Introduction to R

Eduardo Martínez

2022-09-30

Eduardo Martínez Introduction to R 2022-09-30 1 / 121

1 Arithmetic in R

2 Vectors and Matrices

3 Control Structures

4 Functions

5 DataFrame

6 Graphs - ggplot2

Eduardo Martínez Introduction to R 2022-09-30 2 / 121

R Markdown

Free software to perform statistical procedures.

Rstudio is an IDE for R.

Eduardo Martínez Introduction to R 2022-09-30 3 / 121

 Section 1

Arithmetic in R

Eduardo Martínez Introduction to R 2022-09-30 4 / 121

Basic operations

3+2-10ˆ2

## [1] -95
3+(2-10)ˆ2

## [1] 67
sqrt(16)

## [1] 4
sqrt(2)

## [1] 1.414214

Eduardo Martínez Introduction to R 2022-09-30 5 / 121

Basic operations

3+2-10ˆ2

## [1] -95
3+(2-10)ˆ2

## [1] 67
sqrt(16)

## [1] 4
sqrt(2)

## [1] 1.414214

Eduardo Martínez Introduction to R 2022-09-30 6 / 121

Assigning values to a variable

var1 <- 3
var1

## [1] 3
var2 = 4
var2

## [1] 4
var1ˆ2+var2ˆ2

## [1] 25

Eduardo Martínez Introduction to R 2022-09-30 7 / 121

Functions

sin(3.14)

## [1] 0.001592653
acos(-1)

## [1] 3.141593
exp(1)

## [1] 2.718282

Eduardo Martínez Introduction to R 2022-09-30 8 / 121

Logarithms

log(2) # (ln)

## [1] 0.6931472
log10(2) # log base 10

## [1] 0.30103
log(16,base = 2)

## [1] 4

Eduardo Martínez Introduction to R 2022-09-30 9 / 121

Undefined values (mistakes)

log(0)

## [1] -Inf
1/0

## [1] Inf
0/0

## [1] NaN

Eduardo Martínez Introduction to R 2022-09-30 10 / 121

Boolean operations

value1 = TRUE

value1

## [1] TRUE
class(value1)

## [1] "logical"
value2 = FALSE

Eduardo Martínez Introduction to R 2022-09-30 11 / 121

Boolean operations

value1 && value2 #and

## [1] FALSE
value1 || value2 #or

## [1] TRUE
!value1 #not

## [1] FALSE

Eduardo Martínez Introduction to R 2022-09-30 12 / 121

Functions with boolean output

4 >= 2

## [1] TRUE
var1 != var2 # útil para filtrar

## [1] TRUE
value1 != value2

## [1] TRUE

Eduardo Martínez Introduction to R 2022-09-30 13 / 121

Strings

text1 = "Hello world"

text1

## [1] "Hello world"

class(text1)

## [1] "character"

Eduardo Martínez Introduction to R 2022-09-30 14 / 121

Strings

toupper(text1) # útil para limpiar

## [1] "HELLO WORLD"

tolower(text1) # útil para limpiar

## [1] "hello world"

Eduardo Martínez Introduction to R 2022-09-30 15 / 121

Subsets of a string

substring(text1, 1, 4)

## [1] "Hell"
substring(text1, 6, 10)

## [1] " worl"

substring(text1, 5, 5)

## [1] "o"

Eduardo Martínez Introduction to R 2022-09-30 16 / 121

Replacements

gsub("e","i", text1)

## [1] "Hillo world"

gsub("d","t", text1)

## [1] "Hello worlt"

text2 = "it's me."

paste(text1,text2)

## [1] "Hello world it's me."

Eduardo Martínez Introduction to R 2022-09-30 17 / 121

 Section 2

Vectors and Matrices

Eduardo Martínez Introduction to R 2022-09-30 18 / 121

Vectors

vec1 <- c(8,6,7,5,3,0,9)

vec1[1] # R index starts at 1

## [1] 8
vec1[7]

## [1] 9
vec1[10]

## [1] NA

Eduardo Martínez Introduction to R 2022-09-30 19 / 121

Calling the last element

length(vec1)

## [1] 7
vec1[length(vec1)]

## [1] 9

Eduardo Martínez Introduction to R 2022-09-30 20 / 121

Slicing vectors with [ ]

vec1[2:5]

## [1] 6 7 5 3
vec1[5:10]

## [1] 3 0 9 NA NA NA
vec1[c(2,4,6)]

## [1] 6 5 0
vec1[c(2,4,6,8)]

## [1] 6 5 0 NA

Eduardo Martínez Introduction to R 2022-09-30 21 / 121

Operations

vec2 = c(5,3,8,2,10,0,1)

vec3 = c(3, TRUE, 4, "two", 3, 8, 2)

vec4 = c(3, NA, 4, NA, 3, 8, 2)

Eduardo Martínez Introduction to R 2022-09-30 22 / 121

Operations

vec1 + vec2
vec1 + vec3
vec1 + vec4

Eduardo Martínez Introduction to R 2022-09-30 23 / 121

Vectors from a sequence

vec5 = seq(2, 16, by = 2)

vec6 = seq(50, 20, by = -2)

vec7 = seq(0, 1, by = 0.01)

Eduardo Martínez Introduction to R 2022-09-30 24 / 121

Operations

vec1 - vec2

## [1] 3 3 -1 3 -7 0 8
vec1*vec2

## [1] 40 18 56 10 30 0 9
vec1 %*% vec2

## [,1]
## [1,] 163
vec1 / vec2

## [1] 1.600 2.000 0.875 2.500 0.300 NaN 9.000

Eduardo Martínez Introduction to R 2022-09-30 25 / 121

Operations

vec1 + vec3
vec1 + vec4
vec1 + vec5

Eduardo Martínez Introduction to R 2022-09-30 26 / 121

Operations

vec1 + 3

## [1] 11 9 10 8 6 3 12
vec1 + c(3,3,3,3,3,3,3)

## [1] 11 9 10 8 6 3 12
vec5 + c(2,3)

## [1] 4 7 8 11 12 15 16 19
vec1 + c(2,3)

## Warning in vec1 + c(2, 3): longer object length is not a mu

## object length
## [1] 10 9 9 8 5 3 11

Eduardo Martínez Introduction to R 2022-09-30 27 / 121

Deleting odd positions of vec5

vec5 * c(0,1)

## [1] 0 4 0 8 0 12 0 16

Eduardo Martínez Introduction to R 2022-09-30 28 / 121

Vectorization

vec1ˆ2

## [1] 64 36 49 25 9 0 81
vec1ˆvec2

## [1] 32768 216 5764801 25 59049 1 9

Eduardo Martínez Introduction to R 2022-09-30 29 / 121

Vectorization

sqrt(vec1)

## [1] 2.828427 2.449490 2.645751 2.236068 1.732051 0.000000 3

exp(vec1)

## [1] 2980.95799 403.42879 1096.63316 148.41316 20.08554

log(vec1)

## [1] 2.079442 1.791759 1.945910 1.609438 1.098612 -Inf 2

Eduardo Martínez Introduction to R 2022-09-30 30 / 121

Getting information of a vector

min(vec1)

## [1] 0
max(vec1)

## [1] 9
sum(vec1)

## [1] 38

Eduardo Martínez Introduction to R 2022-09-30 31 / 121

Getting information of a vector

mean(vec1)

## [1] 5.428571
var(vec1)

## [1] 9.619048
sd(vec1)

## [1] 3.101459

Eduardo Martínez Introduction to R 2022-09-30 32 / 121

Getting information of a vector

summary(vec1)

## Min. 1st Qu. Median Mean 3rd Qu. Max.

## 0.000 4.000 6.000 5.429 7.500 9.000
sort(vec2) # de menor a mayor

## [1] 0 1 2 3 5 8 10
sort(vec2, decreasing = TRUE) # de mayor a menor

## [1] 10 8 5 3 2 1 0

Eduardo Martínez Introduction to R 2022-09-30 33 / 121

Funciones sobre vectores “raros”

sumar caracteres sum(vec3)

sumar NA sum(vec4)
sum(vec4, na.rm = TRUE) ## na.remove
vec1 + vec4

Eduardo Martínez Introduction to R 2022-09-30 34 / 121

Boolean vectors

vec8 = c(TRUE, TRUE, FALSE, FALSE, FALSE, TRUE, FALSE)

sum(vec8)

## [1] 3
vec1 + vec8

## [1] 9 7 7 5 3 1 9
mean(vec8)

## [1] 0.4285714

Eduardo Martínez Introduction to R 2022-09-30 35 / 121

Finding NA

is.na(vec4)

## [1] FALSE TRUE FALSE TRUE FALSE FALSE FALSE

sum(is.na(vec4)) # counting NA

## [1] 2
sum(!is.na(vec4)) # counting not NA

## [1] 5

Eduardo Martínez Introduction to R 2022-09-30 36 / 121

Boolean output with vectors

vec1 > 5

## [1] TRUE TRUE TRUE FALSE FALSE FALSE TRUE

sum(vec1 > 5)

## [1] 4
!(vec1 > 5)

## [1] FALSE FALSE FALSE TRUE TRUE TRUE FALSE

sum(vec1 <=5)

## [1] 3

Eduardo Martínez Introduction to R 2022-09-30 37 / 121

Using [] and boolean sentences to filter

is.na(vec4)

## [1] FALSE TRUE FALSE TRUE FALSE FALSE FALSE

vec4[is.na(vec4)] # NA values

## [1] NA NA
vec4[!is.na(vec4)] # not NA values

## [1] 3 4 3 8 2

Eduardo Martínez Introduction to R 2022-09-30 38 / 121

Using [] and boolean sentences to filter

vec1 > 5

## [1] TRUE TRUE TRUE FALSE FALSE FALSE TRUE

vec1[vec1 > 5]

## [1] 8 6 7 9
vec1[vec1 < 8]

## [1] 6 7 5 3 0

Eduardo Martínez Introduction to R 2022-09-30 39 / 121

Using a vector to slice another one

vec1 %% 2 == 0 # TRUE if the entry is even

## [1] TRUE TRUE FALSE FALSE FALSE TRUE FALSE

vec2[vec1 %% 2 == 0] # if the entry in vec1 is even, show the

## [1] 5 3 0
vec4[vec1 %% 2 == 0]

## [1] 3 NA 8

Eduardo Martínez Introduction to R 2022-09-30 40 / 121

Using a vector to slice another one

vec1[vec4 %% 2 == 0]

## [1] NA 7 NA 0 9
vec5[vec1 %% 2 == 0] # be careful

## [1] 2 4 12 16
vec6[vec1 %% 2 == 0] # be careful

## [1] 50 48 40 36 34 26 22 20

Eduardo Martínez Introduction to R 2022-09-30 41 / 121

Assigning values

vec2[5]

## [1] 10
vec2[5] = 1

vec1[4] = 6

Eduardo Martínez Introduction to R 2022-09-30 42 / 121

Data imputation

vec4[is.na(vec4)] = 0

Eduardo Martínez Introduction to R 2022-09-30 43 / 121

Data imputation

vec4 = c(3, NA, 4, NA, 3, 8, 2)

vec4[!is.na(vec4)] # not null values in vec4

## [1] 3 4 3 8 2
mean(vec4[!is.na(vec4)])

## [1] 4

Eduardo Martínez Introduction to R 2022-09-30 44 / 121

Data imputation

vec4[is.na(vec4)] = 4

mean(vec4)

## [1] 4

Eduardo Martínez Introduction to R 2022-09-30 45 / 121

Truncated data

vec6 > 40 #find

## [1] TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE FALSE
## [13] FALSE FALSE FALSE FALSE
vec6[vec6 > 40] #filter

## [1] 50 48 46 44 42
vec6[vec6 > 40] = 40 #replace

Eduardo Martínez Introduction to R 2022-09-30 46 / 121

Delete elements of a vector

vec5

## [1] 2 4 6 8 10 12 14 16
vec5[-2]

## [1] 2 6 8 10 12 14 16
vec5 = vec5[-2]

Eduardo Martínez Introduction to R 2022-09-30 47 / 121

Delete elements of a vector

vec5[-(3:5)] # from 3rd to 5th

## [1] 2 6 14 16
vec5[-c(3,5)] # 3rd and 5th

## [1] 2 6 10 14 16
vec5[c(3,5)] = c(-100,100)

Eduardo Martínez Introduction to R 2022-09-30 48 / 121

Delete elements of a vector

vec5[vec5 > 10] = 8

vec5

## [1] 2 6 -100 10 8 8 8
vec4[vec4 != 4]

## [1] 3 3 8 2

Eduardo Martínez Introduction to R 2022-09-30 49 / 121

Fixing vec3

class(vec3)

## [1] "character"
as.numeric(vec3)

## Warning: NAs introduced by coercion

## [1] 3 NA 4 NA 3 8 2

Eduardo Martínez Introduction to R 2022-09-30 50 / 121

Fixing vec3

vec3 = as.numeric(vec3)

## Warning: NAs introduced by coercion

vec3[2] = 1
vec3[4] = 2
sum(vec3)

## [1] 23

Eduardo Martínez Introduction to R 2022-09-30 51 / 121

Coercion

var1 = "3"
var2 = "4"
# var1 + var2

Eduardo Martínez Introduction to R 2022-09-30 52 / 121

Coercion

as.numeric(var1) + as.numeric(var2)

## [1] 7
# as.logical
# as.character
# as.complex (rarely used)

Eduardo Martínez Introduction to R 2022-09-30 53 / 121

Matrices

m1 = c(1,2,4)
m2 = c(3,2,5)
m = matrix(c(m1,m2), nrow = 3, ncol =2) # Change nrow and nco
m

## [,1] [,2]
## [1,] 1 3
## [2,] 2 2
## [3,] 4 5

Eduardo Martínez Introduction to R 2022-09-30 54 / 121

Matrices

m3 = c(1,5,6)

m= matrix(c(m1,m2,m3), nrow = 3, ncol = 3) # opción 1: usar ma

## [,1] [,2] [,3]

## [1,] 1 3 1
## [2,] 2 2 5
## [3,] 4 5 6

Eduardo Martínez Introduction to R 2022-09-30 55 / 121

Matrices

m = matrix(c(m1,m2), nrow = 3, ncol =2) # opci?n 2: cbind

m

## [,1] [,2]
## [1,] 1 3
## [2,] 2 2
## [3,] 4 5
m5 = cbind(m,m3) #column binding, tambi?n existe rbind
m5

## m3
## [1,] 1 3 1
## [2,] 2 2 5
## [3,] 4 5 6

Eduardo Martínez Introduction to R 2022-09-30 56 / 121

Matrices

Wrong use of rbind rbind(m,m3)

Eduardo Martínez Introduction to R 2022-09-30 57 / 121

Matrices

# fixing the previous rbind sentence

rbind(m5,m3)

## m3
## 1 3 1
## 2 2 5
## 4 5 6
## m3 1 5 6

Eduardo Martínez Introduction to R 2022-09-30 58 / 121

Slicing a matrix with [ row, col ]
m5

## m3
## [1,] 1 3 1
## [2,] 2 2 5
## [3,] 4 5 6
m5[1:2, ] #row 1 a 2, all columns

## m3
## [1,] 1 3 1
## [2,] 2 2 5
m5[,1:2] #col 1 a 2, all rows

##
## [1,] 1 3
## [2,] 2 2
## [3,] 4 5
Eduardo Martínez Introduction to R 2022-09-30 59 / 121
Usign c( ) to “jump”
m5

## m3
## [1,] 1 3 1
## [2,] 2 2 5
## [3,] 4 5 6
m5[c(1,3),]

## m3
## [1,] 1 3 1
## [2,] 4 5 6
m5[,c(1,3)]

## m3
## [1,] 1 1
## [2,] 2 5
## [3,] 4 6
Eduardo Martínez Introduction to R 2022-09-30 60 / 121
Linear algebra functions

m5

## m3
## [1,] 1 3 1
## [2,] 2 2 5
## [3,] 4 5 6
diag(m5)

## [1] 1 2 6
t(m5)

## [,1] [,2] [,3]

## 1 2 4
## 3 2 5
## m3 1 5 6

Eduardo Martínez Introduction to R 2022-09-30 61 / 121

Linear algebra functions

det(m5)

## [1] 13
dim(m)

## [1] 3 2

Eduardo Martínez Introduction to R 2022-09-30 62 / 121

Operations

m6 = t(m5)
m5 + m6

## m3
## [1,] 2 5 5
## [2,] 5 4 10
## [3,] 5 10 12
m5 + 3 ## recursion

## m3
## [1,] 4 6 4
## [2,] 5 5 8
## [3,] 7 8 9

Eduardo Martínez Introduction to R 2022-09-30 63 / 121

Operations

m5 + matrix(3, nrow=3, ncol=3)

## m3
## [1,] 4 6 4
## [2,] 5 5 8
## [3,] 7 8 9
m5 + 3 == m5 + matrix(3, nrow=3, ncol=3)

## m3
## [1,] TRUE TRUE TRUE
## [2,] TRUE TRUE TRUE
## [3,] TRUE TRUE TRUE

Eduardo Martínez Introduction to R 2022-09-30 64 / 121

Operations

m5 %*% m6

## [,1] [,2] [,3]

## [1,] 11 13 25
## [2,] 13 33 48
## [3,] 25 48 77
m5 * m6

## m3
## [1,] 1 6 4
## [2,] 6 4 25
## [3,] 4 25 36

Eduardo Martínez Introduction to R 2022-09-30 65 / 121

Vectorization over a matrix

exp(m)

## [,1] [,2]
## [1,] 2.718282 20.085537
## [2,] 7.389056 7.389056
## [3,] 54.598150 148.413159
sqrt(m)

## [,1] [,2]
## [1,] 1.000000 1.732051
## [2,] 1.414214 1.414214
## [3,] 2.000000 2.236068

Eduardo Martínez Introduction to R 2022-09-30 66 / 121

Matrix from a sequence

m7 = matrix(1:12,nrow = 4, ncol = 3)

m8 = rbind(m5,m6,m7)

Eduardo Martínez Introduction to R 2022-09-30 67 / 121

 Section 3

Control Structures

Eduardo Martínez Introduction to R 2022-09-30 68 / 121

Context

Problem: Determine whether a number is “big” or not Solution: Compare

with 30
test = 300

Eduardo Martínez Introduction to R 2022-09-30 69 / 121

if then

if(test < 30){

print('small')
}

Eduardo Martínez Introduction to R 2022-09-30 70 / 121

if then else

if(test < 30){

print('small')
}else{
print('big')
}

## [1] "big"

Eduardo Martínez Introduction to R 2022-09-30 71 / 121

if anidados

if(test < 30){

print('es un número pequeño')
}else{if(test>30){
print('es un número grande')
}else{
print('the edge')
}
}

## [1] "es un número grande"

Eduardo Martínez Introduction to R 2022-09-30 72 / 121

Vectorized if (similar to Excel)

ifelse(test < 30, 'small', 'big')

## [1] "big"

Eduardo Martínez Introduction to R 2022-09-30 73 / 121

Control structures and vectorization

if(vec6 < 30){ print(‘small’) }else{ print(‘big’) }

Eduardo Martínez Introduction to R 2022-09-30 74 / 121

Control structures and vectorization

ifelse(vec6 < 30, 'small', 'big')

## [1] "big" "big" "big" "big" "big" "big" "big"

## [10] "big" "big" "small" "small" "small" "small" "small
ifelse(vec1 %% 2 == 0, 'even','odd')

## [1] "even" "even" "odd" "even" "odd" "even" "odd"

Eduardo Martínez Introduction to R 2022-09-30 75 / 121

For loop

list = vec1

# variable i as a counter

for(i in 1:7){
print(list[i])
}

## [1] 8
## [1] 6
## [1] 7
## [1] 6
## [1] 3
## [1] 0
## [1] 9

Eduardo Martínez Introduction to R 2022-09-30 76 / 121

Standarization

for(i in 1:7){
print((list[i] - mean(list))/sd(list))
}

## [1] 0.7830416
## [1] 0.1381838
## [1] 0.4606127
## [1] 0.1381838
## [1] -0.8291029
## [1] -1.79639
## [1] 1.105471

Eduardo Martínez Introduction to R 2022-09-30 77 / 121

Storing

standardlist = c()
for(i in 1:7){
standardlist[i]=(list[i] - mean(list))/sd(list)
}
standardlist

## [1] 0.7830416 0.1381838 0.4606127 0.1381838 -0.8291029

Eduardo Martínez Introduction to R 2022-09-30 78 / 121

Fixing the end of the loop

for(i in 1:length(list)){
print(list[i])
}

## [1] 8
## [1] 6
## [1] 7
## [1] 6
## [1] 3
## [1] 0
## [1] 9

Eduardo Martínez Introduction to R 2022-09-30 79 / 121

Jumps

for(i in seq(1,7,by=2)){
print(list[i])
}

## [1] 8
## [1] 7
## [1] 3
## [1] 9

Eduardo Martínez Introduction to R 2022-09-30 80 / 121

for + if works like vectotrization

for(i in 1:length(list)){
if(list[i] < 30){
print('small')
}else{
print('big')
}
}

## [1] "small"
## [1] "small"
## [1] "small"
## [1] "small"
## [1] "small"
## [1] "small"
## [1] "small"

Eduardo Martínez Introduction to R 2022-09-30 81 / 121

for runs over lists

for(i in list){
print(i)
}

## [1] 8
## [1] 6
## [1] 7
## [1] 6
## [1] 3
## [1] 0
## [1] 9

Eduardo Martínez Introduction to R 2022-09-30 82 / 121

for and validations

for(value in list){
if(value>5){
print("not valid")
}
}

## [1] "not valid"

## [1] "not valid"
## [1] "not valid"
## [1] "not valid"
## [1] "not valid"

Eduardo Martínez Introduction to R 2022-09-30 83 / 121

for and validations

for(value in list){
if(value>5){
print(paste(value," is not valid"))
}
}

## [1] "8 is not valid"

## [1] "6 is not valid"
## [1] "7 is not valid"
## [1] "6 is not valid"
## [1] "9 is not valid"

Eduardo Martínez Introduction to R 2022-09-30 84 / 121

for and validations

for(i in 1:length(list)){
if(list[i] > 5){
print(paste("The value at position ",i,"is not valid becau
}
}

## [1] "The value at position 1 is not valid because 8 is g

## [1] "The value at position 2 is not valid because 6 is g
## [1] "The value at position 3 is not valid because 7 is g
## [1] "The value at position 4 is not valid because 6 is g
## [1] "The value at position 7 is not valid because 9 is g

Eduardo Martínez Introduction to R 2022-09-30 85 / 121

While loop

i = 1
while(i <= length(list)){
print(list[i])
i=i+1
}

## [1] 8
## [1] 6
## [1] 7
## [1] 6
## [1] 3
## [1] 0
## [1] 9

Eduardo Martínez Introduction to R 2022-09-30 86 / 121

 Section 4

Functions

Eduardo Martínez Introduction to R 2022-09-30 87 / 121

Defining functions

isbig <- function(n){

if(n < 30){
print('small')
}else{if(n>30){
print('big')
}else{
print('IDK')
}

}
}

Eduardo Martínez Introduction to R 2022-09-30 88 / 121

Calling a function

isbig(15)

## [1] "small"
isbig(150)

## [1] "big"
isbig(30)

## [1] "IDK"

Eduardo Martínez Introduction to R 2022-09-30 89 / 121

Even function

iseven = function(n){
remainder = n %% 2
if(remainder == 0)
return(TRUE)
return(FALSE)
}

Eduardo Martínez Introduction to R 2022-09-30 90 / 121

Even function

iseven(15)

## [1] FALSE
iseven(258928)

## [1] TRUE
# iseven(vec1) # Wrong

sapply(vec1, iseven) # vectorized function

## [1] TRUE TRUE FALSE TRUE FALSE TRUE FALSE

Eduardo Martínez Introduction to R 2022-09-30 91 / 121

Function with seevral arguments

isdivisible <- function(N1,N2){

if(N1 %% N2 == 0)
return(TRUE)
return(FALSE)
}

isdivisible(15,4)

## [1] FALSE
isdivisible(21616431684,4)

## [1] TRUE

Eduardo Martínez Introduction to R 2022-09-30 92 / 121

if in a function

isdivisible2 <- function(N1,N2){

ifelse(N1 %% N2 == 0,return('yes'),return('no'))
}

isdivisible2(15,4)

## [1] "no"

Eduardo Martínez Introduction to R 2022-09-30 93 / 121

Function over a list

overaverage = function(list,value){
if(value > mean(list))
return('above average')
return('not above average')
}

overaverage(vec6,40)

## [1] "above average"

overaverage(vec1,7)

## [1] "above average"

Eduardo Martínez Introduction to R 2022-09-30 94 / 121

Calling functions
for(value in vec5){
print(value)
print(overaverage(vec5, value))
}

## [1] 2
## [1] "above average"
## [1] 6
## [1] "above average"
## [1] -100
## [1] "not above average"
## [1] 10
## [1] "above average"
## [1] 8
## [1] "above average"
## [1] 8
## [1] "above average"
## [1] 8 Martínez
Eduardo Introduction to R 2022-09-30 95 / 121
 Section 5

DataFrame

Eduardo Martínez Introduction to R 2022-09-30 96 / 121

Loading data

favs <- read.table("favorites.txt", sep="," , header = TRUE)

Eduardo Martínez Introduction to R 2022-09-30 97 / 121

Using dialog frame

# favs <- read.table(file.choose(), sep="," , header = TRUE)

Eduardo Martínez Introduction to R 2022-09-30 98 / 121

read.csv

favs = read.csv("favorites.txt")

Eduardo Martínez Introduction to R 2022-09-30 99 / 121

Class

class(favs)

## [1] "data.frame"
head(favs) ## first 5

## flavor number
## 1 pistachio 6
## 2 mint chocolate chip 7
## 3 vanilla 5
## 4 chocolate 10
## 5 strawberry 2
## 6 neopolitan 4

Eduardo Martínez Introduction to R 2022-09-30 100 / 121

Use of $ to choose a column

names(favs)

## [1] "flavor" "number"

class(favs$flavor)

## [1] "character"
class(favs$number)

## [1] "integer"

Eduardo Martínez Introduction to R 2022-09-30 101 / 121

String as factor

favs = read.csv("favorites.txt", stringsAsFactors = TRUE)

class(favs$flavor)

## [1] "factor"

Eduardo Martínez Introduction to R 2022-09-30 102 / 121

Using [ ]

favs$flavor

## [1] pistachio mint chocolate chip vanilla

## [4] chocolate strawberry neopolitan
## 6 Levels: chocolate mint chocolate chip neopolitan pistachi
favs[["flavor"]]

## [1] pistachio mint chocolate chip vanilla

## [4] chocolate strawberry neopolitan
## 6 Levels: chocolate mint chocolate chip neopolitan pistachi

Eduardo Martínez Introduction to R 2022-09-30 103 / 121

Using [ ]

favs[,1]

## [1] pistachio mint chocolate chip vanilla

## [4] chocolate strawberry neopolitan
## 6 Levels: chocolate mint chocolate chip neopolitan pistachi
favs[1:3,]

## flavor number
## 1 pistachio 6
## 2 mint chocolate chip 7
## 3 vanilla 5

Eduardo Martínez Introduction to R 2022-09-30 104 / 121

Rename a column

names(favs)

## [1] "flavor" "number"

names(favs)[1] = "flav"

names(favs)

## [1] "flav" "number"

Eduardo Martínez Introduction to R 2022-09-30 105 / 121

Structure

str(favs)

## 'data.frame': 6 obs. of 2 variables:

## $ flav : Factor w/ 6 levels "chocolate","mint chocolate c
## $ number: int 6 7 5 10 2 4

Eduardo Martínez Introduction to R 2022-09-30 106 / 121

 Section 6

Graphs - ggplot2

Eduardo Martínez Introduction to R 2022-09-30 107 / 121

install.packages("ggplot2")

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-lib

## (as 'lib' is unspecified)
library(ggplot2)

Eduardo Martínez Introduction to R 2022-09-30 108 / 121

ggplot(favs, aes(x=flav,y=number))+ggtitle("Ice Cream") + geom
Ice Cream

10.0

7.5
number

5.0

2.5

0.0

chocolate mint chocolate chip neopolitan pistachio strawberry vanilla

flav
Eduardo Martínez Introduction to R 2022-09-30 109 / 121
mtcars
mtcars

## mpg cyl disp hp drat wt qsec vs

## Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0
## Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0
## Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1
## Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1
## Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0
## Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1
## Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0
## Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1
## Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1
## Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1
## Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1
## Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0
## Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0
## Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0
## Cadillac Fleetwood
Eduardo Martínez 10.4 8 to472.0
Introduction R 205 2.93 5.250 17.98
2022-09-30 0
110 / 121
Frequency table

unique(mtcars$carb)

## [1] 4 1 2 3 6 8
table(mtcars$carb)

##
## 1 2 3 4 6 8
## 7 10 3 10 1 1

Eduardo Martínez Introduction to R 2022-09-30 111 / 121

Bar graph
qplot(factor(carb),data = mtcars, geom = "bar")

## Warning: `qplot()` was deprecated in ggplot2 3.4.0.

## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where th
## generated.

10.0

7.5

5.0

Eduardo Martínez Introduction to R 2022-09-30 112 / 121

Bar graph
qplot(factor(carb),data = mtcars, geom = "bar",xlab="number of

10.0

7.5

5.0

2.5

Eduardo Martínez Introduction to R 2022-09-30 113 / 121

Bar graphs
qplot(factor(carb),data = mtcars,
geom = "bar",xlab="number of carburetors",
fill =factor(carb))

10.0

7.5

factor(carb)
1
2

5.0 3
4
6
8

2.5

Eduardo Martínez Introduction to R 2022-09-30 114 / 121

Intervals

cut(mtcars$mpg, 6)

## [1] (18.2,22.1] (18.2,22.1] (22.1,26.1] (18.2,22.1] (18.2,

## [7] (10.4,14.3] (22.1,26.1] (22.1,26.1] (18.2,22.1] (14.3,
## [13] (14.3,18.2] (14.3,18.2] (10.4,14.3] (10.4,14.3] (14.3,
## [19] (30,33.9] (30,33.9] (18.2,22.1] (14.3,18.2] (14.3,
## [25] (18.2,22.1] (26.1,30] (22.1,26.1] (30,33.9] (14.3,
## [31] (14.3,18.2] (18.2,22.1]
## 6 Levels: (10.4,14.3] (14.3,18.2] (18.2,22.1] (22.1,26.1] .
freq = table(cut(mtcars$mpg, 6))

Eduardo Martínez Introduction to R 2022-09-30 115 / 121

Histogram
qplot(mpg, data=mtcars, geom="histogram")

## `stat_bin()` using `bins = 30`. Pick better value with `bin

Eduardo Martínez Introduction to R 2022-09-30 116 / 121

Histogram
qplot(mpg, data=mtcars, geom="histogram", binwidth = 3.9)

10.0

7.5

5.0

2.5

Eduardo Martínez Introduction to R 2022-09-30 117 / 121

Histogram
qplot(mpg, data=mtcars, geom="histogram", binwidth = 3.9, colo

10.0

7.5

5.0

2.5

Eduardo Martínez Introduction to R 2022-09-30 118 / 121

KDE
qplot(mpg, data=mtcars, geom="density")

0.06

0.04

0.02

Eduardo Martínez Introduction to R 2022-09-30 119 / 121

Bonus

## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-lib

## (as 'lib' is unspecified)
## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-lib
## (as 'lib' is unspecified)
## Using libcurl 7.68.0 with OpenSSL/1.1.1f

Eduardo Martínez Introduction to R 2022-09-30 120 / 121

Import JSON
df = fromJSON('https://www.datos.gov.co/resource/24ny-2dhf.jso
head(df)

## icount entidad pr latitud longitud clasificacion

## 1 2 INVIAS-OTROS 37 1.020441 -77.698917 Muy Bajo
## 2 2 ANI 36 0.997095 -77.474728 Muy Bajo
## 3 4 ANI 79 1.163092 -77.286501 Muy Bajo
## 4 2 INVIAS-OTROS sd 1.168242 -77.255688 Muy Bajo
## 5 2 INVIAS-OTROS 20 3.879461 -76.922322 Muy Bajo
## 6 2 INVIAS-OTROS 26 3.870278 -76.87666 Muy Bajo
## departamento divipola id_mt id_tramo ti
## 1 NARIÑO 52720 <NA> <NA>
## 2 NARIÑO 52352 4G025 RumPast_Tramo_UF3
## 3 NARIÑO 52001 4G025 RumPast_Tramo_UF5
## 4 NARIÑO 52001 <NA> RPC_Tramo_5VOrientPasto S
## 5 VALLE DEL CAUCA 76109 <NA> ViaPuerto_Tramo_UF0 S
## 6 VALLE DEL CAUCA 76109 <NA> ViaPuerto_Tramo_UF0 S
Eduardo Martínez Introduction to R 2022-09-30 121 / 121