EXPERIMENT 5

#LOAD DATA FROM DIFFERENT FILES LIKE CSV AND EXCEL R

getwd()

setwd("C:/Users/HP/Desktop/R LAB PROGRAMS")

OUTPUT:

> getwd()

[1] "C:/Users/HP/Documents"

> setwd("C:/Users/HP/Desktop/R LAB PROGRAMS")

#IMPORTING DATA USING READ.CSV

f1<- read.csv("marks.csv")

f1

#length of data frame

length(f1)

#summary of the data frame

summary(f1)

OUTPUT:

Student.ID Name JAVA.MARKS DM.MARKS OS.MARKS CGPA

1 101 Alice 85 90 88 3.8

2 102 Bob 78 85 80 3.4

3 103 Charlie 92 88 95 4.0

4 104 David 75 82 77 3.2

5 105 Emily 88 95 89 3.9

6 106 Frank 80 78 82 3.1

7 107 Grace 95 92 97 4.2

8 108 Henry 70 75 67 2.9

9 109 Irene 89 87 91 3.7

10 110 Jack 84 91 86 3.6

> length(f1)

[1] 6
> summary(f1)

Student.ID Name JAVA.MARKS DM.MARKS

Min. :101.0 Length:10 Min. :70.00 Min. :75.00
 1st Qu.:103.2 Class :character 1st Qu.:78.50 1st Qu.:82.75
Median :105.5 Mode :character Median :84.50 Median :87.50
Mean :105.5 Mean :83.60 Mean :86.30
3rd Qu.:107.8 3rd Qu.:88.75 3rd Qu.:90.75
Max. :110.0 Max. :95.00 Max. :95.00
OS.MARKS CGPA
Min. :67.0 Min. :2.900
1st Qu.:80.5 1st Qu.:3.250
Median :87.0 Median :3.650
Mean :85.2 Mean :3.580
3rd Qu.:90.5 3rd Qu.:3.875
Max. :97.0 Max. :4.200

#DISCRIPTIVE STATISTICS

#DATA DESCRIPTION

#COMPUTING MEAN VALUE

mean = mean(f1$CGPA)

mean

#computing median

median = median(f1$CGPA)

median

#computing mode

install.packages("modeest")

library(modeest)

mode = mfv(f1$CGPA)

print(mode)

cat("mean, median & mode of the java discription are: ")

print(mean)

print(median)

print(mode)

OUTPUT:

> mean

[1] 3.58

> median

[1] 3.65

package ‘modeest’ successfully unpacked and MD5 sums checked

> print(mode)

[1] 2.9 3.1 3.2 3.4 3.6 3.7 3.8 3.9 4.0 4.2

mean, median & mode of the java discription are:

[1] 3.58

[1] 3.65

[1] 2.9 3.1 3.2 3.4 3.6 3.7 3.8 3.9 4.0 4.2

##MEASURES OF VARIABILITY

max = max(f1$JAVA.MARKS)

cat("maximum value: \n",max)

min = min(f1$JAVA.MARKS)

cat("minimum value: \n",min)

OUTPUT:

maximum value:

95

minimum value:

70

#calculate range

range(f1$JAVA.MARKS)

#calculate range, difference between max and min

ranged = max - min

cat("Difference between max and min, Range is : ")

ranged

range(f1$JAVA.MARKS)

max(f1$JAVA.MARKS)

OUTPUT:

> range(f1$JAVA.MARKS)

[1] 70 95

Difference between max and min, Range is : > ranged

[1] 25

> range(f1$JAVA.MARKS)

[1] 70 95
> max(f1$JAVA.MARKS)

[1] 95

#Data variability

#Variance and standard variation

cat("Variance of the java marks: ")

variance = var(f1$JAVA.MARKS)

variance

stdevq = sd(f1$JAVA.MARKS)

meanvq = mean(f1$JAVA.MARKS)

cv = (stdevq/meanvq)* 100

cv

cat("Variance of the java marks: ",variance)

cat("Standard deviation of the java marks: ", stdevq)

varianced = var(f1$DM.MARKS)

stdeva = sd(f1$DM.MARKS)

meannd = mean(f1$DM.MARKS)

meannd

stdeva

cv1 = (stdeva/meannd)*100

cv1

cat("Variance of the dm marks: ",varianced)

cat("Standard deviation of dm marks: ",stdeva)

cat("S.D in java and dm marks: ",stdevq,stdeva)

print("Data variability in java and dm marks")

if(cv > cv1){

print("Java marks have more variability than dm")

}else{

print("Dm marks have more variability than java")

OUTPUT:
Variance of the java marks:

[1] 61.6

> cv

[1] 9.388238

Variance of the java marks: 61.6

Standard deviation of the java marks: 7.848567

> meannd

[1] 86.3

> stdeva

[1] 6.360468

> cv1

[1] 7.370183

Variance of the dm marks: 40.45556

Standard deviation of dm marks: 6.360468

S.D in java and dm marks: 7.848567 6.360468

[1] "Data variability in java and dm marks"

[1] "Java marks have more variability than dm"

##QUANTILES OF THE DATA

quartiles = quantile(f1$JAVA.MARKS)

quartiles

probs = seq(0,1,0.25)

quantile(f1$JAVA.MARKS,probs)

OUTPUT:

> quartiles

0% 25% 50% 75% 100%

70.00 78.50 84.50 88.75 95.00

> quantile(f1$JAVA.MARKS,probs)

0% 25% 50% 75% 100%

70.00 78.50 84.50 88.75 95.00

#DECILES
probs = seq(0,1,0.1)

quantile(f1$JAVA.MARKS,probs)

OUTPUT:

> quantile(f1$JAVA.MARKS,probs)

0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%

70.0 74.5 77.4 79.4 82.4 84.5 86.2 88.3 89.6 92.3 95.0

#PERCENTILES

h = c(1:2000)

probs1 = seq(0,1,0.1)

quantile(h,probs)

OUTPUT:

> quantile(h,probs)

0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%

1.0 200.9 400.8 600.7 800.6 1000.5 1200.4 1400.3 1600.2 1800.1 2000.0

getwd()

setwd("C:/Users/HP/Desktop/R LAB PROGRAMS")

path = "C:/Users/HP/Desktop/R LAB PROGRAMS/student-marks.xlsx"

library("readxl")

ps = read_excel(path , skip=4)

ps

getwd()

setwd("C:/Users/HP/Desktop/R LAB PROGRAMS")

library("readxl")

OUTPUT:

> ps

# A tibble: 6 × 6

`104` David `75` `82` `77` `3.2`

<dbl> <chr> <dbl> <dbl> <dbl> <dbl>

1 105 Emily 88 95 89 3.9

2 106 Frank 80 78 82 3.1

3 107 Grace 95 92 97 4.2

4 108 Henry 70 75 67 2.9

5 109 Irene 89 87 91 3.7

6 110 Jack 84 91 86 3.6

#DATA CLEANING IN R

#Data cleaning refers to the process of transforming raw data into data that is suitable to perform
operations

#Method 1: Remove Rows With Missing Values

library(dplyr)

#remove rows with any missing values

df <- data.frame(

PatientID = c(1, 2, 3, 4, 5),

PatientName = c("John Doe", "Jane Smith", "Bob Johnson", NA, "Charlie Brown"),

Age = c(35, 28, NA, 60, 42),

AdmissionDate = as.Date(c("2024-01-01", "2024-02-15", "2024-03-10", "2024-04-05", "2024-05-

20")),

DischargeDate = as.Date(c("2024-01-10", "2024-03-05", NA, "2024-05-15", "2024-06-10")),

Diagnosis = c("Flu", "Fractured Leg", "Pneumonia", "Hypertension", "Appendicitis"),

RoomNumber = c(101, NA, 310, 415, 520),

DoctorName = c("Dr. Smith", "Dr. Johnson", "Dr. Davis", "Dr. Wilson", NA)

print(df)

df %>% na.omit()

OUTPUT:

> print(df)

PatientID PatientName Age AdmissionDate DischargeDate Diagnosis RoomNumber

1 1 John Doe 35 2024-01-01 2024-01-10 Flu 101

2 2 Jane Smith 28 2024-02-15 2024-03-05 Fractured Leg NA

3 3 Bob Johnson NA 2024-03-10 <NA> Pneumonia 310

4 4 <NA> 60 2024-04-05 2024-05-15 Hypertension 415

5 5 Charlie Brown 42 2024-05-20 2024-06-10 Appendicitis 520

 DoctorName

1 Dr. Smith

2 Dr. Johnson

3 Dr. Davis

4 Dr. Wilson

5 <NA>

> df %>% na.omit()

PatientID PatientName Age AdmissionDate DischargeDate Diagnosis RoomNumber

1 1 John Doe 35 2024-01-01 2024-01-10 Flu 101

DoctorName

1 Dr. Smith

#replace missing values

df1 <- df %>% mutate(across(where(is.numeric), ~ifelse(is.na(.), mean(., nTRUE), .)))

print(df1)

Output

PatientID PatientName Age AdmissionDate DischargeDate

Diagnosis RoomNumber DoctorName
1 1 John Doe 35.00 2024-01-01 2024-01-10
Flu 101.0 Dr. Smith
2 2 Jane Smith 28.00 2024-02-15 2024-03-05
Fractured Leg 336.5 Dr. Johnson
3 3 Bob Johnson 41.25 2024-03-10 <NA>
Pneumonia 310.0 Dr. Davis
4 4 <NA> 60.00 2024-04-05 2024-05-15
Hypertension 415.0 Dr. Wilson
5 5 Charlie Brown 42.00 2024-05-20 2024-06-10
Appendicitis 520.0 <NA>

#remove

zz=c(23,29,NA,9,21.19)
zz
length(zz)
mean(zz)
M=mean(zz,na.rm=T)
print(M)
OUTPUT:
#remove>

zz=c(23,29,NA,9,21.19)

>

zz[1] 23.00 29.00 NA 9.00 21.19

> length(zz)

[1] 5

> mean(zz)

[1] NA

> M=mean(zz,na.rm=T)

> print(M)

[1] 20.5475

#Remove using data frame

df <- data.frame(

Name = c("Alice", "Jack", "Bob", "Anny", "Christie"),

Age = c(24, 35, 23, 32, 40),

City = c("New York", "Los Angeles", NA, "San Francisco", "Seattle"),

Grade = c("A", "B", "C", "A", "B")

print(df)

new_df<- df %>% na.omit()

print(new_df)

OUTPUT:

> print(df)

Name Age City Grade

1 Alice 24 New York A

2 Jack 35 Los Angeles B

3 Bob 23 <NA> C

4 Anny 32 San Francisco A

5 Christie 40 Seattle B

> new_df<- df %>% na.omit()

 > print(new_df)

Name Age City Grade

1 Alice 24 New York A

2 Jack 35 Los Angeles B

4 Anny 32 San Francisco A

5 Christie 40 Seattle B

#Remove duplicate rows using dataFrame

df_with_duplicates <- data.frame(

Name = c("Jack", "Jane", "Jack", "Jane", "Bob", "Alice", "Christie"),

Age = c(25, 30, 25, 30, 22, 28, 35),

City = c("New York", "Los Angeles", "New York", "Los Angeles", "Chicago", "San Francisco",
"Seattle"),

Grade = c("A", "B", "A", "B", "C", "A", "B")

print(df_with_duplicates)

new_df<- df_with_duplicates %>% distinct(.keep_all = TRUE)

print(new_df)

OUTPUT:

> print(df_with_duplicates)

Name Age City Grade

1 Jack 25 New York A

2 Jane 30 Los Angeles B

3 Jack 25 New York A

4 Jane 30 Los Angeles B

5 Bob 22 Chicago C

6 Alice 28 San Francisco A

7 Christie 35 Seattle B

> new_df<- df_with_duplicates %>% distinct(.keep_all = TRUE)

> print(new_df)

Name Age City Grade

1 Jack 25 New York A

2 Jane 30 Los Angeles B

3 Bob 22 Chicago C

4 Alice 28 San Francisco A

5 Christie 35 Seattle B

#Drop rows
df <- data.frame(
Name = c("John", "Jane", "Bob", "Alice", "Charlie"),
Age = c(25, 30, 22, 28, 35),
City = c("New York", "Los Angeles", NA, "San Francisco", "Seattle"),
Grade = c("A", "B", "C", "A", "B")
)
df %>% drop_na()

OUTPUT:

Name Age City Grade

1 John 25 New York A

2 Jane 30 Los Angeles B

3 Alice 28 San Francisco A

4 Charlie 35 Seattle B

#drop rows in specific columns

df %>% drop_na(City)

OUTPUT:

Name Age City Grade

1 John 25 New York A

2 Jane 30 Los Angeles B

3 Alice 28 San Francisco A

4 Charlie 35 Seattle B
# to get column headings
glimpse(df)

OUTPUT:

Rows: 5

Columns: 4

$ Name <chr> "John", "Jane", "Bob", "Alice", "Charlie"

$ Age <dbl> 25, 30, 22, 28, 35

$ City <chr> "New York", "Los Angeles", NA, "San Francisco", "Seattle"

$ Grade <chr> "A", "B", "C", "A", "B"

#bind rows

df1 <- data.frame(

Name = c("Aarav", "Aditi", "Arjun", "Ananya", "Ayush"),
Age = c(25, 30, 22, 28, 35),
City = c("Mumbai", "Delhi", "Bangalore", "Kolkata", "Chennai"),
Grade = c("A", "B", "C", "A", "B")
)
df2 <- data.frame(
Name = c("Bhavya", "Chirag", "Deepika", "Dhruv", "Esha"),
Age = c(27, 32, 24, 30, 28),
City = c("Jaipur", "Ahmedabad", "Lucknow", "Hyderabad", "Pune"),
Grade = c("B", "C", "A", "B", "A")
)
df1
df2
com<- bind_rows(df1,df2)
print(com)

OUTPUT:

Name Age City Grade

1 Aarav 25 Mumbai A
2 Aditi 30 Delhi B

3 Arjun 22 Bangalore C

4 Ananya 28 Kolkata A

5 Ayush 35 Chennai B

Name Age City Grade

1 Bhavya 27 Jaipur B

2 Chirag 32 Ahmedabad C

3 Deepika 24 Lucknow A

4 Dhruv 30 Hyderabad B

5 Esha 28 Pune A

Name Age City Grade

1 Aarav 25 Mumbai A

2 Aditi 30 Delhi B

3 Arjun 22 Bangalore C

4 Ananya 28 Kolkata A

5 Ayush 35 Chennai B

6 Bhavya 27 Jaipur B

7 Chirag 32 Ahmedabad C

8 Deepika 24 Lucknow A

9 Dhruv 30 Hyderabad B

10 Esha 28 Pune A