We’ll start with downloading the text data from SwiftKey link . The data includes blogs, news and twitters text files. They are available in multiple languages but We’ll only deal with the data files in English. Then I’ll analyze the data using text mining and NLP approaches to discover the structure in the data and how words are put together. After that, I’ll be building a predictive text model to predict the most likely next word. Finally, I’ll create a data product using shiny app (covered in part 2).

In this note, we’ll do

Some basic plots to blog, news and twitter data files in en_US directory.

• line count plot

• word count histogram plots for blogs, news and twitters data.

word clouds

After merging the three datasets, we did tokenization to the text and drew word cloud for unigrams and bigrams analysis.

Unigrams Word Cloud:

Bigrams Word Cloud:

This is part 1 of DS course capstone project by JHU in Coursera. Source code can be found on RPubs