Word Prediction Project is a Shiny app based on R code that uses a text prediction algorithm to predict the next words based on text entered by a user.

It’s possible to view my App on the follow link https://papazian.shinyapps.io/CapstoneApp/

About the source sode, please visit https://github.com/Papazian/Capstone

Synthetic information: - Friendly raphical user nterface

• Pre-load database

• Simple predictions

The goal of this exercise is to create a product to highlight the prediction algorithm that you have built and to provide an interface that can be accessed by others. For this project you must submit:

A Shiny app that takes as input a phrase (multiple words) in a text box input and outputs a prediction of the next word. A slide deck consisting of no more than 5 slides created with R Studio Presenter pitching the algorithm and app.

Data set was down loaded following the course instruction.

After loading data into R, it was created a corpus and cleaned removing punctuation, links, white space, numbers and all kinds of special characters.

This corpus was then tokenized in a database called n-grams, after this procedure It was aggregated in a bi-,tri- and quadgram term frequency matrices have been transferred into frequency dictionaries.

The result about this working method is the shinyapp that predict the next word in connection with the text input by a user.

We have two programs: server.R and ui.R The server.R loads the N-gram from my GitHub account The ui.R receives text input from user. The server.R will process the input and the next word predicted is then stored as output$textOut The text output is the next predicted word in the sentence

{id .class width=50% height=50%}