Deepjyoti Chakraborty
8th Feb 2021
This presentation is created as a guide for the Shiny app developed as part of requirement for Capstone project of the Data Science specialization
The goal of the project is to build a predictive text model which needs to be deployed with a Shiny app where the model will predict the next word as the user types a phrase in a text box and the predicted text is displayed in real-time in the Shiny app to the user. This is similar to the predictive text features that are embedded in keyboard apps in mobile phones.
Shiny app - https://deepjyoti.shinyapps.io/Application_Text_Prediction_Capstone_Project/
Github repository - https://github.com/djch1989/Capstone-Project
The data for this project is from a corpus called HC Corpora which contains text data from Twitter, Blogs and News. The English text data from this data is used for the project wherein the data is first cleaned and preprocessed.
Steps of cleaning and preprocessing:
The prediction model is built using the .Rdata files of n-grams as input and the algorithm used is Katz Backoff
The working behind the model:
The Shiny App developed for the Capstone project is shown below along with instructions:
Screenshot of Shiny App