# function to clear the console, plots and environment

clear$\_$all $<-$ function$()\{$

# clear console

cat$("\backslash 014")$

# clear plots

if $($dev$.$cur$()>1)$ dev.off$()$

while $($dev$.$cur$()>1)$ dev.off$()$

# clear environment $($global environment$)$

rm$($list $=$ ls$($envir $=.$GlobalEnv$),$ envir $=.$GlobalEnv$)$

message$("$Console$,$ Plots, and Environment cleared!"$)$

$\}$

#$----------------------------------------------------------------------------------------------$

# function to install and load packages

install$\_$and$\_$load$\_$packages $<-$ function$($packages$)\{$

# check for packages that are not installed

new$\_$packages $<-$ packages$[!($packages $\%$in$\%$ installed.packages$()[,$ "Package"$])]$

# install missing packages

if $($length$($new$\_$packages$))\{$

install.packages$($new$\_$packages$)$

message$("$The following packages were installed: $",$ paste$($new$\_$packages, collapse $=","))$

$\}$ else $\{$

message$("$All packages are already installed."$)$

$\}$

# load all the packages

sapply$($packages$,$ require, character.only $=$ TRUE$)$

$\}$

#$----------------------------------------------------------------------------------------------$

# example usage

clear$\_$all$()$

packages$\_$to$\_$install $<-$ c$("$ggplot$2",$ "GGally", "PerformanceAnalytics", "ggcorrplot"$)$

install$\_$and$\_$load$\_$packages$($packages$\_$to$\_$install$)$

#$----------------------------------------------------------------------------------------------$

# simple scatter plot using base R

x $<-$ c$(1,2,3,4,5)$

y $<-$ c$(5,4,3,2,1)$

plot$($x$,$ y$,$ main$=$"Basic Scatter Plot",

xlab$="$X$-$axis", ylab$="$Y$-$axis", col$=$"red",

pch$=19)$

#$----------------------------------------------------------------------------------------------$

# example of a simple scatter plot using ggplot$2$

data $<-$ data.frame$($x $=$ c$(1,2,3,4,5),$

y $=$ c$(5,4,3,2,1))$

#install.packages$("$ggplot$2")$ # or enter the package name in packages$\_$to$\_$install above

#library$($ggplot$2)$

ggplot$($data$,$ aes$($x $=$ x$,$ y $=$ y$))+$

geom$\_$point$($color$=$"blue"$)+$

labs$($title$=$"Scatter Plot with ggplot$2",$ x$="$X$-$axis", y$="$Y$-$axis"$)$

#$----------------------------------------------------------------------------------------------$

# $1.$ data exploration

#$----------------------------------------------------------------------------------------------$

# load the built$-$in mtcars dataset $($there are several datasets in R$,$ such as: iris, airquality, etc$)$

data$($mtcars$)$

# dataset description

$?$mtcars

# get the dimensions of the dataset: rows, cols

dimensions $<-$ dim$($mtcars$)$

# print the number of rows and columns

cat$("$Number of rows:", dimensions$[1])$

cat$("$Number of columns:", dimensions$[2],$

$"$

$","($mtcars dataset$)")$

print$($paste$("$Number of columns:", dimensions$[2]))$

# print column names

print$("$Column Names:"$)$

colnames$($mtcars$)$

# print row names

print$("$Row Names:"$)$

rownames$($mtcars$)$

# print the first few rows

print$("$First Few Rows:"$)$

head$($mtcars$)$

# print the first $20$ rows

head$($mtcars$,20)$

# print the last few rows

print$("$Last Few Rows:"$)$

tail$($mtcars$)$

# print the entire dataset

print$("$Entire Dataset:"$)$

print$($mtcars$)$

# print column names and their data types

print$("$Structure of Dataset:"$)$

str$($mtcars$)$

# summary statistics of all columns

summary$($mtcars$)$

# print specific rows and columns

print$($mtcars$[1$:$5,1$:$3])$ #$($e$.$g$.,$ rows $1$ to $5$ and columns $1$ to $3)$

print$($mtcars$[,1])$ #first col values

print$($mtcars$[2,])$ #second row values

print$($mtcars$[2,1])$ #second row, first col value

# subset the mtcars dataset with multiple conditions

subset$\_$mtcars $<-$ subset$($mtcars$,$ mpg $>20$ &

hp $<150$ &

cyl $==4)$

subset$\_$mtcars # we need to run this line to visualize the result stored in subset$\_$mtcars df

# calculate and display unique values for each column

sapply$($mtcars$,$ unique$)$

# calculate the range for each numeric column, ignoring NA values

sapply$($mtcars$,$ function$($col$)$ range$($col$,$ na$.$rm $=$ TRUE$))$

#$----------------------------------------------------------------------------------------------$

# $2.$ missing values $($in R$,$ NA stands for "not available"$)$

#$----------------------------------------------------------------------------------------------$

# check if any NA values are present in the dataset

any$($is$.$na$($mtcars$))$

# count total NA values in the dataset

sum$($is$.$na$($mtcars$))$

#$-----$

# there are no NA values in mtcars dataset

# introducing NA in a new dataset: my$\_$dataset

rownames$($mtcars$)<-$

Step by Step Solution

There are 3 Steps involved in it

1 Expert Approved Answer

Step: 1 Unlock

Question Has Been Solved by an Expert!

Get step-by-step solutions from verified subject matter experts

Step: 2 Unlock

Step: 3 Unlock

Students Have Also Explored These Related Programming Questions!

Q:

CSE 110 - Introduction to Computer Science I CSE 110-Car Loan Program PROJECT #1-File handling, Loops, and Functions Modify the Car Loan program that computed car loan information (or create a new...

Q:

1. Twenty-One Problem Expected Duration: 2-3 hours For this project you will implement a game of Twenty-One with a dealer and one player. It is possible to implement this game in procedural stylebut...

Q:

I need help with this. It is c code! This is my 3rd time posting because no one can help. Description This homework project involves creating a program to play the game of connect 41 The core concept...

Q:

I believe everything needed is provided below In C# with the correct classess pls with explanation rubric is shown at the end would be appreciated thank you in advance, track stores the current...

Q:

mplement Code In Pyhton3 Assignment Overview You are tasked with creating an application that uses a GUI that simulates a simple banking interface similar to an ATM / online banking using the Python...

Q:

Implement Code In Pyhton3 Assignment Overview You are tasked with creating an application that uses a GUI that simulates a simple banking interface similar to an ATM / online banking using the Python...

Q:

Python Programming Programming Project Pica Centro 2 Important notes: please write the Pica Centro program in Python 2 only and please need to include a main() function and a single call to get that...

Q:

The following members must be in a class called BITSET: 1. A private vector of integers. This will be where the actual bitset data is stored. The user may specify any integer as a bit, and your class...

Q:

PLEASE USE THE COMPILER IN THE LAST IMAGE TO COMPILE THE CODE. Overview You will be designing a BITSET class. This allows me to store a large number of Boolean values (true/false). The purpose of...

Q:

Python Programming Programming Project Pica Centro 3 Important notes: please write the Pica Centro program in Python 2 only and please include a main() function and a single call to get that logic...

Q:

Air enters a compressor with a stagnation pressure of 100 kPa and a stagnation temperature of 350C, and it is compressed to a stagnation pressure of 900 kPa. Assuming the compression process to be...

Q:

What is the function of each of the following components of the protein-synthesizing apparatus: (a) aminoacyl-tRNA synthetase, (b) release factor 1, (c) peptidyl transferase, (d) initiation factors,...

Q:

11. What led to the passage of the Public Company Accounting Reform and Investor Protection Act of 2002?

Q:

The following graph plots a supply curve (orange line) for a group of recent graduates looking to sell used art history textbooks. Each seller has only a single used textbook available for sale....

Previous Question Next Question