Next Word Prediction - Data Science Capstone

This repository contains a Next Word Prediction project built in R and Shiny as part of the Data Science Capstone. The goal is to create a predictive text model that suggests the next word given a phrase. This project was completed as part of the Data Science Capstone from the Johns Hopkins University Data Science Specialization on Coursera.

📅 Completed on October 11, 2016

---

📂 Repository Structure

.
├── ShinyApp/
│   └── NextWordPrediction/   # R/Shiny app for interactive prediction
├── SlideDeck/                # Project presentation slides
└── README.md                 # Project documentation

---

🚀 Getting Started

Prerequisites

• R (version 4.0 or higher recommended)
• R packages:
  • shiny
  • stringr
  • data.table
  • (add more based on your actual code)

Install packages in R:

install.packages(c("shiny", "stringr", "data.table"))

Running the Shiny App

1. Navigate to the Shiny app folder:

   setwd("ShinyApp/NextWordPrediction")

2. Run the app:

   library(shiny)
   runApp()

This will launch the interactive web app where you can type a phrase and get next-word predictions.

---

📖 Project Overview

The app predicts the next word by analyzing text data and applying natural language processing techniques.
It uses n-gram models trained on text datasets to provide probable next words.

Key steps include:

• Data preprocessing (cleaning, tokenization, removing punctuation/stopwords)
• Building n-gram frequency models
• Prediction logic based on most frequent n-grams
• Shiny app interface for real-time predictions

---

🎯 Features

• Input a phrase and get next word suggestions
• Lightweight Shiny interface
• Supports interactive exploration of text prediction

---

🖼️ Usage Example

Here’s how the Shiny app looks in action:

---

📊 Slide Deck

The SlideDeck/ folder contains the presentation that explains:

• Project motivation
• Methodology
• Model design
• Results and challenges

---

🤝 Contributing

Contributions are welcome!

1. Fork this repository
2. Create a new branch (git checkout -b feature-branch)
3. Commit your changes (git commit -m "Added new feature")
4. Push to the branch (git push origin feature-branch)
5. Open a Pull Request

---

📜 License

This project is licensed under the MIT License (or update with your actual license).