This Shiny app uses a trigram-based natural language model trained on a handcrafted storytelling corpus to predict the next word in a phrase. Users enter a phrase with at least two words, and the app returns the most likely next word based on narrative patterns. Built with R and powered by , , and , the app showcases how simple language models can enhance creativity, writing tools, and educational experiences. Whether you're a writer, teacher, or technologist, this tool invites you to explore the future of predictive storytelling.

This document presents a concise exploratory analysis of the en_US.twitter.txt dataset from the SwiftKey corpus. It includes key summary statistics such as line counts, word totals, and average words per tweet. Through visualizations like histograms and word clouds, the report highlights frequent terms and patterns in user-generated content. A frequency table of top words complements the visuals, and a brief narrative explains the linguistic trends observed in the sample. The report is written in a clear, manager-friendly style to support decision-making and project planning. It confirms that the data has been successfully loaded and understood, and outlines next steps for building a predictive text model and deploying a Shiny app.

This presentation introduces the Ethiopian Kale Altitude Explorer, a Shiny application designed to visualize and filter Ethiopian kale accessions based on altitude. The app allows users to interactively select altitude ranges, view accession locations on a Leaflet map, and explore summary statistics and accession details. Built for accessibility and clarity, the app supports ecological research and breeding efforts by highlighting altitude-adapted accessions. This 5-slide pitch outlines the problem, features, embedded R code, and future directions for expanding the tool’s impact.

This interactive plot illustrates the altitude distribution of Ethiopian kale (Brassica carinata) accessions collected across Gurage and Gedeo zones. Each data point represents a unique accession, with altitude values ranging from 1,470 to 2,485 meters above sea level. The visualization highlights geographic variation in elevation, which is critical for understanding local adaptation, stress tolerance, and breeding potential. Accessions from Gedeo tend to occupy higher altitudes, suggesting possible resilience traits, while Gurage accessions cluster in mid-altitude ranges. This altitude-based insight supports targeted conservation and selection strategies for sustainable crop improvement in Ethiopia.

The Kale Accession Collection Map in Ethiopia is a geospatial visualization that showcases the geographic distribution of kale (Brassica oleracea) accessions collected across various regions and agroecological zones of Ethiopia. Here's a detailed description of what this map represents and why it's significant:

Assignment for the Coursera work

This project showcases an interactive data visualization built with Plotly in R, designed to explore simulated crop yield data across multiple regions.

Updated after learning about R Markdown.

This post is for Coursera course in Reproducible Research Project2