Scribd
Upload
30 views6 pages

Question No1

This document contains R code to analyze several datasets: 1) It analyzes ratings data by finding the most frequent rating and creating a bar plot of the rating frequencies. 2) It analyzes health data by creating a bar plot of quality frequencies. 3) It analyzes income data by creating frequency distributions, relative frequency distributions, and a histogram of the income variable. 4) It analyzes gas price data by creating frequency distributions, relative frequency distributions, and a histogram of the price variable. 5) It analyzes asset return data by creating a scatterplot with a trend line and computing the correlation coefficient. 6) It analyzes health and lifestyle data by creating scatter plots

Uploaded by

aniketgupta8433244176
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
30 views6 pages

Question No1

This document contains R code to analyze several datasets: 1) It analyzes ratings data by finding the most frequent rating and creating a bar plot of the rating frequencies. 2) It analyzes health data by creating a bar plot of quality frequencies. 3) It analyzes income data by creating frequency distributions, relative frequency distributions, and a histogram of the income variable. 4) It analyzes gas price data by creating frequency distributions, relative frequency distributions, and a histogram of the price variable. 5) It analyzes asset return data by creating a scatterplot with a trend line and computing the correlation coefficient. 6) It analyzes health and lifestyle data by creating scatter plots

Uploaded by

aniketgupta8433244176
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 6

#Question 01

#import the dataset and Label it


Getwd()
#set working directory
# Sample data of ratings
Ratings <- c(4, 5, 3, 4, 5, 4, 3, 2, 4, 5, 4, 4, 3, 5, 4, 5, 4, 3, 4, 5)
# Constructing frequency distribution
Rating_counts <- table(ratings)
# Displaying the frequency distribution
Print(“Frequency Distribution:”)
Print(rating_counts)
# Finding the rating with the most frequency
Most_frequent_rating <- names(which.max(rating_counts))
Print(paste(“Rating with the most frequency:”, most_frequent_rating))
# Constructing a bar chart
Barplot(rating_counts, main = “Quality Ratings of Entrées”,
Xlab = “Rating”, ylab = “Frequency”, col = “brown”,
Ylim = c(0, max(rating_counts)+5))
#Question 02
#SET WORKING DIRECTORY
Getwd()
#IMPORT THE DATASET AND LABEL IT
Ssdd <- read.csv(“Health.CSV”, header = TRUE, sep = “,”)
#Creating Bar Plot Quality and
#Creating Frequency for Quality
Quality_Frequency <- table(ssdd$Quality)
Quality_Frequency
View(Quality_Frequency)
Barplot(ssdd$Response, col=”red”)
#The quality of the patients are in average good
#Question 04
#Import the Dataset and Label it
Getwd()
#Set Working directory
Ssdd <- read.csv(“TRANSACTIONS.CSV”, header =TRUE, sep = “,”)
#Creating Frequency and relative Frequency Distributions
Intervals <- seq(22000,27000, by=1000)
Income.cut <- cut(ssdd$Income, intervals, left=FALSE, right=TRUE)
Income.frequency <-table(Income.cut)
Income.frequency
View(Income.frequency)
Income.prop<-prop.table(Income.frequency)
Income.prop
View(Income.prop)
#Creating Histogram
Hist(ssdd$Income,right=TRUE, main=”Histogram for the Income Variable”,
xlab=”Annual Income(in $1000s)”, col=”black”)
#Question 05
#Create Histogram
Getwd()
#Import your data set and label it
Ssdd <- read.csv(“Gas_2019.csv”, header = TRUE, sep =”,”)
#Creating Frequency and relative frequency distribution
Intervals <- seq(1.70,4.00, by=0.30)
Price.cut <- cut(ssdd$Price, intervals, left=FALSE, right=TRUE)
Price.frequency <-table(Price.cut)
Price.frequency
View(Price.frequency)
Price.prop <- prop.table(Price.frequency)
Price.prop
View(Price.prop)
#Creating Histogram
Hist(ssdd$Price, breaks=intervals, right=TRUE, main=”Histogram for the Price”,
xlab=”Price”,col=”blue”)
#Question 06
#Import the Dataset and Label it
#Set Working directory
Getwd()
# Define the returns for Asset A and Asset B
Return_A <- c(10, 8, 6, 4, 2)
Return_B <- c(2, 4, 6, 8, 10)

# Create a scatterplot with a trend line


Plot(return_A, return_B, xlab = “Return A (%)”, ylab = “Return B (%)”, main =
“Scatterplot of Returns”)
Abline(lm(return_B ~ return_A), col = “red”)

# Compute and print the correlation coefficient


Correlation <- cor(return_A, return_B)
Cat(“Correlation coefficient:”, correlation, “\n”)

# Explanation for diversification


Message <- ifelse(correlation < 0, “negative”, ifelse(correlation == 0, “no”, “positive”))
Cat(“Including both assets in the portfolio may help diversify risk as their returns have
a”, message, “relationship.”)
#Question 07
#Import the Healthy Living data and label it
Getwd()
#Set working directory
Ssdd <- read.csv(“Healthy_Living.csv”, header = TRUE,sep = “,”)
#Plotting a Scatter Plot
Plot(ssdd$Health ~ ssdd$Exercise, main = “Scatterplot of Health and Exercise”, xlab =
“Health”, ylab = “Exercise”, col=”red”, pch=16)
Plot(ssdd$Health ~ ssdd$Smoking, main = “Scatterplot of Health and Smoking”, xlab =
“Health”, ylab = “Smoking”, col=”blue”, pch=16)

You might also like