To practice convolutional neural network (CNN) design, I worked on a classification problem that was more challenging than toy datasets but still lightweight enough to train quickly on my local machine. The following details the design of a 3-block CNN architecture and the lessons I learned from training it on clothing image data. Dataset Characteristics…
Category: Data Science
Machine learning, computer vision, natural language processing and data analysis projects.
OCR Image Search
This Flask app scans a folder of images and makes the text inside them fully searchable, using open-source Tesseract OCR. This could be helpful for someone who has a massive folder of screenshots or scanned documents and wants to find what they need without uploading everything to a cloud service. This app runs 100% locally…
Data Science CV
I published my professional resume at cv.blakerayvid.com, turning my old Word file into an HTML/CSS/JS document. It lists my skills, projects, work history, and provides a PDF download. I built it to give a fast, clear view of what I do. Thanks to this change, I can now maintain my resume with VSCode. 🔗 View…
SOAP: A New Polling Platform
Constructive political criticism online is hard to find. Discussions quickly turn mean, and even minor disagreements can escalate into major arguments. Messages often get lost if one’s audience is too small, and misunderstood words can lead to backlash. That’s where Soap comes in—a new kind of social platform designed to change the way we talk…
Sentiment Classifier
My Flatiron School Data Science Bootcamp Phase 3 Project was to address the business problem of brand reputation management by monitoring and analyzing Twitter sentiment. The goal was to develop a machine learning model that can correctly classify tweets as positive, negative, or neutral, and provide insights to improve brand perception and engagement strategies. 🔗…
Space Debris Exploration
This is an exploratory data analysis (EDA) of a Kaggle dataset I made as part of the Flatiron School Data Science Bootcamp. The slides from an associated presentation are available here. 🔗 View on GitHub