Raghav Khemka 3B RMC

RMC FILE
INDEX
S.NO. Topic Page

No.
UNIT-1 Research design & Data Presentation
1 Basic commands for R studio
2 Variables and Data Types
3 Different types of operators
4 Simple programming Constructs such as -If, else
5 Simple programming Constructs such as -For, While, Break
6 User defined and Built-in functions
7 Lists
8 Vectors
9 Matrices
10 Arrays
UNIT-2 Data analysis using R
11 Data -Frames
12 Import from Spreadsheet
13 Data Exploration-
14 Summary statistics
15 Referring specific rows & columns
16 Quick-Plots
17 R-Notebook
UNIT-3 Graphical analysis of data
18 Histogram, Density plot, Whisker plots
19 Pie Charts, Cleveland dot Charts, Pair plots
20 Factor Data type
21 Date data type
UNIT-4 Statistical Tests
22 Correlation
23 t-test, two sample independent t -test , Paired t-test
24 Chi Square t test
25 Anova
26 Regression- Linear
27 Multiple Linear Regression
28 Logistics Regression
29 Step wise regression- Forward, Backward and Both
30 Tables- used :
 Input
 Cardata
 Sample data
 Pairedtestdata
P a g e 1 | 72
RMC FILE
 ANN2
 Twowayann
 Wtloss
P a g e 2 | 72
RMC FILE
ASSIGNMENT 1
BASIC COMMANDS FOR R STUDIO
Variables: A variable is a name for a value, such as x, current temperature, or subject.id. We can
create a new variable by assigning a value to it using assignment operator.
Assignment Operator: The use of these operators is to assign values to the variables. These are the
two kinds of assignments, leftwards and rightwards assignment.
Operators <- and = are used to assign variables.
ASSIGN VALUES TO VARIABLES, PASTE AND READLINE FUNCTIONS
> x <- 20
> x
[1] 20
>
> y
[1] 30
> z <- x + y
> z
[1] 50
> a <- "Hello"
> a
[1] "Hello"
> b <- "Kunal"
> b
[1] "Kunal"
> paste (a, b)
[1] "Hello Kunal"
> readline("what is your name?")
what is your name? Lakshay
[1] "Lakshay"
> urname <- readline("what is your name?")
what is your name? Kunal
P a g e 3 | 72
RMC FILE
> urname
[1] "Kunal"
> paste(a, urname)
[1] "Hello Kunal"
> m <- x+y+z
> m
[1] 100
> m <- x+y+z #Adding 3 numeric variables
> m <- x+y+z # Adding 3 numeric variables
> m # display value of m
[1] 100
> # "Good Night"
> "Good Morning!" # "Good night"
[1] "Good Morning!"
> c
P a g e 4 | 72
RMC FILE
ASSIGNMENT 2
VARIABLES AND DATA TYPES
age <- 5
age
# [1] 5
Age <- 10
Age
# [1] 10
x <-10
y <- 12.5
z <- 13L
class(z)
# [1] "integer"
class(x)
# [1] "numeric"
class(y)
# [1] "numeric"
urname <- "Hello"

class(urname)
# [1] "character"
name1 <- "12.5"

class(name1)
# [1] "character"
name2 <- "13.5"

name3 <- 14.5
name4 <- 15.5
m <- name3 + name4
m
# [1] 30
class(name3)
# [1] "numeric"
class(name2)
# [1] "character"
P a g e 5 | 72
RMC FILE
l <- "true"
l
# [1] "true"
class(l)
# [1] "character"
v <- TRUE
v
# [1] TRUE
class(v)
# [1] "logical"
str <- "R is lower case case sensative language. It is very good language.
It include"
str
# [1] "R is lower case case sensative language. It is very good language.
It include"
cat(str)
# R is lower case case sensative language. It is very good language. It

include
a <- "Hello!!! , How are you..,

+ i m fine."
a
# [1] "Hello!!! , How are you..,\n+ i m fine."
cat(a)
# Hello!!! , How are you..,

# + i m fine.
nchar(a)
# [1] 37
grepl("Hello",a)
# [1] TRUE
q <- "Hello"
w <-"How are you!!!!"
paste(q,w)
# [1] "Hello How are you!!!!"
P a g e 6 | 72
RMC FILE
## Builtin Math Function

max(5,10,15)
# [1] 15
min(5,10,15)
# [1] 5
sqrt(16)
# [1] 4
abs(-4.7)
# [1] 4.7
ceiling(1.4)
# [1] 2
floor(1.4)
# [1] 1
P a g e 7 | 72
RMC FILE
ASSIGNMENT 3
DIFFERENT TYPES OF OPERATORS
# Arithmatic Operators
> x <- 5
> y <- 2
> x
[1] 5
> y
[1] 2
> x <- 5
> y <- 2
> x
[1] 5
> y
[1] 2
> x+y
[1] 7
> x-y
[1] 3
> x*y
[1] 10
> x/y
[1] 2.5
> y^x
[1] 32
> x%%y
[1] 1
# Comparison operators
x
## [1] 5
P a g e 8 | 72
RMC FILE
## [1] 2
x == y
## [1] FALSE
x != y
## [1] TRUE
x > y
## [1] TRUE
x < y
## [1] FALSE
x >= y
## [1] TRUE
# Logical Operators
a <- 200
b <- 33
c <- 500
a
## [1] 200
## [1] 33
## [1] 500
# And operator (&)

z <- a >b & c>a
z
## [1] TRUE
z <- a >b & c<a

z
## [1] FALSE
# OR operator (|)
z <- a>b | a > c
z
## [1] TRUE
P a g e 9 | 72
RMC FILE
z <- a<b | a > c

z
## [1] FALSE
# Not operator (!)

x <- ! a >c
x
## [1] TRUE
x <- ! a < c
x
## [1] FALSE
P a g e 10 | 72
RMC FILE
ASSIGNMENT 4
IF CONSTRUCT AND NESTED IF
IF CONSTRUCT:
a <- 33
b <- 200
if (b>a){ print("b is greater than a")}
## [1] "b is greater than a"
a <- 33
b <- 33
if (b>a)
{print("b is greater than a")} else if (a==b)
{print("a and b are equal")}
## [1] "a and b are equal"
a <- 245
b <- 33
if (b > a)
{print("b is greater than a")} else if (a==b)
{print("a and b are equal")} else
{print("a is greater than b")}
## [1] "a is greater than b"
a <- 200
b <- 33
if (b > a)
{print("b is greater than a")} else
{print("b is not greater than a")}
## [1] "b is not greater than a"
NESTED IF:
myage <- readline("Enter your age")
## Enter your age
if(myage <18)
{print("You are not a major, u are not eligible to work")} else
{
if(myage >=18 & myage <=60) {
print("u are eligible to work, please fill application form and email
us")} else
P a g e 11 | 72
RMC FILE
{
print("As per govt rules, you are too old to work, please collect
your pension")
}}
## [1] "You are not a major, u are not eligible to work"
P a g e 12 | 72
RMC FILE
ASSIGNMENT 5
LOOP
While Loop:
i <- 1
while (i < 6) {
print(i)
i <- i + 1
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
i <- 1
while (i < 6) {
print(i)
i <- i + 1
if (i == 4) {
break
}
}
## [1] 1
## [1] 2
## [1] 3
i <- 0
while (i < 6) {
i <- i + 1
if (i == 3) {
next
}
print(i)
}
## [1] 1
## [1] 2
## [1] 4
## [1] 5
## [1] 6
dice <- 1
while (dice <= 6) {
if (dice < 6) {
print("No Yahtzee")
} else {
print("Yahtzee!")
}
P a g e 13 | 72
RMC FILE
dice <- dice + 1

}
## [1] "No Yahtzee"

## [1] "No Yahtzee"
## [1] "No Yahtzee"
## [1] "No Yahtzee"
## [1] "No Yahtzee"
## [1] "Yahtzee!"
For Loop:
for (x in 1:10) {
print(x)
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
## [1] 10
dice <- 1:6
for(x in dice) {
if (x == 6) {
print(paste("The dice number is", x, "Yahtzee!"))
} else {
print(paste("The dice number is", x, "Not Yahtzee"))
}
}
## [1] "The dice number is 1 Not Yahtzee"

## [1] "The dice number is 6 Yahtzee!"
P a g e 14 | 72
RMC FILE
ASSIGNMENT 6
USER DEFINED AND BUILT IN
BUILT IN FUNCTION:
> print(seq(32,44))
#[1] 32 33 34 35 36 37 38 39 40 41 42 43 44
> print(mean(25:82))
#[1] 53.5
> print(sum(41:68))
#[1] 1526
CALLING A FUNCTION:
new.function <- function(a) {
for(i in 1:a) {
b <- i^2
print(b)
}
}
new.function(6)
##new.function(6)
[1] 1
[1] 4
[1] 9
[1] 16
[1] 25
[1] 36
CALLING A FUNCTION WITHOUT AN ARGUMENT

new.function <- function() {
for(i in 1:5) {
print(i^2)
}
P a g e 15 | 72
RMC FILE
}
new.function()
## new.function()
[1] 1
[1] 4
[1] 9
[1] 16
[1] 25
CALLING A FUNCTION WITH ARGUMENT VALUES (BY POSITION

AND BY NAME)
new.function <- function(a,b,c) {

result <- a * b + c
print(result)
}
new.function(5,3,11)
new.function(a = 11, b = 5, c = 3)
# [1] 26
# [1] 58
CALLING A FUNCTION WITH DEFAULT ARGUMENT

new.function <- function(a = 3, b = 6) {
result <- a * b
print(result)
}
new.function()
new.function(9,5)
# [1] 18
# [1] 45
LAZY EVALUATION OF FUNCTION
new.function <- function(a, b) {
print(a^2)
print(a)
print(b)
P a g e 16 | 72
RMC FILE
new.function(6)
# [1] 36
# [1] 6
# Error in print(b) : argument "b" is missing, with no default
P a g e 17 | 72
RMC FILE
ASSIGNMENT 7
LISTS
LISTS OF STRING:
thislist <- list("apple", "banana", "cherry")
thislist
## [[1]]
## [1] "apple"
##
## [[2]]
## [1] "banana"
##
## [[3]]
## [1] "cherry"
thislist[1]
## [[1]]
## [1] "apple"
CHANGING VALUE OF SPECIFIC ITEM:

thislist[1] <- "blackcurrant"
thislist
## [[1]]
## [1] "blackcurrant"
##
## [[2]]
## [1] "banana"
##
## [[3]]
## [1] "cherry"
LENGHTH OF LISTS:
length(thislist)
## [1] 3
ADD ITEM AT THE END OF LIST:

append(thislist, "orange")
## [[1]]
## [1] "apple"
P a g e 18 | 72
RMC FILE
##
## [[2]]
## [1] "banana"
##
## [[3]]
## [1] "cherry"
##
## [[4]]
## [1] "orange"
TO ADD ITEM AFTER A SPECIFIED ITEM:

append(thislist, "orange", after = 2)
## [[1]]
## [1] "apple"
##
## [[2]]
## [1] "banana"
##
## [[3]]
## [1] "orange"
##
## [[4]]
## [1] "cherry"
REMOVING LIST ITEMS:

newlist <- thislist[-1]
newlist
## [[1]]
## [1] "banana"
##
## [[2]]
## [1] "cherry"
SPECIFYING RANGE OF INDEXES:

thislist <- list("apple", "banana", "cherry", "orange", "kiwi", "melon",
"mango")
(thislist)[2:5]
## [[1]]
## [1] "banana"
##
## [[2]]
## [1] "cherry"
##
## [[3]]
## [1] "orange"
P a g e 19 | 72
RMC FILE
##
## [[4]]
## [1] "kiwi"

for (x in thislist) {
print(x)
}
## [1] "apple"
## [1] "banana"
## [1] "cherry"
COMBINING LISTS:
list1 <- list("a", "b", "c")
list2 <- list(1,2,3)
list3 <- c(list1,list2)
list3
## [[1]]
## [1] "a"
##
## [[2]]
## [1] "b"
##
## [[3]]
## [1] "c"
##
## [[4]]
## [1] 1
##
## [[5]]
## [1] 2
##
## [[6]]
## [1] 3
P a g e 20 | 72
RMC FILE
ASSIGNMENT 8
VECTORS
VECTOR OF STRINGS:
fruits <- c("banana", "apple", "orange")
fruits
## [1] "banana" "apple” “orange"
numbers <- c(1, 2, 3)
numbers
## [1] 1 2 3
VECTOR WITH NUMERICAL VALUES WITH A SEQUENCE:

numbers <- 1:10
numbers
## [1] 1 2 3 4 5 6 7 8 9 10
numbers1 <- 1.5:6.5

numbers1
## [1] 1.5 2.5 3.5 4.5 5.5 6.5
numbers2 <- 1.5:6.3

numbers2
## [1] 1.5 2.5 3.5 4.5 5.5
VECTORS OF LOGICAL VALUES :

log_values <- c(TRUE, FALSE, TRUE, FALSE)
log_values
## [1] TRUE FALSE TRUE FALSE
TO FIND NO OF VECTORS:
fruits <- c("banana", "apple", "orange")
length(fruits)
## [1] 3
SORT OF VECTORS:
fruits <- c("banana", "apple", "orange", "mango", "lemon")
numbers <- c(13, 3, 5, 7, 20, 2)
sort(fruits)
## [1] "apple" "banana" "lemon" "mango" "orange"
P a g e 21 | 72
RMC FILE
sort(numbers)
## [1] 2 3 5 7 13 20
ACESSING VECTORS:
fruits[1]
## [1] "banana"
fruits[c(1, 3)]
## [1] "banana" "orange"

fruits[c(-1)]
## [1] "apple" "orange" "mango" "lemon"
fruits[1] <- "pear"
fruits
## [1] "pear" "apple" "orange" "mango" "lemon"
P a g e 22 | 72
RMC FILE
ASSIGNMENT 9
MATRICES
CREATING A MATRIX:
thismatrix <- matrix(c(1,2,3,4,5,6), nrow = 3, ncol = 2)
thismatrix
## [,1] [,2]
## [1,] 1 4
## [2,] 2 5
## [3,] 3 6
CREATING A MATRIX WITH STRING:

thismatrix <- matrix(c("apple", "banana", "cherry", "orange"), nrow = 2,
ncol = 2)
thismatrix
## [,1] [,2]
## [1,] "apple" "cherry"
## [2,] "banana" "orange"
ACESSING THE ITEMS:

ncol = 2)
thismatrix[1, 2]
## [1] "cherry"

ncol = 2)
thismatrix[2,]
## [1] "banana" "orange"

ncol = 2)
thismatrix[,2]
## [1] "cherry" "orange"
thismatrix <- matrix(c("apple", "banana", "cherry", "orange","grape",

"pineapple", "pear", "melon", "fig"), nrow = 3, ncol = 3)
thismatrix[c(1,2),]
## [,1] [,2] [,3]

## [1,] "apple" "orange" "pear"
## [2,] "banana" "grape" "melon"
P a g e 23 | 72
RMC FILE

thismatrix[, c(1,2)]
## [,1] [,2]
## [1,] "apple" "orange"
## [2,] "banana" "grape"
## [3,] "cherry" "pineapple"
ADD ROWS AND COLUMNS:

C-BIND:

newmatrix <- cbind(thismatrix, c("strawberry", "blueberry",
"raspberry"))newmatrix
## [,1] [,2] [,3] [,4]

## [1,] "apple" "orange" "pear" "strawberry"
## [2,] "banana" "grape" "melon" "blueberry"
## [3,] "cherry" "pineapple" "fig" "raspberry"
R-BIND:

newmatrix <- rbind(thismatrix, c("strawberry", "blueberry",
"raspberry"))enewwmatrix
## [,1] [,2] [,3]

## [1,] "apple" "orange" "pear"
## [2,] "banana" "grape" "melon"
## [3,] "cherry" "pineapple" "fig"
## [4,] "strawberry" "blueberry" "raspberry"
REMOVING ROWS AND COLUMNS:

thismatrix <- matrix(c("apple", "banana", "cherry", "orange", "mango",
"pineapple"), nrow = 3, ncol =2)
thismatrix <- thismatrix[-c(1), -c(1)]

thismatrix
## [1] "mango" "pineapple"
CHECKING SPECIFIED ITEMS:

ncol = 2)
ncol = 2)
dim(thismatrix)
## [1] 2 2
P a g e 24 | 72
RMC FILE

ncol = 2)
length(thismatrix)
## [1] 4
COMBINING MATRICES:
Matrix1 <- matrix(c("apple", "banana", "cherry", "grape"), nrow = 2, ncol
= 2)
Matrix2 <- matrix(c("orange", "mango", "pineapple", "watermelon"), nrow =
2, ncol = 2)
Matrix_Combined <- rbind(Matrix1, Matrix2)
Matrix_Combined
## [,1] [,2]
## [1,] "apple" "cherry"
## [2,] "banana" "grape"
## [3,] "orange" "pineapple"
## [4,] "mango" "watermelon"
Matrix_Combined <- cbind(Matrix1, Matrix2)

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

## [1,] "apple" "cherry" "orange" "pineapple"
## [2,] "banana" "grape" "mango" "watermelon"
P a g e 25 | 72
RMC FILE
P a g e 26 | 72
RMC FILE
ASSIGNMENT 10
ARRAYS
ARRAY WITH ONE DIMENSION:
thisarray <- c(1:24)
thisarray
## [1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22
23 24
ARRAY WITH ONE OR MORE DIMENSION:

multiarray <- array(thisarray, dim = c(4, 3, 2))
multiarray
## , , 1
##
## [,1] [,2] [,3]
## [1,] 1 5 9
## [2,] 2 6 10
## [3,] 3 7 11
## [4,] 4 8 12
##
## , , 2
##
## [,1] [,2] [,3]
## [1,] 13 17 21
## [2,] 14 18 22
## [3,] 15 19 23
## [4,] 16 20 24
ACCESSING ELEMENTS IN ARRAYS:

multiarray[2, 3, 2]
## [1] 22

multiarray[c(1),,1]
## [1] 1 5 9

multiarray[,c(1),1]
## [1] 1 2 3 4
TO FIND IF A ELEMENT IS PRESENT:
P a g e 27 | 72
RMC FILE

2 %in% multiarray
## [1] TRUE
NUMBER OF ROWS AND COLUMNS:

dim(multiarray)
## [1] 4 3 2
DIMENSION OF ARRAY:
length(multiarray)
## [1] 24
LOOP THROUGH AN ARRAY:

for(x in multiarray){
print(x)
}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
## [1] 10
## [1] 11
## [1] 12
## [1] 13
## [1] 14
## [1] 15
## [1] 16
## [1] 17
## [1] 18
## [1] 19
## [1] 20
## [1] 21
## [1] 22
P a g e 28 | 72
RMC FILE
## [1] 23
## [1] 24
P a g e 29 | 72
RMC FILE
ASSIGNMENT 11
DATA FRAMES
CREATING DATA FRAME:
Data_Frame <- data.frame (
Training = c("Strength", "Stamina", "Other"),
Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
Data_Frame
## Training Pulse Duration

## 1 Strength 100 60
## 2 Stamina 150 30
## 3 Other 120 45
SUMMARIZE DATA FRAME:

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
Data_Frame
summary(Data_Frame)

## Length:3 Min. :100.0 Min. :30.0
## Class :character 1st Qu.:110.0 1st Qu.:37.5
## Mode :character Median :120.0 Median :45.0
## Mean :123.3 Mean :45.0
## 3rd Qu.:135.0 3rd Qu.:52.5
## Max. :150.0 Max. :60.0
ACCESSING COLUMS FROM DATA FRAME:

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
Data_Frame[1]
Data_Frame[["Training"]]
Data_Frame$Training
## Training
## 1 Strength
P a g e 30 | 72
RMC FILE
## 2 Stamina
## 3 Other
## [1] "Strength" "Stamina" "Other"
## [1] "Strength" "Stamina" "Other"
ADDING ROWS :

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
New_row_DF <- rbind(Data_Frame, c("Strength", 110, 110))
New_row_DF

## 2 Stamina 150 30
## 3 Other 120 45
## 4 Strength 110 110
ADD NEW COLUMNS:

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
New_col_DF <- cbind(Data_Frame, Steps = c(1000, 6000, 2000))
New_col_DF
## Training Pulse Duration Steps
## 1 Strength 100 60 1000
## 2 Stamina 150 30 6000
## 3 Other 120 45 2000
REMOVING ROWS AND COLUMNS:

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
Data_Frame_New <- Data_Frame[-c(1), -c(1)]
Data_Frame_New
## Pulse Duration
## 2 150 30
## 3 120 45
NUMBER OF ROWS AND COLUMNS:
P a g e 31 | 72
RMC FILE

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
dim(Data_Frame)
## [1] 3 3

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
ncol(Data_Frame)
## [1] 3
nrow(Data_Frame)
## [1] 3

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
length(Data_Frame)
## [1] 3
COMBINING TWO OR MORE DATA FRAMES:
R-BIND:
Data_Frame1 <- data.frame (

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
Training = c("Stamina", "Stamina", "Strength"),
Pulse = c(140, 150, 160),
Duration = c(30, 30, 20)
)
New_Data_Frame <- rbind(Data_Frame1, Data_Frame2)
New_Data_Frame

## 2 Stamina 150 30
## 3 Other 120 45
## 4 Stamina 140 30
P a g e 32 | 72
RMC FILE
## 5 Stamina 150 30
C-BIND:

Pulse = c(100, 150, 120),
Duration = c(60, 30, 45)
)
Steps = c(3000, 6000, 2000),
Calories = c(300, 400, 300)
)
New_Data_Frame1 <- cbind(Data_Frame3, Data_Frame4)
New_Data_Frame1
## Training Pulse Duration Steps Calories

## 1 Strength 100 60 3000 300
## 2 Stamina 150 30 6000 400
## 3 Other 120 45 2000 300
P a g e 33 | 72
RMC FILE
ASSIGNMENT 12
IMPORTING EXCEL FILE
STEP 1: First go to packages on the lower right column and install xlsx
package.
STEP 2: Create a excel file and import it via import data set.
Your excel file is imported.
P a g e 34 | 72
RMC FILE
ASSIGNMENT 13
DATA EXPLORATION
install.packages("xlsx")
any(grepl("xlsx",installed.packages()))
library(readxl)
INPUT <- read_excel("INPUT.XLSX")
print(INPUT)
class(INPUT)
head(INPUT)
tail(INPUT)
head(INPUT,3)
tail(INPUT,3)
names(INPUT)
dim(INPUT)
ncol(INPUT)
nrow(INPUT)
#class(INPUT)
[1] "tbl_df" "tbl" "data.frame"
# head(INPUT)
# A tibble: 6 × 4
ID NAME SALARY DEPT
<dbl> <chr> <dbl> <chr>
1 1 Rick 45000 IT
2 2 Dan 78000 Finance
3 3 Michel 45000 HR
4 4 Ryan 89000 Operations
5 5 Gary 48000 Finance
6 6 Nina 92000 IT
# tail(INPUT)
# A tibble: 6 × 4
ID NAME SALARY DEPT
1 3 Michel 45000 HR
2 4 Ryan 89000 Operations
3 5 Gary 48000 Finance
4 6 Nina 92000 IT
5 7 Simon 65000 Operations
6 8 Guru 65000 HR
# head(INPUT,3)
# A tibble: 3 × 4
ID NAME SALARY DEPT
1 1 Rick 45000 IT
2 2 Dan 78000 Finance
P a g e 35 | 72
RMC FILE
3 3 Michel 45000 HR
# tail(INPUT,3)
# A tibble: 3 × 4
ID NAME SALARY DEPT
1 6 Nina 92000 IT
2 7 Simon 65000 Operations
3 8 Guru 65000 HR
# names(INPUT)
[1] "ID" "NAME" "SALARY" "DEPT"
# dim(INPUT)
[1] 8 4
# ncol(INPUT)
[1] 4
# nrow(INPUT)
[1] 8
P a g e 36 | 72
RMC FILE
ASSIGNMENT 14
SUMMARY STATISTICS
str(INPUT)
summary(INPUT)
# str(INPUT)
tibble [8 × 4] (S3: tbl_df/tbl/data.frame)
$ ID : num [1:8] 1 2 3 4 5 6 7 8
$ NAME : chr [1:8] "Rick" "Dan" "Michel" "Ryan" ...
$ SALARY: num [1:8] 45000 78000 45000 89000 48000 92000 65000 65000
$ DEPT : chr [1:8] "IT" "Finance" "HR" "Operations" ...
# summary(INPUT)
ID NAME SALARY DEPT
Min. :1.00 Length:8 Min. :45000 Length:8
1st Qu.:2.75 Class :character 1st Qu.:47250 Class :character
Median :4.50 Mode :character Median :65000 Mode :character
Mean :4.50 Mean :65875
3rd Qu.:6.25 3rd Qu.:80750
Max. :8.00 Max. :92000
P a g e 37 | 72
RMC FILE
ASSIGNMENT 15
REFERRING SPECIFIC ROWS AND COLUMNS
summary(INPUT[,3])
summary(INPUT[,2:3])
summary(INPUT[,c(2,4)])
min(INPUT$SALARY)
max(INPUT$SALARY)
mean(INPUT$SALARY)
median(INPUT$SALARY)
var(INPUT$SALARY)
sd(INPUT$SALARY)
quantile(INPUT$SALARY,0.25)
# summary(INPUT[,3])
SALARY
Min. :45000
1st Qu.:47250
Median :65000
Mean :65875
3rd Qu.:80750
Max. :92000
# summary(INPUT[,2:3])
NAME SALARY
Length:8 Min. :45000
Class :character 1st Qu.:47250
Mode :character Median :65000
Mean :65875
3rd Qu.:80750
Max. :92000
# summary(INPUT[,c(2,4)])
NAME DEPT
Length:8 Length:8
Class :character Class :character
Mode :character Mode :character
# min(INPUT$SALARY)
[1] 45000
# max(INPUT$SALARY)
[1] 92000
P a g e 38 | 72
RMC FILE
# mean(INPUT$SALARY)
[1] 65875
# median(INPUT$SALARY)
[1] 65000
# var(INPUT$SALARY)
[1] 365267857
# sd(INPUT$SALARY)
[1] 19111.98
# quantile(INPUT$SALARY,0.25)
25%
47250
50%
65000
75%
80750
P a g e 39 | 72
RMC FILE
ASSIGNMENT 16
QUICK PLOTS
STEP 1: First go on the lower right-side window and click on install, and install
GGally and ggplot2. When installed it will be this.
STEP 2: Now according to the file, create a qplot or quick plot. After creating a
new r script, qplot would look like this.
P a g e 40 | 72
RMC FILE
P a g e 41 | 72
RMC FILE
ASSIGNMENT 18
HISTOGRAM, DENSITY PLOT, WHISKER PLOT
BOX PLOT:
HISTOGRAM:
P a g e 42 | 72
RMC FILE
SCATTER PLOT:
P a g e 43 | 72
RMC FILE
DENSITY PLOT:
P a g e 44 | 72
RMC FILE
ASSIGNMENT 19
PIE CHARTS, CLEVELAND DOT CHARTS, PAIR PLOTS
PIE CHARTS:
PAIR PLOTS:
P a g e 45 | 72
RMC FILE
CLEVELAND DOT CHART:
P a g e 46 | 72
RMC FILE
ASSIGNMENT 20
FACTOR DATA TYPE
CREATING A VECTOR:
apple_colors <- c('green','green','yellow','red','red','red','green')
class(apple_colors)
# [1] "character"
CREATING FACTOR OBJECT:

factor_apple <- factor(apple_colors)
print(factor_apple)
print(nlevels(factor_apple))
# [1] green green yellow red red red green

# Levels: green red yellow
# [1] 3
EXAMPLE:
gender <- factor(c("female", "female", "male", "female", "male"))
gender
levels(gender)
# [1] female female male female male

# Levels: female male
## [1] "female" "male"
text <- c("test1", "test2", "test1", "test1") # create a character vector

class(text)
text_factor <- factor(text)
class(text_factor)
# [1] "character"
# [1] "factor"
day_vector <- c('evening', 'morning', 'afternoon', 'midday', 'midnight',

'evening')
factor_day <- factor(day_vector, order = TRUE, levels =c('morning',
'midday', 'afternoon', 'evening', 'midnight'))
factor_day
# [1] evening morning afternoon midday midnight evening

# Levels: morning < midday < afternoon < evening < midnight
P a g e 47 | 72
RMC FILE
P a g e 48 | 72
RMC FILE
ASSIGNMENT 21
DATE DATA TYPE
today <- Sys.Date()

date()
# [1] "Mon Dec 5 11:56:02 2022"
format(Sys.Date(), format = "%d %B, %Y")

format(Sys.Date(), format = "Today is a %A!")
## [1] "21 November, 2022"
## [1] "Today is a Monday!"
CONVERTING STRING TO DATES:

strDates <- c("01/05/1965","08/16/1975")
dates <- as.Date(strDates, "%m/%d/%Y")
strDates <- as.character(dates)
P a g e 49 | 72
RMC FILE
ASSIGNMENT 22
CORRELATION
PEARSON CORRELATION:
res <- cor.test(cardata$wt, cardata$mpg, method = "pearson")
res
Pearson's product-moment correlation
data: cardata$wt and cardata$mpg

t = -9.559, df = 30, p-value = 1.294e-10
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
-0.9338264 -0.7440872
sample estimates:
cor
-0.8676594
KENDALL CORRELATION:
res1 <- cor.test(cardata$wt, cardata$mpg, method = "kendall")

res1
Kendall's rank correlation tau

z = -5.7981, p-value = 6.706e-09
alternative hypothesis: true tau is not equal to 0
sample estimates:
tau
-0.7278321
SPEARMAN CORRELATION:
res2 <- cor.test(cardata$wt, cardata$mpg, method = "spearman")

res2
Spearman's rank correlation rho

S = 10292, p-value = 1.488e-11
alternative hypothesis: true rho is not equal to 0
sample estimates:
rho
-0.886422
P a g e 50 | 72
RMC FILE
ASSIGNMENT 23
T-TEST, TWO SAMPLE INDEPENDENT T-TEST, PAIRED TEST
ONE SAMPLE T-TEST:

res <- t.test(sample_data$HEIGHT, mu = 65)
res
#One Sample t-test
data: sample_data$HEIGHT
t = -3.8005, df = 19, p-value =
0.001208
alternative hypothesis: true mean is not equal to 65
57.16883 62.73117
sample estimates:
mean of x
59.95
PAIRED T TEST:
t.test(pairedttestdata$Before,pairedttestdata$After, paired = TRUE,

alternative = "two.sided")
#Paired t-test
data: pairedttestdata$Before and pairedttestdata$After

t = -20.804, df = 9, p-value =
6.411e-09
alternative hypothesis: true mean difference is not equal to 0
-215.7375 -173.4225
sample estimates:
mean difference
-194.58
TWO SAMPLE INDEPENDENT T-TEST
t.test(sample_data$HEIGHT~sample_data$GENDER)
#Welch Two Sample t-test
data: sample_data$HEIGHT by sample_data$GENDER

t = -3.956, df = 11.223, p-value = 0.002165
P a g e 51 | 72
RMC FILE
alternative hypothesis: true difference in means between group FEMALE and

group MALE is not equal to 0
-12.284618 -3.515382
sample estimates:
mean in group FEMALE mean in group MALE
56.0 63.9
P a g e 52 | 72
RMC FILE
ASSIGNMENT 24
CHI SQUARE T TEST
table(cardata$am,cardata$cyl)
chisq.test(table(cardata$am,cardata$cyl))
chisq.test(cardata$am,cardata$cyl)
## table(cardata$am,cardata$cyl)
4 6 8
0 3 4 12
1 8 3 2
## chisq.test(table(cardata$am,cardata$cyl))
Pearson's Chi-squared test
data: table(cardata$am, cardata$cyl)

X-squared = 8.7407, df = 2, p-value =
0.01265
## chisq.test(cardata$am,cardata$cyl)
Pearson's Chi-squared test
data: cardata$am and cardata$cyl

X-squared = 8.7407, df = 2, p-value =
0.01265
P a g e 53 | 72
RMC FILE
ASSIGNMENT 25
ANOVA
ONE WAY ANOVA TEST:
summary(aov(wtloss$grps~wtloss$df_wt))
## library(readxl)
> wtloss <- read_excel("D:/Lakshay/Bcom/RMC/wtloss.xlsx")
> View(wtloss)
> summary(aov(wtloss$grps~wtloss$df_wt))
Df Sum Sq Mean Sq F value
wtloss$df_wt 1 12.27 12.273 17.36
Residuals 18 12.73 0.707
Pr(>F)
wtloss$df_wt 0.00058 ***
Residuals
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1
TWO WAY ANOVA TEST:

table(ANN2$supp, ANN2$dose)
res.aov2 <- aov(len ~ supp + dose, data = ANN2)
summary(res.aov2)
## library(readxl)
> ANN2 <- read_excel("D:/Lakshay/Bcom/RMC/ANN2.xlsx")
> View(ANN2)
> table(ANN2$supp, ANN2$dose)
0.5 1 2
OJ 3 1 3
VC 1 1 1
> res.aov2 <- aov(len ~ supp + dose, data = ANN2)
> summary(res.aov2)
supp 1 38.7 38.7 1.506
dose 1 690.5 690.5 26.910
Residuals 7 179.6 25.7
Pr(>F)
supp 0.25935
dose 0.00127 **
Residuals
---
P a g e 54 | 72
RMC FILE
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1
EXAMPLE 2:
res.aov2 <- aov(plant_height ~ Watering_freq + sunlight_exp, data =
twowayann)
summary(res.aov2)
## library(readxl)
> twowayann <- read_excel("D:/Lakshay/Bcom/RMC/twowayann.xlsx")
> View(twowayann)
> res.aov2 <- aov(plant_height ~ Watering_freq + sunlight_exp, data =
twowayann)
> summary(res.aov2)
Watering_freq 2 1.281 0.6405 1.694
sunlight_exp 3 7.028 2.3427 6.198
Residuals 4 1.512 0.3780
Pr(>F)
Watering_freq 0.2931
sunlight_exp 0.0552 .
Residuals
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1
P a g e 55 | 72
RMC FILE
ASSIGNMENT 26
REGRESSION-LINEAR
x <- c(153, 169, 140, 186, 128,

136, 178, 163, 152, 133)
y <- c(64, 81, 58, 91, 47, 57,
75, 72, 62, 49)
model <- lm(y~x)
print(model)
## print(model)
Call:
lm(formula = y ~ x)
Coefficients:
(Intercept) x
-39.7137 0.6847
EXAMPLE 2:
df <- data.frame(x = 182)

res <- predict(model, df)
cat("\nPredicted value of a person
with height = 182")
print(res)
## Predicted value of a person

with height = 182> print(res)
1
84.9098
PLOT:
P a g e 56 | 72
RMC FILE
ASSIGNMENT 27
MULTIPLE LINEAR AGGRESSION
input <- airquality[1:50,

c("Ozone","Wind","Temp")]
input
## input
Ozone Wind Temp
1 41 7.4 67
2 36 8.0 72
3 12 12.6 74
4 18 11.5 62
5 NA 14.3 56
6 28 14.9 66
7 23 8.6 65
8 19 13.8 59
9 8 20.1 61
10 NA 8.6 69
11 7 6.9 74
12 16 9.7 69
13 11 9.2 66
14 14 10.9 68
15 18 13.2 58
16 14 11.5 64
17 34 12.0 66
18 6 18.4 57
19 30 11.5 68
20 11 9.7 62
21 1 9.7 59
22 11 16.6 73
23 4 9.7 61
24 32 12.0 61
25 NA 16.6 57
26 NA 14.9 58
27 NA 8.0 57
28 23 12.0 67
29 45 14.9 81
30 115 5.7 79
31 37 7.4 76
32 NA 8.6 78
33 NA 9.7 74
34 NA 16.1 67
35 NA 9.2 84
36 NA 8.6 85
37 NA 14.3 79
38 29 9.7 82
39 NA 6.9 87
40 71 13.8 90
P a g e 57 | 72
RMC FILE
41 39 11.5 87
42 NA 10.9 93
43 NA 9.2 92
44 23 8.0 82
45 NA 13.8 80
46 NA 11.5 79
47 21 14.9 77
48 37 20.7 72
49 20 9.2 65
50 12 11.5 73
CREATE REGRESSION MODEL:
model <- lm(Ozone~Wind + Temp,

data = input)
print(model)
## print(model)
Call:
lm(formula = Ozone ~ Wind + Temp, data = input)
Coefficients:
(Intercept) Wind Temp
-58.239 -0.739 1.329
P a g e 58 | 72
RMC FILE
ASSIGNMENT 28
LOGISTICS REGRESSION
input <- cardata[,c("am","cyl","hp","wt")]

data1 = glm(formula = am ~ cyl + hp + wt, data = input, family =
binomial)
print(summary(data1))
## print(summary(data1))
Call:
glm(formula = am ~ cyl + hp + wt, family = binomial, data = input)
Deviance Residuals:
Min 1Q Median 3Q
-2.17272 -0.14907 -0.01464 0.14116
Max
1.27641
Coefficients:
Estimate Std. Error z value
(Intercept) 19.70288 8.11637 2.428
cyl 0.48760 1.07162 0.455
hp 0.03259 0.01886 1.728
wt -9.14947 4.15332 -2.203
Pr(>|z|)
(Intercept) 0.0152 *
cyl 0.6491
hp 0.0840 .
wt 0.0276 *
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1
(Dispersion parameter for binomial family taken to be 1)
Null deviance: 43.2297 on 31 degrees of freedom

Residual deviance: 9.8415 on 28 degrees of freedom
AIC: 17.841
Number of Fisher Scoring iterations: 8
P a g e 59 | 72
RMC FILE
ASSIGNMENT 29
STEPWISE REGRESSION
xl <- lm(mpg ~ 1, data = cardata)

x2 <- lm(mpg~cyl+disp+hp+drat+wt+qsec+vs+am+gear+carb, data = cardata)
summary(x2)
## summary(x2)
Call:
lm(formula = mpg ~ cyl + disp + hp + drat + wt + qsec + vs +
am + gear + carb, data = cardata)
Residuals:
Min 1Q Median 3Q Max
-3.4506 -1.6044 -0.1196 1.2193 4.6271
Coefficients:
Estimate Std. Error t value
(Intercept) 12.30337 18.71788 0.657
cyl -0.11144 1.04502 -0.107
disp 0.01334 0.01786 0.747
hp -0.02148 0.02177 -0.987
drat 0.78711 1.63537 0.481
wt -3.71530 1.89441 -1.961
qsec 0.82104 0.73084 1.123
vs 0.31776 2.10451 0.151
am 2.52023 2.05665 1.225
gear 0.65541 1.49326 0.439
carb -0.19942 0.82875 -0.241
Pr(>|t|)
(Intercept) 0.5181
cyl 0.9161
disp 0.4635
hp 0.3350
drat 0.6353
wt 0.0633 .
qsec 0.2739
vs 0.8814
am 0.2340
gear 0.6652
carb 0.8122
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1
Residual standard error: 2.65 on 21 degrees of freedom

Multiple R-squared: 0.869, Adjusted R-squared: 0.8066
P a g e 60 | 72
RMC FILE
F-statistic: 13.93 on 10 and 21 DF, p-value: 3.793e-07
FORWARD STEP WISE
forwardnew <- step(xl, scope = list(lower=xl,

upper=x2),direction="forward")
forwardnew$anova
summary(forwardnew)
forwardnew$coefficients
## summary(forwardnew)
Call:
lm(formula = mpg ~ wt + cyl + hp, data = cardata)
Residuals:
-3.9290 -1.5598 -0.5311 1.1850 5.8986
Coefficients:
(Intercept) 38.75179 1.78686 21.687
wt -3.16697 0.74058 -4.276
cyl -0.94162 0.55092 -1.709
hp -0.01804 0.01188 -1.519
Pr(>|t|)
(Intercept) < 2e-16 ***
wt 0.000199 ***
cyl 0.098480 .
hp 0.140015
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1

## forwardnew$coefficients
(Intercept) wt cyl
38.7517874 -3.1669731 -0.9416168
hp
-0.0180381
BACKWARD STEP WISE
backwardnew <- step(x2,direction = "backward")

backwardnew$anova
summary(backwardnew)
backwardnew$coefficients
P a g e 61 | 72
RMC FILE
## summary(backwardnew)
Call:
lm(formula = mpg ~ wt + qsec + am, data = cardata)
Residuals:
-3.4811 -1.5555 -0.7257 1.4110 4.6610
Coefficients:
(Intercept) 9.6178 6.9596 1.382
wt -3.9165 0.7112 -5.507
qsec 1.2259 0.2887 4.247
am 2.9358 1.4109 2.081
Pr(>|t|)
(Intercept) 0.177915
wt 6.95e-06 ***
qsec 0.000216 ***
am 0.046716 *
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1

## backwardnew$coefficients
(Intercept) wt qsec
9.617781 -3.916504 1.225886
am
2.935837
BOTH STEP WISE:
bothnew <- step(x2,direction = "both")

bothnew$anova
bothnew$coefficients
summary(bothnew)
## bothnew <- step(x2,direction = "both")

Start: AIC=70.9
mpg ~ cyl + disp + hp + drat + wt + qsec + vs + am + gear + carb
Df Sum of Sq RSS AIC

- cyl 1 0.0799 147.57 68.915
- vs 1 0.1601 147.66 68.932
- carb 1 0.4067 147.90 68.986
P a g e 62 | 72
RMC FILE
- gear 1 1.3531 148.85 69.190

- drat 1 1.6270 149.12 69.249
- disp 1 3.9167 151.41 69.736
- hp 1 6.8399 154.33 70.348
- qsec 1 8.8641 156.36 70.765
<none> 147.49 70.898
- am 1 10.5467 158.04 71.108
- wt 1 27.0144 174.51 74.280
Step: AIC=68.92
mpg ~ disp + hp + drat + wt + qsec + vs + am + gear + carb

- vs 1 0.2685 147.84 66.973
- carb 1 0.5201 148.09 67.028
- gear 1 1.8211 149.40 67.308
- drat 1 1.9826 149.56 67.342
- disp 1 3.9009 151.47 67.750
- hp 1 7.3632 154.94 68.473
<none> 147.57 68.915
- qsec 1 10.0933 157.67 69.032
- am 1 11.8359 159.41 69.384
+ cyl 1 0.0799 147.49 70.898
- wt 1 27.0280 174.60 72.297
Step: AIC=66.97
mpg ~ disp + hp + drat + wt + qsec + am + gear + carb

- carb 1 0.6855 148.53 65.121
- gear 1 2.1437 149.99 65.434
- drat 1 2.2139 150.06 65.449
- disp 1 3.6467 151.49 65.753
- hp 1 7.1060 154.95 66.475
<none> 147.84 66.973
- am 1 11.5694 159.41 67.384
- qsec 1 15.6830 163.53 68.200
+ vs 1 0.2685 147.57 68.915
+ cyl 1 0.1883 147.66 68.932
- wt 1 27.3799 175.22 70.410
Step: AIC=65.12
mpg ~ disp + hp + drat + wt + qsec + am + gear

- gear 1 1.565 150.09 63.457
- drat 1 1.932 150.46 63.535
<none> 148.53 65.121
- disp 1 10.110 158.64 65.229
- am 1 12.323 160.85 65.672
- hp 1 14.826 163.35 66.166
+ carb 1 0.685 147.84 66.973
P a g e 63 | 72
RMC FILE
+ vs 1 0.434 148.09 67.028

+ cyl 1 0.414 148.11 67.032
- qsec 1 26.408 174.94 68.358
- wt 1 69.127 217.66 75.350
Step: AIC=63.46
mpg ~ disp + hp + drat + wt + qsec + am

- drat 1 3.345 153.44 62.162
- disp 1 8.545 158.64 63.229
<none> 150.09 63.457
- hp 1 13.285 163.38 64.171
+ gear 1 1.565 148.53 65.121
+ cyl 1 1.003 149.09 65.242
+ vs 1 0.645 149.45 65.319
+ carb 1 0.107 149.99 65.434
- am 1 20.036 170.13 65.466
- qsec 1 25.574 175.67 66.491
- wt 1 67.572 217.66 73.351
Step: AIC=62.16
mpg ~ disp + hp + wt + qsec + am

- disp 1 6.629 160.07 61.515
<none> 153.44 62.162
- hp 1 12.572 166.01 62.682
+ drat 1 3.345 150.09 63.457
+ gear 1 2.977 150.46 63.535
+ cyl 1 2.447 150.99 63.648
+ vs 1 1.121 152.32 63.927
+ carb 1 0.011 153.43 64.160
- qsec 1 26.470 179.91 65.255
- am 1 32.198 185.63 66.258
- wt 1 69.043 222.48 72.051
Step: AIC=61.52
mpg ~ hp + wt + qsec + am

- hp 1 9.219 169.29 61.307
<none> 160.07 61.515
+ disp 1 6.629 153.44 62.162
+ carb 1 3.227 156.84 62.864
+ drat 1 1.428 158.64 63.229
- qsec 1 20.225 180.29 63.323
+ cyl 1 0.249 159.82 63.465
+ vs 1 0.249 159.82 63.466
+ gear 1 0.171 159.90 63.481
- am 1 25.993 186.06 64.331
- wt 1 78.494 238.56 72.284
P a g e 64 | 72
RMC FILE
Step: AIC=61.31
mpg ~ wt + qsec + am

<none> 169.29 61.307
+ hp 1 9.219 160.07 61.515
+ carb 1 8.036 161.25 61.751
+ disp 1 3.276 166.01 62.682
+ cyl 1 1.501 167.78 63.022
+ drat 1 1.400 167.89 63.042
+ gear 1 0.123 169.16 63.284
+ vs 1 0.000 169.29 63.307
- am 1 26.178 195.46 63.908
- qsec 1 109.034 278.32 75.217
- wt 1 183.347 352.63 82.790
## bothnew$anova
Step Df Deviance Resid. Df Resid. Dev
1 NA NA 21 147.4944
2 - cyl 1 0.07987121 22 147.5743
3 - vs 1 0.26852280 23 147.8428
4 - carb 1 0.68546077 24 148.5283
5 - gear 1 1.56497053 25 150.0933
6 - drat 1 3.34455117 26 153.4378
7 - disp 1 6.62865369 27 160.0665
8 - hp 1 9.21946935 28 169.2859
AIC
1 70.89774
2 68.91507
3 66.97324
4 65.12126
5 63.45667
6 62.16190
7 61.51530
8 61.30730
## bothnew$coefficients
(Intercept) wt qsec
9.617781 -3.916504 1.225886
am
2.935837
## summary(bothnew)
Call:
lm(formula = mpg ~ wt + qsec + am, data = cardata)
Residuals:
-3.4811 -1.5555 -0.7257 1.4110 4.6610
P a g e 65 | 72
RMC FILE
Coefficients:
(Intercept) 9.6178 6.9596 1.382
wt -3.9165 0.7112 -5.507
qsec 1.2259 0.2887 4.247
am 2.9358 1.4109 2.081
Pr(>|t|)
(Intercept) 0.177915
wt 6.95e-06 ***
qsec 0.000216 ***
am 0.046716 *
---
Signif. codes:
0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’
0.1 ‘ ’ 1

P a g e 66 | 72
RMC FILE
ASSIGNMENT 30
TABLES USED
INPUT TABLE:
CARDATA TABLE:
P a g e 67 | 72
RMC FILE
SAMPLE DATA TABLE:
PAIRED T TEST:
ANN2 TABLE:
P a g e 68 | 72
RMC FILE
TWOWAYANN:
WTLOSS:
P a g e 69 | 72
RMC FILE
P a g e 70 | 72
RMC FILE
ASSIGNMENT 17
R Notebook
summary(INPUT[,3])
summary(INPUT[,2:3])
quantile(INPUT SALARY ,0.25 ¿ quantile ¿SALARY,0.50) quantile(INPUT$SALARY,0.75)

SALARY
Min. :45000
1st Qu.:47250
Median :65000
Mean :65875
3rd Qu.:80750
Max. :92000
NAME SALARY
Length:8 Min. :45000
Class :character 1st Qu.:47250
Mode :character Median :65000
Mean :65875
3rd Qu.:80750
Max. :92000
min(INPUT$SALARY)
max(INPUT$SALARY)
mean(INPUT$SALARY)
median(INPUT SALARY ¿ var ¿SALARY) sd(INPUT$SALARY){r}

[1] 45000
[1] 92000
[1] 65875
This is an [R Markdown](http://rmarkdown.rstudio.com) Notebook. When you

execute code within the notebook, the results appear beneath the code.
Try executing this chunk by clicking the *Run* button within the chunk or by
placing your cursor inside it and pressing *Ctrl+Shift+Enter*.
```{r}
plot(cars)
Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing
Ctrl+Alt+I.
When you save the notebook, an HTML file containing the code and output will be saved
alongside it (click the Preview button or press Ctrl+Shift+K to preview the HTML file).
P a g e 71 | 72
RMC FILE
The preview shows you a rendered HTML copy of the contents of the editor. Consequently,
unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when
it was last run in the editor is displayed.
P a g e 72 | 72

Raghav Khemka 3B RMC

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Raghav Khemka 3B RMC

Uploaded by

Copyright:

Available Formats

RMC FILE

S.NO. Topic Page

urname <- "Hello"

name1 <- "12.5"

name2 <- "13.5"

# R is lower case case sensative language. It is very good language. It

a <- "Hello!!! , How are you..,

# [1] "Hello!!! , How are you..,\n+ i m fine."

# Hello!!! , How are you..,

# [1] "Hello How are you!!!!"

## Builtin Math Function

# And operator (&)

z <- a >b & c<a

z <- a<b | a > c

# Not operator (!)

## [1] "b is greater than a"

## [1] "a and b are equal"

## [1] "a is greater than b"

## [1] "b is not greater than a"

## Enter your age

## [1] "You are not a major, u are not eligible to work"

dice <- dice + 1

## [1] "No Yahtzee"

dice <- 1:6

## [1] "The dice number is 1 Not Yahtzee"

CALLING A FUNCTION WITHOUT AN ARGUMENT

CALLING A FUNCTION WITH ARGUMENT VALUES (BY POSITION

new.function <- function(a,b,c) {

CALLING A FUNCTION WITH DEFAULT ARGUMENT

LAZY EVALUATION OF FUNCTION

new.function <- function(a, b) {

thislist <- list("apple", "banana", "cherry")

CHANGING VALUE OF SPECIFIC ITEM:

ADD ITEM AT THE END OF LIST:

TO ADD ITEM AFTER A SPECIFIED ITEM:

REMOVING LIST ITEMS:

SPECIFYING RANGE OF INDEXES:

thislist <- list("apple", "banana", "cherry")

numbers <- c(1, 2, 3)

VECTOR WITH NUMERICAL VALUES WITH A SEQUENCE:

numbers1 <- 1.5:6.5

## [1] 1.5 2.5 3.5 4.5 5.5 6.5

numbers2 <- 1.5:6.3

## [1] 1.5 2.5 3.5 4.5 5.5

VECTORS OF LOGICAL VALUES :

## [1] TRUE FALSE TRUE FALSE

## [1] "apple" "banana" "lemon" "mango" "orange"

fruits <- c("banana", "apple", "orange", "mango", "lemon")

## [1] "banana" "orange"

fruits <- c("banana", "apple", "orange", "mango", "lemon")

## [1] "apple" "orange" "mango" "lemon"

fruits <- c("banana", "apple", "orange", "mango", "lemon")

fruits[1] <- "pear"

## [1] "pear" "apple" "orange" "mango" "lemon"

CREATING A MATRIX WITH STRING:

ACESSING THE ITEMS:

thismatrix <- matrix(c("apple", "banana", "cherry", "orange"), nrow = 2,

## [1] "banana" "orange"

thismatrix <- matrix(c("apple", "banana", "cherry", "orange"), nrow = 2,

## [1] "cherry" "orange"

thismatrix <- matrix(c("apple", "banana", "cherry", "orange","grape",

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

thismatrix <- matrix(c("apple", "banana", "cherry", "orange","grape",

ADD ROWS AND COLUMNS: