Repository Summary: R Machine Learning

This repository contains comprehensive R coding solutions and reports for three distinct machine learning projects. Each project is stored in its respective folder and tackles a unique analytical task using various statistical and machine learning techniques. The final reports for each project are available in both PDF and HTML formats, providing detailed insights, results, and visualizations.

Projects Overview

1. Brexit Vote Analysis:

   • Folder: Brexit Vote Analysis
   • Description: This project analyzes the demographic factors influencing the Brexit vote using logistic regression. It examines the impact of variables such as social class, median income, age, education, and foreign-born population on the likelihood of an electoral ward voting to Leave the EU. The analysis includes model interpretation, alternative approaches, and comparison with visual trends presented by the Guardian newspaper.

2. Olympic Medal Prediction:

   • Folder: Olympic Medal Prediction
   • Description: This project investigates how the number of Olympic medals won by a country can be predicted based on population and GDP. It employs linear regression models, log-transformed inputs, and K-means clustering to analyze the data. The project evaluates model performance and selection, providing insights into the relationship between national characteristics and Olympic success.

3. Mushroom Classification:

   • Folder: Mushroom Classification
   • Description: This project focuses on classifying mushrooms as edible or poisonous using visual and olfactory characteristics. It compares the performance of logistic regression, decision trees, and random forests, tuning each model for optimal accuracy. Cross-validation and statistical tests are used to determine the best predictive model, showcasing the application of machine learning techniques to a classic dataset.

Summary

This repository demonstrates the application of various statistical and machine learning techniques to solve real-world problems using R. It includes detailed analyses, model evaluations, and insightful results for predicting Brexit voting patterns, Olympic medal counts, and mushroom edibility. The repository serves as a valuable resource for understanding the practical use of machine learning in different contexts.