This project involves comprehensive analysis of NHS Digital Data to derive insights and improve healthcare services. It demonstrates advanced skills in data engineering, analysis, and visualization within the healthcare sector.

Key features:

• Web scrapes data from NHS Digital publications using Python
• Stores data efficiently in PostgreSQL database using SQLAlchemy
• Performs extensive data cleaning and preprocessing
• Implements sophisticated data analysis and time-series analysis
• Creates interactive visualizations and dashboards
• Optimizes performance through multithreading and chunked data uploading
• Follows best practices in Python programming and data engineering

This comprehensive data analysis project for Turtle Games, an online game retailer, aims to improve overall sales performance through advanced data analysis techniques and machine learning models.

Key features:

• Loyalty Points Modelling using various regression models (98% R-squared achieved)
• Customer Segmentation using K-means clustering
• Sentiment Analysis of customer reviews using NLP techniques
• Personalized Product Recommendations for each customer segment
• Interactive dashboard creation using HTML/CSS/JavaScript and Plotly

The Sailing Dashboard is a comprehensive tool for analyzing sailing performance data. It processes GPX files from various recording devices (such as Garmin watches or Strava) to create detailed performance metrics for sailors.

Key features:

• Parses GPX files to create individual dataframes for each sailing session
• Calculates heading and speed from GPX data
• Determines sailing mode (upwind, downwind, or reach) based on calculated metrics
• Includes a widget to update mark locations and course type, which saves race information to a JSON file
• Planned future development: Web application for clubs and regattas, allowing competitors to upload their data and view race results