Data Science Capstone

For the Data Science Capstone project offered by Johns Hopkins University through Coursera, JHU partnered with SwiftKey a popular keyboard replacement app for mobile devices that uses predictive analytics to predict the next word a user types.

This presentation is part of the Data Science Capstone project. The objective of this project is to build a predictive text app such as SwiftKey. To build this engine, we use the data from HC Corpora which contains a large number of sentences.

For the Capstone project, the main goal is to build a Shiny application that is able to predict the next word.

To create the word prediction app, we took the following steps:

• From the HC Corpora dataset, we cleaned the data and then tokenize the data into n-grams. We created bigrams, trigrams and quadgrams.
• These n-grams are then stored in term freqency matrices.
• The matrices are then used to do word prediction.

The app is hosted on ShinyApps.io

The R Presentation is available at RPubs.

Source code for ui.R and server.R files and the word prediction app are available in my GitHub repository.

The interim milestone report is available here