Wooo ! above arrangement of words is enough to blow my mind and I am sure your too,isn’t it?

This arrangement is a word cloud.

Lets go to its standard definition.

A word cloud is an image composed of words used in a particular text or subject, in which the size of each word indicates its frequency or importance.

If you are interested to go deep in R and want to learn how ot make word cloud using R then read the post further ,otherwise you can do this much more easily online with Wordle.

Step 1:Install R 

If you don’t have R installed the do it by the following link.

r-project.org  and follow download and installation steps.

Step 2:Install RStudio

Rstudio is a graphical interface to R.It provides all tabs and windows: command line, workspace, history, files, plots, packages and help in the same place.So it become quite interesting and easy to work on it.You can install Rstudio from here :rstudio.com

Step 3:Choose a text file

(i)Create a new folder(I named it ‘temp’) in you default directory.

(ii)Create a new text document(I named it ‘far.txt’) inside the newly created folder(In my case ‘temp’) and paste the content of which you want to create ‘word cloud’.

Step 4:Install required Packages in R

Open Rstudio and Goto ‘Tools’ t -> ‘Install Packages’


Go to bottom right Window

Packages -> Install

(i)text mining package (‘tm’)

(ii) wordcloud package (‘wordcloud’)

If any of the other package would be required Rstudio will indicate you and then download accordingly all the required packages.

Tick all the required packages or you can include them by typing “library(package name)” in the console.

Step 5:The Data Process: Text mining,clean-up,word cloud

Now we will load our interest text file in Rstudio and then clean it up so that the word cloud make sense;such as removal of words like “the” and other similar words.

We need to load text file in Corpus, so that ‘tm’ package can process.A corpus is a collection of document.Note that following command loads everything in the specified directory(i.e why we have created new folder ‘temp’ with one text document ‘far.txt’).

wordcloud <- Corpus (DirSource("temp/"))

To see whats there in corpus type the below command.

> inspect(wordcloud)

This should print the content in the screen.


Now we will clean the data according to the requirement.

Look at the following command.Type one command at the time.We have used tm_map function which comes with tm package.

(i) This command removes all the white spaces in the document.

> wordcloud <- tm_map(wordcloud, stripWhitespace)

(ii)This command make sure all of your data is in PlainTextDocumen and all your non-standard transformation has been standarised.

> wordcloud <- tm_map(wordcloud, PlainTextDocument)

(iii)Below command remove English common words like ‘the’ (so-called ‘stopwords’)

> wordcloud <- tm_map(wordcloud, removeWords, stopwords("english"))

(iv)Following command carry out text stemming.

> wordcloud <- tm_map(wordcloud, stemDocument)

Note:Depending on what you want to achieve you could also explicitly remove numbers and punctuation with the removeNumbers and removePunctuation arguments.

Now comes the magic part!

If all the above process went perfectly fine ,then get ready to see the magic.Type the following command to see your word cloud.

> wordcloud(wordcloud, scale=c(5,0.5), max.words=100, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, "Dark2"))

After you run this command you will see similar to below word cloud.


Let me briefly explain some terms of above command and for the detain go

 scale : controls the difference between the largest and smallest font.

max.wordslimit the number of words in the cloud.

rot.per : percentage of vertical text.

colors : symbolising your data, from single colors.

If you want to manually remove some of the words type the following command.

> wordcloud <- tm_map(wordcloud,removeWords,"subject")

and again run wordcloud() command to get the wordcloud.

> wordcloud(wordcloud, scale=c(5,0.5), max.words=100, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, "Dark2"))


Lets limit the number of words to 500.

> wordcloud(wordcloud, scale=c(5,0.5), max.words=500, random.order=FALSE, rot.per=0.35, use.r.layout=FALSE, colors=brewer.pal(8, "Dark2"))



You have learned to create word cloud.

Have fun ! 🙂