The Nutrient-Weight Confabulation

Image for post
Image for post
Photo by Charles Deluvio on Unsplash

One common criticism of a plant-based or vegan diet is that you can’t get enough protein. I would like to dispel this myth by showing the importance of choosing the right basis of measuring nutrition content and discuss the implications this has on nutrition as a whole.

The Wrong Measurement

If I had a teaspoon of melted butter, which gets 100 percent of its calories from fat, and I pour it into a glass of water, I can now say to you that it is nearly 100 percent fat-free. …


Image for post
Image for post
Photo by Matese Fields on Unsplash

Data Science Discovered in an Unexpected Place

My journey into data science began in a place I never could have expected. During my time in undergrad studying mathematics, I picked up the well-renowned book “The Power of Habit” by Charles Duhigg. I have always been interested in behavioral psychology, and several of my friends had recommended it to me. It’s largely a book about how habits are formed, changed, and cleverly utilized in business scenarios, but Duhigg is crafty and explains the power of habit through several intriguing and unforgettable stories.

At the time, I was studying to become a math teacher, but my interest in academia was waning, and I was considering other options. Two of the stories Duhigg told in his book included brilliant uses of data science that made huge impacts in their respective fields. The stories immediately grabbed my attention and opened my eyes to the power of data. I remember thinking to myself, “man, if I could get a job doing this… that would be a dream!”


Image for post
Image for post
Photo by Adrian Korte on Unsplash

As a lover of both music and data, the idea of combining the two sounded enticing. Innovative companies such as Spotify and Shazam have been able to leverage music data in a clever way to provide amazing services to users! I wanted to try my hand at working with audio data and try to build a model that could automatically classify a song by its genre. The code for my project can be found here.

An automatic genre classification algorithm could greatly increase efficiency for music databases such as AllMusic. It could also help music recommender systems and playlist generators that companies like Spotify and Pandora use. …


Image for post
Image for post
Image from Gradiom

If you are anything like me, trying to understanding the mel spectrogram has not been an easy task. You read an article only to be lead to another… and another… and another… on and on it goes. I hope this short post will clarify some of the confusion and explain the mel spectrogram from the ground up.

Signals

A signal is a variation in a certain quantity over time. For audio, the quantity that varies is air pressure. How do we capture this information digitally? We can take samples of the air pressure over time. The rate at which we sample the data can vary, but is most commonly 44.1kHz, or 44,100 samples per second. …

About

Leland Roberts

Data Storytelling | Math | Driven by Curiosity

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store