an array (e.g., rows or columns). Works with arrays, matrices, and data frames.
lapply() List Applies a function to each element of a list and returns a list. Useful for operations on lists where the output length may vary.
sapply() Depends on Input Simplifies the output of lapply() into a vector or matrix. Attempts to simplify the result into the most meaningful data structure.
tapply() Varies Applies a function over subsets of a vector, array, or data frame, grouped by a given factor or list of factors. Useful for applying a function by groups.
mapply() Depends on Input Applies a function to the first elements of each argument, the second elements, and so on. Useful for element-wise operations on multiple vectors or lists.

lapply(): return a list

x <- list(a = 1:10, beta = exp(-3:3), logic = c(TRUE,FALSE,FALSE,TRUE))
result <- lapply(x, mean) ## compute the list mean for each list element
result
# $a
# [1] 5.5

# $beta
# [1] 4.535125

# $logic
# [1] 0.5
class(result)
# [1] "list"

sapply()

x <- list(a = 1:10, beta = exp(-3:3), logic = c(TRUE,FALSE,FALSE,TRUE))
result <- sapply(x, mean) ## compute the list mean for each list element
result
#        a     beta    logic
# 5.500000 4.535125 0.500000
class(result)
# [1] "numeric"
# "numeric" because all the elements in the result vector are numeric.

tapply()

groups <- as.factor(rbinom(32, n = 5, prob = 0.4))
groups
# [1] 9  11 13 17 13
# Levels: 9 11 13 17
tapply(groups, groups, length) ## is almost the same as table(groups)
#  9 11 13 17
#  1  1  2  1
table(groups)
# groups
#  9 11 13 17
#  1  1  2  1

apply()

x <- matrix(1:12,nrow=4,ncol=3)
#      [,1] [,2] [,3]
# [1,]    1    5    9
# [2,]    2    6   10
# [3,]    3    7   11
# [4,]    4    8   12
apply(x, 1, sum) ## Take the mean of each row
# [1] 15 18 21 24
apply(x, 2, sum) ## Take the mean of each column
# [1] 10 26 42

mapply()

## Define a function that adds two numbers
add_numbers <- function(x, y) { return(x + y) }
# Create two vectors
vector1 <- c(1, 2, 3)
vector2 <- c(4, 5, 6)
# Apply the add_numbers function element-wise to the two vectors
result <- mapply(add_numbers, vector1, vector2)
# [1] 5 7 9

dplyr

Installing and Loading Package

# Installing dplyr package
install.packages('dplyr', dependencies = T)

# Loading package
library('dplyr')

filter()

starwars %>% filter(skin_color == "light", eye_color == "brown")

arrange()

starwars %>% arrange(height) ## By default ascending sorting
starwars %>% arrange(desc(height)) ## desc is used for descending
starwars %>% arrange(height, mass) ## Sorting based on multiple columns
starwars %>% arrange(desc(height), mass)

slice()

starwars %>% slice(5:10)
starwars %>% slice_head(n=5) ## slice_head() and slice_tail() select the first or last rows
starwars %>% slice_random(n=5) ## slice_sample() randomly selects rows
starwars %>% filter(!is.na(height)) %>% slice_max(height, n=5) ## slice_min() and slice_max() select rows with highest or lowest values of a variable. We first must choose only the values which are not NA

select()

# Select columns by name
starwars %>% select(hair_color, skin_color, eye_color)
# Select all columns between hair_color and eye_color (inclusive)
starwars %>% select(hair_color:eye_color)
# Select all columns except those from hair_color to eye_color (inclusive)
starwars %>% select(!(hair_color:eye_color))
# Select all columns ending with color.
starwars %>% select(ends_with("color"))
# Other choices are starts_with(), matches() and contains()

rename()

# Renaming a column from homeworld to home_world
starwars %>% rename(home_world = homeworld)

mutate()

starwars %>% mutate(height_m = height / 100)
# If you only want to keep the new variables, use .keep = "none"
# We can’t see the height in meters we just calculated, but we can fix that using a select command
starwars %>%
    mutate(height_m = height / 100) %>%
    select(height_m, height, everything())

summarise()

starwars %>% summarise(height = mean(height, na.rm = TRUE))
# An example of using summarise with group_by()
starwars %>%
    group_by(species, sex) %>%
    select(height, mass) %>%
    summarise(
        height = mean(height, na.rm = TRUE),
        mass = mean(mass, na.rm = TRUE)
    )

TOP