Examine match scores using Q-grade features

Previously, I looked at how well each sub-metric of a Q-grade correlates to the total score, and some interesting notes popped out for certain years and regions. Now, I aimed to see how the sub-metrics could be used as a feature descriptor and compared to each other. Would this reveal anything about coffee similarities across region, year, or process method?

Similarity

To compute a similarity score, each vector of 10 sub-metrics was compared to all the others using Root-mean-square:

Image for post
Image for post

These scores were computed for all coffees vs all coffees as seen below colorized by score and sorted by country:

Image for post
Image for post
Image by author as are all the images in this article.

However, in the breakdowns below, I adjusted each graph to be between 0% and 100%. 100% doesn’t mean perfect match, and 0% isn’t no match. It’s relative to the data in each chart where 100% is the maximum similarity (most similar) and 0% is the minimum similarity (least similar). …


300+ beans with grades and prices

I love buying green beans from Sweet Maria’s. I’ve been roasting for 6 years now, and I’ve gotten the majority of my green beans from them. I was curious though, how well Q-scores trended with cost, so I pulled all their data and did some simple analysis. In short, I found a general trend with cost so you have to pay more to get higher scored beans, which should be higher quality. I also found certain features correlate more to cost than other.

The main caveat is that these beans are based on what Sweet Maria’s procures, which is based in part on their customer base. So any analysis can not generalize outside of Sweet Maria’s due to their curation. It would be very interesting to do this type of analysis across multiple sellers, but their data was not as easily accessible as Sweet Maria’s. …


Data on extraction vs coffee roast age

I’ve been collecting data on my shots for almost 2 years. I wanted to look through that information to see if I could see any trends, particularly the age of a roast. The main caveats are:

  1. My methods have improved over time.
  2. My tastes have changed.
  3. My tasting palate has expanded.

So I normalized the data to give a fairer comparison. I found taste and extraction improved over time up to 5 weeks post-roast. I did not find a taste drop off past three weeks, which is what is typically suggested by roasters. …

About

Robert McKeon Aloe

I’m in love with my Wife, my Kids, Espresso, Data Science, tomatoes, cooking, engineering, talking, family, Paris, and Italy, not necessarily in that order.

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