Assignment_3

This project analyzes housing data using R to identify important factors affecting house prices through data cleaning, visualization, and linear regression modeling.

This project focuses on the exploratory analysis and development of a Context-Aware Next-Word Prediction Engine using Natural Language Processing (NLP) techniques in R. The report analyzes large-scale text datasets to understand word distributions, linguistic relationships, and contextual patterns using unigram, bigram, and trigram models. Interactive tables and visualizations were created to explore the structure of the datasets and identify important language trends. A statistical back-off prediction strategy was designed to improve next-word prediction accuracy while maintaining efficient runtime and memory usage for future Shiny application deployment. Tools and Technologies Used: * R Programming * R Markdown * Plotly * DT Package * NLP Concepts * N-Gram Language Modeling The project demonstrates the foundational steps required for building a scalable predictive text application suitable for real-time user interaction.

Up to date tests for paper

ExamIDs2026a

Analysis for risk management group project Nvidia

Data Product 1. Does the link lead to a Shiny app with a text input box that is running on shinyapps.io? Yes, the link leads to a functional Shiny application hosted on shinyapps.io. The application contains a text input box where users can enter phrases for next-word prediction. 2. Does the app load to the point where it can accept input? Yes, the application loads successfully and allows users to interact with the text input interface without errors. 3. When you type a phrase in the input box do you get a prediction of a single word after pressing submit and/or a suitable delay for the model to compute the answer? Yes, after entering a phrase, the application predicts a single next word using the implemented n-gram back-off prediction model. 4. Put five phrases drawn from Twitter or news articles in English leaving out the last word. Did it give a prediction for every one? Yes, the application generated predictions for all tested phrases. Prediction quality varied depending on the context and availability of matching n-grams in the dataset. Slide Deck 5. Does the link lead to a 5 slide deck on RPubs? Yes, the link leads to a concise 5-slide presentation deck published on RPubs. 6. Does the slide deck contain a description of the algorithm used to make the prediction? Yes, the presentation clearly explains the n-gram prediction algorithm and the back-off strategy used for unseen word combinations. 7. Does the slide deck describe the app, give instructions, and describe how it functions? Yes, the slide deck provides an overview of the application, explains user interaction steps, and describes how predictions are generated. 8. How would you describe the experience of using this app? The application provides a smooth and user-friendly experience. Predictions are generated quickly, and the interface is simple enough for both technical and non-technical users. 9. Does the app present a novel approach and/or is particularly well done? Yes, the app demonstrates an effective implementation of predictive text modeling using lightweight n-gram techniques optimized for performance and usability. 10. Would you hire this person for your own data science startup company? Yes, the project demonstrates strong analytical thinking, practical implementation skills, and the ability to communicate technical concepts clearly.