Module 5: Data Presentation

Scripts for RStudio

#install packages

install.packages("readr")

install.packages("pander")

#load packages

library(readr)

library(pander)

# Construction of Frequency Distribution Table (FDT)

#Example 1: Beverages

#Import the files

purchase<-read.csv("purchase.csv")

purchase

#Check the data

View(purchase)

#Frequency Table

#Count the frequency

purchase.freq <-table(purchase)

purchase.freq

#Output: from row to column

freq.dist<-cbind(purchase.freq)

freq.dist
#label the column "Frequency"

colnames(freq.dist)<-c("Frequency")

freq.dist

#Generate the FDT

pander(freq.dist)

#Example 2: Cars

#Creating Vectors, saving to Cars

Cars <-c(1, 2, 1, 0, 3, 4, 0, 1, 1, 2, 2, 3, 2, 1, 4, 0, 0)

Cars

#Determine the Frequency

car.freq <-table(Cars)

car.freq

#Find the relative frequency

car.relfreq<-(car.freq/sum(car.freq))

car.relfreq

#Percent relative frequency

car.percent <-(car.relfreq * 100)

car.percent

#Combine the 3 frequencies

car.fredist <- cbind(car.freq, car.relfreq, car.percent)

car.fredist
#Label the columns

colnames(car.fredist) <-c("Frequency", "Relative Frequency", "Percent Frequency (%)")

car.fredist

#Output

pander(car.fredist)

#Example 3: Grouped Distribution

#Import files

Rent <-read.csv("Rent.csv")

Rent

#Check the stored information

View (Rent)

#Create the Grouped Frequency Distribution Table. (Adjust to get an equal width)

breaks <-seq(425, 621, by = 28)

breaks

#Create the class interval

classint <-cut(Rent$Monthly.Rent, breaks, right=FALSE)

classint

#Determine the number of observations

freq <-table(classint)

freq

#Transform Frequency Table

freq.dist

#Label Columns

colnames(freq.dist)<-c("Frequency")

freq.dist

#Output

pander(freq.dist)

#Bar Graph

#Install packages

install.packages("tidyverse")

install.packages("forcats")

install.packages("readr")

#Load packages

library(readr)

library(tidyverse)

library(forcats)

#Import the file

purchase<-read.csv("purchase.csv")

#Check the stored information

purchase

#Generate the bar chart

bar1<-ggplot(purchase, aes(x=Purchase))+geom_bar(width=0.5)+ggtitle("Soft Drinks")

bar1

#Arrange in decreasing order

bar2<- ggplot(mutate(purchase,Purchase=fct_infreq(Purchase)))+geom_bar(aes(x=Purchase))

#Produce the Plot

bar2

#Pie Chart

#Load the package

library(readr)

#Import the file

purchase <-read.csv("purchase.csv")

purchase

#Store the file and get the frequency

data.freq <-table(purchase)

data.freq

#store the frequency

freq <-c(19, 8, 5, 13, 5)

freq

#Label

label <-c("Coke Classic", "Diet Coke", "Dr. Pepper", "Pepsi", "Sprite")

label

#Computing the percentage

percent

#Add the computed percentage to label

label <- paste(label, percent)

label

#Add the percent sign

label <-paste(label, "%", sep ="")

label

#Constructing the Pie Chart

piechart <-pie(freq, labels=label, col=rainbow(length(label)),main="Pie Chart of Soft Drinks Purchases")

#Dot Plot

#package for Dot plot

install.packages("ggplot2")

#Load the package

library(readr)

library(ggplot2)

#If you manually enter the data, use this script

cars<-c(1, 2, 1, 0, 3, 4, 0, 1, 1, 1, 2, 2, 3, 2, 3, 1, 4, 0, 0)

#Check if you really stored the information

cars

#Generating the output when data are manually entered in Rstudio

#Use this script when the file you import file

cars<-read.csv("Cars.csv")

#Check the stored information

cars

#Use this syntax to generate the dot plot when the file is imported

dplot<- ggplot(cars, aes(Cars))+geom_dotplot(binwidth=0.25)

#Check the output

dplot

#Stem and Leaf Plot 1

#Input the data manually in the object named data

data <-c(8.6, 11.7, 9.4, 10.2, 11.0, 8.8)

#Check the stored information

data

#Generate the stem and leaf plot

stem(data)

#Stem and Leaf Plot 2

#Load the package

library(readr)
#Import the file and save to the object named data

data <-read.csv("inflation.csv")

#Check the data

data

#Inspect the data frame

head(data)

#Select only the variable "Inflation" and store in the object named inf

inf <-data$Inflation

#Check the information stored in the object inf

inf

#Generate the stem and leaf plot

output<-stem(inf,scale=2)

#Histogram

#Load the package

library(readr)

#Import file

data <-read.csv("Rent.csv")

#Check the stored information in the object named "data"

data
#Generate the Histogram

hist(data$Monthly.Rent, breaks=seq(425, 625, by=25), main="Histogram of Rents", xlab="Monthly

#Crosstabulation

#Install the Package

install.packages("summarytools")

#Load the packages

library(readr)

library(summarytools)

library(pander)

#Import files and stored in the object named "Salary"

salary<-read.csv("salaries.csv")

#Check the stored information

salary

#Inspect the data frame

head(salary)

#Syntax to create a cross tabulation of rank and sex

crosstab <-ctable(x=salary$Rank, y=salary$sex, prop="r")

#Check the Result

crosstab
#Generate the cross-tabulation table

pander(crosstab)

#Scatter Diagram/Plot

#Load the package

library(readr)

#Import file and save to the object name "data"

data<-read.csv("Advertising.csv")

#Check the stored information

data

#Inspect the data frame

head(data)

#Syntax to generate the scatter plot

plot(x=data$Number.of.Commercials, y=data$Sale,

xlab="Number of Commercials", ylab="Sales",

main="Number of Commercials vs Sales", xlim=c(0,10), ylim=c(0, 100))

#Add a trend line to the scatter plot

abline(lm(data$Sales~data$Number.of.Commercials))