Data Analysis: Introduction to R

• R is used to perform data analysis in the Data Analysis for Biologists course

About R

• An open-source language and environment
• Used for statistical computing
• Developed and maintained by an R core group and R foundation
• R is not GUI based
• It is a command-line-based environment and language

R Community

• Thousands contribute to its development
• People create new packages and tools for R
• Part of a new project and freely available for download
• Different from tools like Excel, Sigma Plot, or SPSS that use symbols

Downloading R

• To download, visit the R website: r-project.org
• The website offers information about R
• Look for the download page to access mirror sites

R Mirror Sites

• The sites allow downloads
• Users may choose a mirror site in India
• 0-Cloud automatically redirects to the nearest and best mirror

R Compatibility and Installation

• Compatible with Linux, Mac, and Windows operating systems
• Most users will download R for Windows
• There are multiple options for download
• Starting with the base package is recommended

Base Packages

• Double-click the downloaded file to install
• What has been installed is just the basic, default R
• Packages and programs are readily available for specific types of work

R Packages

• Different packages may not come with the default R installation
• Install them as needed
• Packages related to financial data analysis are kept separate

R Web Page

• When you click task view, a consolidated list of different packages appears based on utility
• To perform cluster analysis, download the package

R Learning

• It is possible to perform operations those work with lectures and videos
• Apart from these, lots of resources, and books available on how to use R
• There are books for biologists

R Web Page Manuals

• The R web page contains organized manuals
• Download or view the manuals on the web page
• Supplement video course work with the available manual
• Install R studio, and learn how to use it

R Studio

• R studio is an integrated development environment
• Called IDE for R
• Useful for day-to-day data analysis from lab data
• Provides all the R elements and tools in one place
• Install it after installing R

Course Code

• The presenter will provide the script/code for the data analysis performed in the course
• Code can be used in the default R that has been installed, it can also be used in R studio
• R studio is better to work in
• R studio is an IDE with different versions

R Studio Versions

• One version for desktop, one is a server version
• Download the free desktop version
• Download and install the desktop version
• Installation is easy and self-explanatory

Using R

• Use R after following installation instructions, after downloading and installing R and R studio
• The basic aspects of R will be shown
• Afterwards, R studio use will he shown
• The different functions and tools in R will be shown in separate videos

R on your Machine

• When R is opened after installation, tool bars, and menus appear on top
• The window is called the R console
• A greater than sign appears which is called the command prompt

R as a Command Tool

• Therefore, commands must be written and R must be asked to execute them
• All the comments are given in this command prompt
• To perform something, put the cursor there, and clean the previous information
• Clean with Ctrl L

First Command

• Control and 1 are pressed simultaneously to clean the command prompt
• The first command will be written
• A simple example is provided
• Get the square root of 16

Square Root

• The code sqrt is entered, then type the round bracket, and enter 16
• Press enter
• The answer is calculated as 4

Variable Assignment

• To make a new variable called a
• Must assign a variables to the value 3
• Enter the text a = 3
• If a is entered, the value of a will be printed

Numerical Recognition

• To indicate that the value of x is y
• This will return an error message, because the computer does not automatically assume what number x and y are
• Numbers must be pre assigned the way that 3 was to a in the earlier step

Commmands

• First load and clean, then perform calculations
• Each input has an assigned meaning
• Those commands will be given to R

Typing

• When performed one by one, errors may be made
• To correct an error, go back and change the script
• If the same script is to be used in the future, scripts come in

Scripts

• Programs and codes where commands for data analysis are all written in order
• Load the particular script, and execute it for analysis

Directory

• It is good practice set the directory that you are working and saving the file to
• Select change directory and select C, and set the directory there
• Then, everything that is saved will go to that folder

R Editor

• The new window that comes up after selecting new script, is written as R editor
• It is not a console
• A script is just a set of R commands
• To say x, back arrow is an assignment symbol

Sequence

• How a sequence is entered to assign it to x
• Is it good practice when you are writing a script to add comments

Comments

• What that part of the program is undertaking
• A comment is entered with the # symbol
• R will know not to read these lines as code

Toolbars

• Run Line or Selection
• The function and line you are working on can be executed with one of these
• The run line button executes in the console

Numbers

• The number code
• See what the previous comment that has been done
• Has created a sequence of number with and increase of 1

Other Values

• The editor can be updated, with the new variables, with assigned values and comments

Run and Saving Scripts

• Go to save, and click save, select which folder you want to save the file to, and provide a file name
• You can then save the code
• Run all, and  the all of the selected code
• The sequence the plot appears

Re-Running

• If you close the script but want to run it again
• Go to open, and select the script to start working with it again
• The commands can then be actioned
• Can always modify the code to suit

Package Install

• All operations have appeared
• Now what to do if you have to install the package
• You have to go to the packages section

Packages

• You can install the packages option
• The program will then take you to the mirror sites
• Pick the India mirror
• The package is then automatically installed

R Studio Introduction

• After installing a default version of R, you must install R studio
• With lots of panes
• On the top pane the script is written

R Output

• At the bottom is the R console as seen in previous video lectures
• In the command prompt in the R console to clean
• Ctrl L is used to make it easier to read

Script Input

• The script can be typed in to the top line of the window
• Select the particular part of the code
• Push run to allow it to be executed

Re-Running Code

• Press Ctrl with the first, second, or second to last item to repeat functions

Code Execution

• After executing a line, immediately look to the right hand side pane

Environment

• Two tabs that have been assigned
• Another environment in History

Variables

• Values created while working are currently shown in the environments tab
• X has a set of numbers for its values 1 through 10

Alternate Execution

• Alt and enter can be pressed instead of pressing run in a line
• A value will be created in the environment line
• Y will be showing a sequence of numbers starting with 1, 4, 9 sequentially

History Tab

• The history tab shows all comments and functions that have been input

R Pane Tab

• The tabs can be organized to optimize your screen
• This can be applied on the work stream

Data Set

• The code provided, generated a dataset
• Those numbers can then be assigned those data
• The code is the executed
• They can be seen on the right plot tab
• This will apply to the R studio

Viewer Tab

• Plots appear based on the different data that are applied to different
• The variables that you will look to see different numerical values

Packages

• There could certain other packages
• They has been created which will also create an images
• Images which are created by creating local web-file
• Can be visible these other tab
• Can play with different menus

Packager Tab

• Shows all the packages which are in currently installed
• Open to be work environment at that moment, so no

Overloading

• Package will not be not working
• The easy way to make this happen and get them that you want

Curl Packages

• Can do there I automatic click get loaded
• How what is in installed can be that what to do
• All function are very simple and accessible

Tool Package Install

• Select the repository you want-CRAN
• This can also include Ggplot
• The installed items will be downloaded automatically

Useful Code

• A particular function code
• Know about function which can be a particular command

Functions

• Console can happen in help
• Console for the information that's important

Viewer Tab

• The viewer tab here for our studio here is where there is a local web file.
• There may be packages which create local files.