5-slide pitch for a Shiny app that predicts the next word as you type, using an n-gram language model (trigram/bigram backoff) trained on the SwiftKey blogs, news, and Twitter corpus.

Milestone report for the Data Science Capstone project. Explores the SwiftKey English blogs, news, and Twitter datasets — summarizing file size, line/word counts, word frequency, and vocabulary coverage — and outlines the plan for building an n-gram based text prediction model and Shiny app.