R Programming Practicals

Q.1. The number of students attending an online lecture over five days is given below: 
cat('\014') 
days<-c("Monday","Tuesday","Wednesday","Thursday","Friday") 
students<-c(40, 45, 50, 48, 60) 
plot(students, 
     type="o", 
     xaxt="n", 
     main="Students Attending Online Lecture", 
     xlab="Day", 
     ylab="Number of Students", 
     pch=16) 
axis(1,at=1:5,labels=days)

Q.2. The number of students enrolled in different IT specializations is: 
cat('\014') 
specialization<-c("Data Science","Cyber Security", 
                  "AI","Cloud Computing") 
students<-c(40, 35, 45, 30) 
bar_pos<-barplot(students, 
        names.arg=specialization, 
        main="Students in IT Specializations", 
        xlab="Specialization", 
        ylab="Number of Students", 
        ylim=c(0,50), 
        col="cyan") 
 
text(x=bar_pos,y=students,labels=students,pos=3)

Q.3. A student spends weekly study time on different IT subjects (Subject, Hours). Create a pie chart. 
cat('\014') 
subjects<-c("Programming","Database","Networking","Mathematics","Other") 
hours<-c(10,6,5,4,3) 
 
#Pie Chart with values 
lab<-paste(subjects,"\n",hours) 
pie(hours, 
    labels=lab, 
    main="Weekly Study Time", 
    col=rainbow(length(hours))) 
 
#Pie Chart with Percentage 
pc<-round(hours/sum(hours)*100,2) 
lab<-paste(subjects,"\n",paste0("(", pc, "%)")) 
pie(hours, 
    labels=lab, 
    main="Weekly Study Time", 
    col=rainbow(length(hours)))

Q.4. The following marks were obtained by 20 students in a programming test: 
45, 55, 60, 62, 65, 67, 70, 72, 74, 75, 76, 78, 80, 82, 84, 85, 88, 90, 92, 95 
cat('\014') 
marks<-c(45, 55, 60, 62, 65, 67, 70, 72, 74, 75, 
         76, 78, 80, 82, 84, 85, 88, 90, 92, 95) 
 
h<-hist(marks, 
      main="Distribution of Programming Marks", 
      xlab="Marks", 
      ylab="Frequency", 
      ylim=c(0,7), 
      breaks=5, 
      col="lightgreen") 

 
text(x=h$mids,y=h$counts,labels=h$counts,pos=3)

Q.5. The following data represents the relationship between study hours and programming marks (Study 
Hours, Marks). Create a scatter plot. 
cat('\014') 
study_hours<-c(2,3,4,5,6,7,8,9) 
marks<-c(45,50,55,65,70,75,82,88) 
 
plot(study_hours, marks, 
      main="Study Hours vs Programming Marks", 
      xlab="Study Hours", 
      ylab="Marks", 
      xlim=c(0,10), 
      ylim=c(0,100), 
      pch=19, 
      col="blue")

Q.6. The marks obtained by students in three subjects (Programming, Database, Networking) are given. 
Create a box plot to compare their distributions. 
cat('\014') 
programming<-c(55, 60, 65, 68, 70, 72, 75, 80, 85) 
database<-c(50, 55, 60, 62, 65, 68, 70, 75, 78) 
networking<-c(45, 50, 55, 58, 60, 63, 67, 70, 72) 
 
marks<-data.frame(programming,database,networking) 
 
boxplot(marks, 
        main="Subject-wise Marks Distribution", 
        xlab="Subjects", 
        ylab="Marks", 
        col=c("lightblue","lightgreen","lightyellow"))

Q.7. The number of software projects completed by two teams over four months is given (Month, Team A, 
Team B). Create a multiple line graph to compare the performance of the two teams. 
cat('\014') 
months <- c("January", "February", "March", "April") 
teamA <- c(5, 7, 8, 10) 
teamB <- c(4, 6, 9, 11) 
 
#Plot Team A Line 
plot(teamA, 
     type = "o", 
     pch = 16, 
     col = "red", 
     xaxt = "n", 
     ylim = c(0, 12), 
     main = "Projects Completed by Teams", 
     xlab = "Month", 
     ylab = "Number of Projects" 
     ) 
axis(1, at = 1:4, labels = months) 
 
#Plot Team B Line 
lines(teamB, 
      type = "o", 
      pch = 8, 
      col = "blue") 
 
#Legends 
legend("topleft", 
       legend = c("Team A", "Team B"), 

       col = c("red","blue"), 
       pch = c(16, 8), 
       lty = 1)

Q.8. The number of users of different programming languages in a class is given (Language, Users). Create 
a horizontal bar graph. 
cat('\014') 
languages <- c("Python", "R", "Java", "C++", "JavaScript") 
users <- c(45, 30, 35, 25, 40) 
par(mar = c(5, 7 ,5, 2)) # To adjust margin for Y-axis tick labels 
par(mgp = c(5, 1, 0)) # To adjust position of Y-axis title 
bar_pos<-barplot(users, 
                 names.arg = languages, 
                 horiz = TRUE, 
                 main = "Programming Languages Used by Students", 
                 xlab = "Number of Students", 
                 ylab = "Programming Language", 
                 col = "orange", 
                 xlim = c(0,50), 
                 las = 1) 
text(x = users + 2, 
     y = bar_pos, 
     labels = users, 
     pos = 4)

Q.9. The following data represents the number of hours spent by students on different IT activities (Activity, 
Hours). Create a dot chart. 
cat('\014') 
activity <- c("Coding", 
               "Reading", 
               "Project", 
               "Testing", 
               "Documentation") 
 
hours <- c(12, 7, 10, 6, 5) 
 
dotchart(hours, 
          labels = activity, 
          main = "Time Spent on IT Activities", 
          xlab = "Hours")

Q.10. The following data represents the monthly internet data usage of a student (Month, Data Usage (GB)). 
Create a line graph with points and grid lines. 
cat('\014') 
month <- c("Jan", "Feb", "Mar", "Apr", "May", "Jun") 
usage <- c(80, 95, 110, 105, 125, 140) 
 
plot(usage, 
     type = "o", 
     xaxt = "n", 
     main = "Monthly Internet Data Usage", 
     xlab = "Month", 
     ylab = "Data Usage (GB)", 
     pch = 19) 
 
axis(1, at = 1:6, labels = month) 
 
grid()

Q.1. Create the following diagram in R. (Computer → Hardware, Software; Hardware → CPU, Memory; 
Software → OS, Application) 
cat('\014') 
library(DiagrammeR) 
grViz(" 
digraph { 
  Computer->Hardware 
  Computer->Software 
  Hardware->CPU 
  Hardware->Memory 
  Software->OS 
  Software->Application 
} 
")

Q.2. Create the following diagram in R. (Start → Marks → Check → Pass / Fail → End) 
library(DiagrammeR) 
grViz(" 
digraph { 
  Start->Marks 
  Marks->Check 
  Check->Pass [label='Marks >= 40'] 
  Check->Fail [label='Marks < 40'] 
  Pass->End 
  Fail->End 
} 
")

Q.3. Create the following diagram in R. (Directed graph with nodes A, B, C, D, E) 
cat('\014') 
library(igraph) 
g<-graph_from_literal( 
  A+-B, 
  A-+C, 
  B-+D, 
  C+-D, 
  D-+E 
) 
set.seed(10) 
plot(g, 
     layout=layout_with_fr(g), 
     vertex.color="cyan", 
     vertex.frame.color="blue", 
     vertex.frame.width=3, 
     vertex.size=30, 
     vertex.label.color="black", 
     edge.color="black", 
     edge.width=2, 
     main = "Directed Graph")

Q.4. Create the following diagram in R. (Login validation flowchart) 
library(DiagrammeR) 
 
grViz(" 
digraph { 
  Start [label='START', shape=oval] 
  Login [label='Enter Username\\nand Password', shape=box] 
  Validate [label='Validate Login', shape=diamond] 
  Dashboard [label='Dashboard', shape=box] 
  Error [label='Invalid Login', shape=box] 
  End [label='END', shape=oval] 

 
  Start -> Login 
  Login -> Validate 
  Validate -> Dashboard [label='Valid'] 
  Validate -> Error [label='Invalid'] 
  Dashboard -> End 
  Error -> End 
} 
")

Q.5. Create the following diagram in R. (Web Browser → Web Server → Application Server → Database 
Server, Payment Gateway, dashed style) 
cat('\014') 
library(DiagrammeR) 
grViz(" 
digraph{ 
      node[shape=rectangle,style=dashed] 
      edge[style=dashed] 
      'Web Browser'->'Web Server' 
      'Web Server'->'Application\nServer' 
      'Application\nServer'->'Database\nServer' 
      'Application\nServer'->'Payment\nGateway' 
}" 
)

Q.1. A college teacher wants to study whether the number of hours a student spends studying has an effect 
on the marks obtained in a programming examination. The teacher records data for 10 students (Study 
Hours: 2 to 11, Marks). Perform the following tasks in R: 
1. Create a data frame containing the above data. 
2. Fit a simple linear regression model with Marks as the dependent variable and Study Hours as the 
independent variable. 
3. Display the summary of the regression model. 
4. Obtain the regression equation. 
5. Predict the marks of a student who studies for 7.5 hours. 
6. Plot the data points and regression line. 
cat('\014') 
study_hrs<-c(2,3,4,5,6,7,8,9,10,11) 
marks<-c(45,50,54,61,65,70,74,80,85,88) 
df<-data.frame(study_hrs,marks) 
model<-lm(marks~study_hrs) 
print(summary(model)) 
eq<-coef(model) 
b0<-eq[1] 
b1<-eq[2] 
cat("Regression Equation : y=",b0,"+",b1,"x") 
ans<-predict(model,data.frame(study_hrs=7.5)) 
cat("\nPredicted Marks of a student who studies for 7.5 hours = ",ans) 
plot(study_hrs,marks, 
     main="Marks vs Study Hours", 
     xlab="Study Hours", 
     ylab="Marks", 
     xlim=c(0,12), 
     ylim=c(0,100))
abline(model,col="red")

Q.2. The women dataset contains the height and weight of women. A health researcher wants to investigate 
whether height can be used to predict weight. Perform the following tasks in R: 
1. Load the women dataset. 
2. Display the dataset. 
3. Fit a simple linear regression model. 
4. Identify the independent and dependent variables. 
5. Obtain the regression equation. 
6. Predict the weight of a woman with a height of 65 inches. 
7. Display actual values, predicted values and residuals. 
cat('\014') 
data(women) 
print(women) 
model<-lm(weight~height,data=women) 
print(summary(model)) 
eq<-coef(model) 
b0<-eq[1] 
b1<-eq[2] 
cat("Regression Equation : y=",b0,"+",b1,"x") 
ans<-predict(model,data.frame(height=65)) 
cat("\nPredicted weight of a woman with a height of 65 inches = ",ans,"\n\n") 
predicted<-fitted(model) 
res<-residuals(model) 
result<-data.frame( 
  Actual_Height=women$height, 
  Actual_Weight=women$weight, 
  Predicted_Weight=predicted, 
  Residuals=res 
) 
print(result)

Q.3. An IT department wants to determine whether increasing the RAM of a computer improves its 
application performance score (RAM (GB): 4, 6, 8, 10, 12, 14, 16, 18; Performance Score). Perform the 
following tasks in R: 
1. Enter the data into R. 
2. Fit a simple linear regression model. 
3. Obtain the intercept and slope. 
4. Predict the website loading time when 75 users access the website simultaneously. 
5. Plot residuals against fitted values. 
6. Generate a Normal Q-Q plot. 
7. Generate a histogram of residuals. 
cat('\014') 
ram<-c(4,6,8,10,12,14,16,18) 
pscore<-c(45,52,60,67,73,78,84,88) 
df<-data.frame(ram,pscore) 
model<-lm(pscore~ram) 
print(coef(model)) 
ans<-predict(model,data.frame(ram=75)) 
cat("\nPredicted Website Loading Time when 75 users access the website simultaneously = 
",ans) 
 
fit<-fitted(model) 
res<-residuals(model) 
 
plot(fit,res, 
     main="Residuals vs Fitted Values", 
     xlab="Fitted Values", 

     ylab="Residuals") 
abline(h=0) 
 
qqnorm(res) 
qqline(res)

Q.4. Using the inbuilt cars dataset, a researcher wants to predict the stopping distance of cars based on their 
speed. 
Tasks: 
1. Create the regression model. 
2. Predict stopping distance for speeds of 10, 15, 20 and 25 mph. 
3. Store the predictions in a data frame. 
4. Display the predictions. 
5. Plot the original observations and regression line. 
6. Generate the four standard diagnostic plots using plot(model). 
cat('\014') 
data(cars) 
cat('\014') 
 
data(cars) 
model <- lm(dist ~ speed, data = cars) 
Speed <- c(10, 15, 20, 25) 
Stopping_Distance <- predict( 
  model, 
  data.frame(speed = Speed) 
) 
df <- data.frame(Speed, Stopping_Distance) 
print(df) 
plot(cars$speed, cars$dist, 
     main = "Stopping Distance vs Speed", 
     xlab = "Speed (mph)", 
     ylab = "Stopping Distance (ft)") 
abline(model) 
plot(model)

Q.5. The airquality dataset contains daily air quality measurements in New York. It includes Ozone 
concentration and Temperature. An environmental researcher wants to determine whether temperature can 
be used to predict ozone concentration. Perform following tasks in R: 
1. Load the airquality dataset. 
2. Check for missing values. 
3. Remove observations containing missing values for Ozone and Temp. 
4. Fit a simple linear regression model with Ozone as the dependent variable and Temp as the 
independent variable. 
5. Display the model summary. 
6. Predict ozone concentration when the temperature is 80°F. 

7. Plot the regression line. 
cat('\014') 
data(airquality) 
head(airquality) 
df<-na.omit(airquality[, c("Ozone", "Temp")]) 
model<-lm(Ozone~Temp,data=df) 
print(summary(model)) 
ans<-predict(model,data.frame(Temp=80)) 
cat("\nOzone concentration when the temperature is 80°F = ",ans) 
plot(df$Temp, df$Ozone, 
     main = "Ozone Concentration vs Temperature", 
     xlab = "Temperature (°F)", 
     ylab = "Ozone Concentration", 
     pch = 19) 
abline(model)

Q.1. Consider the following manually collected data of students and perform Weighted Least Squares 
regression to study the relationship between Study Hours (X) and Marks (Y) (Study Hours, Marks, Weight). 
Fit the WLS regression model and predict marks for a student who studies 7 hours. 
cat('\014') 
study_hours<-c(2, 3, 4, 5, 6) 
marks<-c(45, 50, 58, 65, 72) 
weight<-c(1, 2, 3, 4, 5) 
 
df<-data.frame(study_hours, marks, weight) 
print(df) 
 
#WLS model 
model<-lm(marks~study_hours,data=df,weights=weight) 
 
#Model summary 
print(summary(model)) 
 
#Regression equation 
eq<-coef(model) 
b0<-eq[1] 
b1<-eq[2] 
cat("\nRegression Equation: \nMarks =",b0,"+",b1,"*Study Hours\n") 
 
# Prediction 
answer<-predict(model,data.frame(study_hours=7)) 
cat("\nPredicted Marks=",answer) 
 
# Plot 
plot(study_hours, marks, 
     main = "WLS Regression: Marks vs Study Hours", 
     xlab = "Study Hours", 
     ylab = "Marks", 
     pch = 19) 
 
abline(model)

Q.2. A shop records the following data for Advertising Expenditure (X) and Sales (Y) (Advertising 
Expenditure, Sales, Weight). Perform WLS regression and predict sales when advertising expenditure is 35 
units.

cat('\014') 
advertising<-c(10,20,30,40,50) 
sales<-c(25,38,55,70,88) 
weight<-c(1,2,3,4,5) 
 
df<-data.frame(advertising,sales,weight) 
print(df) 
 
#WLS model 
model<-lm(sales~advertising,data=df,weights=weight) 
 
#Model summary 
print(summary(model)) 
 
#Regression equation 
eq<-coef(model) 
b0<-eq[1] 
b1<-eq[2] 
cat("\nRegression Equation: \nSales =",b0,"+",b1,"*Advertising\n") 
 
# Prediction 
answer<-predict(model,data.frame(advertising=35)) 
cat("\nPredicted Sales=",answer) 
 
# Plot 
plot(advertising,sales, 
     main = "WLS Regression: Sales vs Advertising", 
     xlab = "Advertising", 
     ylab = "Sales", 
     pch = 19) 
 
abline(model)

Q.3. Using the built-in cars dataset, perform WLS regression between speed and dist. Use 1/speed as the 
weight. Predict stopping distance for a speed of 20 mph. 
cat('\014') 
data(cars) 
print(head(cars)) 
 
#Create weights 
w<-1/cars$speed 
 
#Fit WLS model 
wls_model<-lm(dist~speed,data=cars,weights=w) 
 
#Model summary 
print(summary(wls_model)) 
 
#Regression equation 
eq<-coef(wls_model) 
cat("\nRegression Equation: dist =",b0, "+",b1,"*speed\n") 
 
#Prediction for speed = 20 
answer<-predict(wls_model,data.frame(speed=20)) 
cat("\nPredicted Speed = ",answer) 
 
# Plot 
plot(cars$speed, cars$dist, 
     main = "WLS Regression: Stopping Distance Vs Speed", 
     xlab = "Speed", 
     ylab = "Stopping Distance", 
     pch = 19) 
 
abline(wls_model)

Q.4. Using the built-in trees dataset, perform WLS regression between Girth and Volume. Use 1/Height as 
the weight. Predict volume for a tree having a girth of 15 inches. 
cat('\014') 
data(trees) 
print(head(trees)) 
 
#Create weights 
w<-1/trees$Height 
 
#Fit WLS model 
wls_model<-lm(Volume~Girth,data=trees,weights=w) 
 
#Model summary 
print(summary(wls_model)) 
 
#Regression equation 
eq<-coef(wls_model) 
cat("\nRegression Equation: Volume =",b0, "+",b1,"*Girth\n") 
 
#Prediction for Girth = 15 
answer<-predict(wls_model,data.frame(Girth=15)) 
cat("\nPredicted Volume = ",answer) 
 
# Plot 
plot(trees$Girth, trees$Volume, 
     main = "WLS Regression: Volume Vs Girth", 
     xlab = "Girth", 
     ylab = "Volume", 
     pch = 19) 
 
abline(wls_model)

Q.1. Create a dataset containing Study Hours, Attendance, Assignment Marks and Exam Marks for 10 
students. Build a Multiple Linear Regression model to predict Exam Marks if Study Hours = 8, Attendance 
= 85, Assignment = 82. 
cat('\014') 
student_data<-data.frame( 
  StudyHours=c(2,3,4,5,6,7,8,9,10,11), 
  Attendance=c(65,70,72,75,78,82,85,88,92,95), 
  Assignment=c(55,60,65,70,72,78,80,85,88,92), 
  ExamMarks=c(52,58,64,69,74,81,85,89,94,97) 
) 
print(student_data) 
 
# Multiple Linear Regression 
model<-lm(ExamMarks~StudyHours+Attendance+Assignment,data=student_data) 
 
#Display model summary 
print(summary(model)) 
 
#Prediction 
new_student<-data.frame(StudyHours = 8,Attendance = 85,Assignment = 82) 
answer<-predict(model,newdata=new_student) 
cat("\nPredicted Marks=",answer)

Q.2. Create a dataset containing House Area, Number of Bedrooms, Age of House and House Price. Use 
Multiple Linear Regression to predict the price of a house with Area = 1900, Bedrooms = 4, Age = 6. 
 
cat('\014') 
HousePrice<-data.frame( 
  Area=c(800,1000,1200,1400,1600,1800,2000,2200,2400,2600), 
  Bedrooms=c(2,2,3,3,3,4,4,4,5,5), 
  Age=c(20,18,15,12,10,8,7,5,4,2), 
  Price=c(45,55,65,75,88,100,115,125,140,155) 
) 
print(HousePrice) 
 
# Multiple Linear Regression 
model<-lm(Price~Area+Bedrooms+Age,data=HousePrice) 
 
#Display model summary 
print(summary(model)) 
 
#Prediction 
new_house<-data.frame(Area=1900,Bedrooms=4,Age=6) 
answer<-predict(model,newdata=new_house) 
cat("\nPredicted Price=",answer)

Q.3. Using the inbuilt mtcars dataset, create a Multiple Linear Regression model to predict Miles Per Gallon 
(mpg) using: Horsepower (hp), Weight (wt), Displacement (disp). Also predict the MPG of a car having: hp 
= 120, wt = 2.8, disp = 200 
cat('\014') 
data(mtcars) 
print(head(mtcars)) 
 
# Create Multiple Linear Regression model 
model<-lm(mpg~hp+wt+disp,data = mtcars) 
 
# Display model summary 
print(summary(model)) 
 
#Prediction 
new_car<-data.frame(hp=120,wt=2.8,disp=200) 
answer<-predict(model,newdata=new_car) 
cat("\nPredicted MPG=",answer)

Q.4. Using the mtcars dataset, apply Ridge Regression to predict mpg using: hp, wt, disp, qsec. Use cross-
validation to determine the optimum value of lambda. 
 
cat('\014') 
library(glmnet) 
data(mtcars) 
 
x<-as.matrix(mtcars[, c("hp", "wt", "disp", "qsec")]) 
 
y<-mtcars$mpg 
 
ridge_model<-glmnet(x,y,alpha=0) 
 
cv_ridge<-cv.glmnet(x,y,alpha=0) 
 
cat("\n Optimum Lambda=",cv_ridge$lambda.min) 
 
plot(cv_ridge) 
 
cat("\nCoefficients\n") 
print(coef(cv_ridge,s="lambda.min"))

Q.5. Using the inbuilt airquality dataset, predict Ozone using: Solar.R, Wind, Temp. Apply Ridge 
Regression and determine the optimum lambda using cross-validation. 
cat('\014') 
 
library(glmnet) 
 
data(airquality) 
 
air_data<-na.omit(airquality) 
 
x<-as.matrix(air_data[, c("Solar.R", "Wind", "Temp")]) 
 
y<-air_data$Ozone 
 
ridge_model<-glmnet(x,y,alpha=0) 
 
cv_ridge<-cv.glmnet(x,y,alpha=0) 
 
cat("\nOptimum Lambda = ",cv_ridge$lambda.min) 
 
plot(cv_ridge) 
 
cat("\nCoefficients\n") 
print(coef(cv_ridge,s="lambda.min")) 
 
new_data<-matrix(c(200, 10, 80),nrow = 1) 
colnames(new_data)<-c("Solar.R", "Wind", "Temp") 
answer<-predict(cv_ridge,newx = new_data,s="lambda.min") 
cat("\nPredicted Ozone Concentration = ",answer)