Blog Archive

Check out all my posts with this blog archive. Click on a headline to read the teaser.

First looks at the Million Song Dataset › What To Listen To (Part I: Basic Intro)

For my final project at Metis, I'm looking at the Million Song Dataset in order to build a music explorer / recommendation engine based on song clusters by low-level sound features Read More ›

NLP and The Guardian › I Like Commas

Predicting author or topic of news article sentences from punctuation and stop words Read More ›

Introduction to image classification › It's a Bird, It's a Plane!

For this project, I got to explore the process of object recognition for image classification, including feature extractions and visualizing my results with D3.js Read More ›

Investigating foreign films in US markets › Crouching Tiger, Hidden Data (Part II: Linear Regressions)

In order to predict the US domestic gross of foreign films, I turned to linear regressions, and discovered that things don't always work out as planned. Read More ›

Investigating foreign films in US markets › Crouching Tiger, Hidden Data (Part I: Web Scraping)

The first step in answering any question involves getting some data. In this case, that meant web scraping. Read More ›

A look at New York MTA data › Riding on Trains at Night

I spent my first week of Metis working on a project to analyze the movement of New Yorkers through MTA turnstile data. Read More ›

First Post!

Read More ›