Module-1 Basics of R

> print("Welcome R Programming Language.")

[1] "Welcome R Programming Language."

> 5+6

[1] 11

> x=56**78

>x

[1] 2.283842e+136

> demo="hello R Programming"

> demo

[1] "hello R Programming"

> #this is r studio introduction

> demo1<-2+3

> demo2=5+6

> demo1

[1] 5

> demo2

[1] 11

> sessionInfo()

> y=1:5

> z=6:10

> plot(y,z)

> name="Parth Mistry"

> tolower(name)

[1] "parth mistry"

> toupper(name)

[1] "PARTH MISTRY"

> #R is case sensitive language

> A=10

> #variable in R Programming

> var_name=10

> [Link]=10

> _var_name=10

Error: unexpected symbol in "_var_name"

> var_name*=10

Error: unexpected '=' in "var_name*="

> .var_name=10

> 5var_name=10

Error: unexpected symbol in "5var_name"

> v5ar_name5=10

> #Assignment of variable

> var1=10

> var2<-20

> 10->var3

> print(var1)

[1] 10

> cat(var1, " ",var2)

10 20

> cat(var1," ",var2, "\n",var3)

10 20

10

> #Types of Data

> #Under Atomic Types

> #1. Numeric

> x=25.67
> print(x)

[1] 25.67

> class(x)

[1] "numeric"

> typeof(x)

[1] "double"

> cat(x,class(x),typeof(x))

25.67 numeric double

> #2. Integer

> x=46864L

> print(x)

[1] 46864

> class(x)

[1] "integer"

> typeof(x)

[1] "integer"

> cat(x,class(x),typeof(x))

46864 integer integer

> #3. Character

> sub="Data Science"

> print(sub)

[1] "Data Science"

> class(sub)

[1] "character"

> typeof(sub)

[1] "character"

> cat(sub,class(sub),typeof(sub))

Data Science character character

> #4. Logical

> flag=TRUE

> print(flag)
[1] TRUE

> class(flag)

[1] "logical"

> typeof(flag)

[1] "logical"

> cat(flag,class(flag),typeof(flag))

TRUE logical logical

> # with & (used to compare 2 variables) as well as short of cat = c

> x=c(TRUE, FALSE, TRUE, FALSE)

> y=c(TRUE, TRUE, FALSE, FALSE)

> x[3] & y[3]

[1] FALSE

> # Logical &&

> x = c(TRUE, FALSE, TRUE)

> y = c(TRUE, TRUE, FALSE)

> result = x[2] && y[2]

> print(result)

[1] FALSE

> #Logical !

> x = TRUE

> !x

[1] FALSE

> #Logical | ||

> x = c(TRUE, FALSE, TRUE, TRUE, FALSE)

> y = c(FALSE, TRUE, FALSE, TRUE, FALSE)

> x|y

[1] TRUE TRUE TRUE TRUE FALSE

> x = c(TRUE, FALSE, TRUE)

> y = c(FALSE, TRUE, FALSE)

> x[1] || y[1]

[1] TRUE
> # Complex

> z=4+3i

> print(z)

[1] 4+3i

> class(z)

[1] "complex"

> typeof(z)

[1] "complex"

> #Raw

> raw_data= charToRaw("Hello")

> print(raw_data)

[1] 48 65 6c 6c 6f

> class(raw_data)

[1] "raw"

> typeof(raw_data)

[1] "raw"

> num = 123

> raw_data = charToRaw([Link](num))

> raw_data

[1] 31 32 33

> #converting data type in R

> num1<- [Link](26L)

> num1

[1] 26

> num2<- [Link](25-56i)> num2

[1] 25

> num3<- [Link](TRUE)

> num3

[1] 1

> num4<- [Link]("abcde456")

> num4
[1] NA

> num5<- [Link]("12345")

> num5

[1] 12345

> #integer

> int1<- [Link](52.6544)

> int1

[1] 52

> int2<- [Link](45-56i)

> int2

[1] 45

> int3<- [Link](TRUE)

> int3

[1] 1

> int4<- [Link]("12345abcd")

> int4

[1] NA

> #complex

> com1<- [Link](562.4556)

> com1

[1] 562.4556+0i

> com2<- [Link](45L)

> com2

[1] 45+0i

> com3<- [Link](FALSE)

> com3

[1] 0+0i

> #logical

> log1<- [Link](15.78i)

> log1
[1] TRUE

> log2<- [Link](0-5i)

> log2

[1] TRUE

> log3<- [Link](0)

> log3

[1] FALSE

> log4<- [Link]("1234")

> log4

[1] NA

> #character

> char1<- [Link](45L)

> char1

[1] "45"

> char2<- [Link](52-89i)

> char2

[1] "52-89i"

> char3<- [Link](TRUE)

> char3

[1] "TRUE"

#raw to character

> rawToChar([Link](c(0x68, 0x65, 0x6c, 0x6c, 0x6f)))

[1] "hello"

> rawToChar([Link](c(0x50, 0x61, 0x72, 0x74, 0x68, 0x20, 0x4d, 0x69, 0x73, 0x74, 0x72, 0x79)))

[1] "Parth Mistry"

> #data types=vectors, list, matrices, data frames, factors,

> ##element of vector are known as components

> #length(): no. of element in vector

> vec <-c(10, 20, 30, 40)

> print(vec)
[1] 10 20 30 40

> class(vec)

[1] "numeric"

> a<-c(3, 4, 5, 1, 5, 7)

>a

[1] 3 4 5 1 5 7

> b<--3:5

>b

[1] -3 -2 -1 0 1 2 3 4 5

> sq<-seq(1,5)

> sq

[1] 1 2 3 4 5

> sq<-seq(1,5, by=.5)

> sq

[1] 1.0 1.5 2.0 2.5 3.0 3.5 4.0 4.5 5.0

> sq<-seq(1,5, by=.4)

> sq

[1] 1.0 1.4 1.8 2.2 2.6 3.0 3.4 3.8 4.2 4.6 5.0

> sq<-seq(1,5,[Link]= 5)

> sq

[1] 1 2 3 4 5

sq<-seq(1,3, [Link]= 5)

> sq

[1] 1.0 1.5 2.0 2.5 3.0

> sq[4]

[1] 2.5

> sq[1]

[1] 1

[1] 1.00 25.75 50.50 75.25 100.00

> numv<-c(12,3, 52.6, 23,45, 89, 145)

[1] 12.0 3.0 52.6 23.0 45.0 89.0 145.0

> class(numv)

[1] "numeric"

> intv<-c(5, 6, 1, 8, 9, 7)

> intv<- [Link](intv)

> class(intv)

[1] "integer"

> intv<-c(5L, 6L, 1L, 8L, 9L, 7L)

> intv

[1] 5 6 1 8 9 7

> class(intv)

[1] "integer"

> charv<-c(1, 5, 8, 7, 9)

> charv<- [Link](charv)

> class(charv)

[1] "integer"

> charvv<-c("parth", "pruthvi", "varun", "rishi")

> charvv

[1] "parth" "pruthvi" "varun" "rishi"

> class(charvv)

[1] "character"

> #logical vector

> #Accessing element of vector

> #by indexing[]

> #indexing start from1 not 0

> char_vec<-c("parth"=12, "trusharkant"=32, "mistry"=31)

> char_vec

parth trusharkant mistry

12 32 31
 > char_vec["parth"]

parth

12

> #vector operations

> a1<-c(1, 2, 3, 4, 5, 6, 7)

> a2<-c("parth", "trusharkant", "mistry")

> a3<-c(a1,a2)

> a3

[1] "1" "2" "3" "4" "5" "6"

[7] "7" "parth" "trusharkant" "mistry"

> a4<-c(5, 6, 7, 8, 1, 2, 4)
> a1*a4
[1] 5 12 21 32 5 12 28
> a1-a4
[1] -4 -4 -4 -4 4 4 3
> a1/a4
[1] 0.2000000 0.3333333 0.4285714 0.5000000 5.0000000 3.0000000 1.7500000

> a2[3]

[1] "mistry"

> a2[7]

[1] NA

> a2[-2]

[1] "parth" "mistry"

> a2[2:4]

[1] "trusharkant" "mistry" NA

> lst <- list(25, "R language", TRUE)

> print(lst)

[[1]]

[1] 25

[[2]]

[1] "R language"

[[3]]

[1] TRUE

> #matrix

> mat <- matrix(1:6, nrow=2, ncol=3)

> print(mat)

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

[1,] 1 3 5

[2,] 2 4 6

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

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

[1,] 1 4 7 10

[2,] 2 5 8 11

[3,] 3 6 9 12

> matrix(7:18, ncol=4, nrow=3)

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

[1,] 7 10 13 16

[2,] 8 11 14 17

[3,] 9 12 15 18

> x<-matrix(1:12, nrow=3, ncol=4, byrow= TRUE)

>x

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

[1,] 1 2 3 4
[2,] 5 6 7 8

[3,] 9 10 11 12

> y<-matrix(7:18, nrow=3, ncol=4, byrow= TRUE)

>y

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

[1,] 7 8 9 10

[2,] 11 12 13 14

[3,] 15 16 17 18

> z=x+y

>z

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

[1,] 8 10 12 14

[2,] 16 18 20 22

[3,] 24 26 28 30

> z=x*y

>z

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

[1,] 7 16 27 40

[2,] 55 72 91 112

[3,] 135 160 187 216

> d=x/y

>d

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

[1,] 0.1428571 0.250 0.3333333 0.4000000

[2,] 0.4545455 0.500 0.5384615 0.5714286

[3,] 0.6000000 0.625 0.6470588 0.6666667

> e=x-y

>e

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

[1,] -6 -6 -6 -6
[2,] -6 -6 -6 -6

[3,] -6 -6 -6 -6

> #data frames

> df <- [Link](Name=c("Alice", "Bob"),

+ Age=c(25,30),

+ Score=c(90.5,85))

> print(df)

Name Age Score

1 Alice 25 90.5

2 Bob 30 85.0

# Factor

> gender <- factor(c("Male", "Female", "Male", "Female"))

> gender

[1] Male Female Male Female

Levels: Female Male

> class(gender)

[1] "factor"

> # Arrays

> arr <- array(1:12, dim = c(3,2,2))

> arr

,,1

[,1] [,2]

[1,] 1 4

[2,] 2 5

[3,] 3 6

,,2

[,1] [,2]
[1,] 7 10

[2,] 8 11

[3,] 9 12

> # Type Checking & Type Conversion

> # Operators in R

> a <- 7.5

> b <- 2

> a+b #Addition

[1] 9.5

> a-b # Subtraction

[1] 5.5

> a*b #Multiplication

[1] 15

> a/b #Division

[1] 3.75

> a%%b #Reminder

[1] 1.5

> a%/%b #Quotient

[1] 3

> a^b #Exponent

[1] 56.25

> # Vectors Function (Collection of similar data types)

> c1 <- c(8,9,6)

> c2 <- c(2,4,5)

> c1 + c2

[1] 10 13 11

> c1 - c2

[1] 6 5 1

> c1 * c2

[1] 16 36 30
> c1 / c2

[1] 4.00 2.25 1.20

> c1 %% c2

[1] 0 1 1

> c1 %/% c2

[1] 4 2 1

> c1 ^ c2

[1] 64 6561 7776

> # Relational

>a

[1] 7.5

>b

[1] 2

> a<b

[1] FALSE

> a>b

[1] TRUE

> a==b

[1] FALSE

> a<=b

[1] FALSE

> a>=b

[1] TRUE

> a!=b

[1] TRUE

> c1

[1] 8 9 6

> c2

[1] 2 4 5

> c1<c2

[1] FALSE FALSE FALSE

[1] TRUE TRUE TRUE

> c1==c2

[1] FALSE FALSE FALSE

> c1<=c2

[1] FALSE FALSE FALSE

> c1>=c2

[1] TRUE TRUE TRUE

> c1!=c2

[1] TRUE TRUE TRUE

> # R if-else Statements

> x <- 25L

> if([Link](x)){

+ print("x is an integer number")

+}

[1] "x is an integer number"

> if([Link](x)){

+ print("x is an integer number")

+ }else{

+ print("x is not an integer number")

+}

[1] "x is an integer number"

> # R Switch Case

> # Switch (expression, case1, case2)

> x <- switch (2,

+ "Nilam",

+ "Parmar",

+ "John",

+ "Sunita"

+)

>x
[1] "Parmar"

> x <- switch (4,

+ "Nilam",

+ "Parmar",

+ "John",

+ "Sunita"

+)

>x

[1] "Sunita"

> #data manepulation

> ##merging and joining data

> # creating sample data frames

> df1 <- [Link](ID=c(1,2,3), Name=c("A","B","C"))

> df2<- [Link](ID=c(2,3,4), Score=c(85,90,78))

> #Inner Join

> df_inner <- merge(df1,df2,by="ID")

> View(df_inner)

> #left Join

> df_left <- merge(df1,df2, by="ID", all.x = TRUE) #NA fill for missing value

> View(df_left)
> #Right join

> df_right <- merge(df1,df2, by="ID", all.x = TRUE)

> View(df_right)

> #Full join

> df_full <- merge(df1,df2, by="ID", all = TRUE)

> View(df_full)

> # Importing Data Set

> # Exporting Data Set

> # CSV File

> library(readxl) # IMPORT

> Parth <- read_excel("C:/Users/parth/OneDrive/Desktop/SEM-4/PBAR/[Link]")

New names:

• `` -> `...25`

• `` -> `...29`

> View(Parth)

> library(writexl) # EXPORT

> age <- c(28, 34, 25, 42, 31, 38, 29)

> salary <- c(50000, 60000, 52000, 80000, 56000, 75000, 54000)

> department <-c("HR", "Finance", "Marketing", "IT", "HR", "Finance", "Marketing")

> experience <- c(3, 10, 2, 15, 5, 12, 4)

> df <- [Link](employee, age, salary, department, experience)

> df

employee age salary department experience

1 John 28 50000 HR 3

2 Emily 34 60000 Finance 10

3 Sophia 25 52000 Marketing 2

4 Michael 42 80000 IT 15

5 Sarah 31 56000 HR 5

6 David 38 75000 Finance 12

7 Anna 29 54000 Marketing 4

> # FOR CSV

> [Link](df, "employee_data.csv", [Link] = T)

> # FOR EXCEL

> write_xlsx(df, "employee_data.xlsx")

> # FOR JavaScript

> write_json(df, "employee_data.json", pretty = T)