East side of Mount Mansfield, Vermont

My fascination with maps, especially relief maps, goes back to childhood. Both of my parents were teachers: maps were all over the house. In college for my senior fine arts project I made a relief map of a hypothetical location out of wood.

Today there’s easy and affordable access to laser cutters and 3D printers, and their potential applications appear endless. While a Data Innovation Fellow at the Vermont Center for Geographic Information and a member at Generator, a Burlington maker space, I’ve found how the mapping and maker worlds intersect through the 3D modeling and printing of terrain and…


It is easy to forget how important time in when it comes to understanding the world. Change over time is what feeds most prediction engines and it is vital for understanding how something is increasing or decreasing. There are a variety of tools that can be used for geospatial time-series data, from libraries for Python and packages in R to the plugins or built-in functionality in ArcGIS and QGIS.

The beginning of my geospatial time-series started with exploring the Decennial Census (which is collected every 10 years) for Vermont from 1791 to 2010 (gather ffrom the Vermont Historical Society here)…


It is easy to forget in a time of huge advances in Computer Science and Artificial Intelligence that by it’s very nature models are not perfect. One of the greatest headaches is how to tackle measuring how accurate a model is in contrast to the know truth.

The first step is always understanding the cost of errors. Would you rather err on guessing something is true when it is not, or not guessing it at all. Sometimes it may be cheaper to lose a customer then spend the hours retaining them, or conversely the cost of vaccinations for those that…


It is easy to forget how much data is stored in the conversations we have every day. With the evolution of the digital landscape, tapping into text, or Natural Language Processing (NLP), is a growing field in artificial intelligence and machine learning. This article covers the common pre-processing concepts applied to NLP problems.

Text can come in a variety of forms from a list of individual words, to sentences to multiple paragraphs with special characters (like tweets for example). …


Hack·a·thon — an event, typically lasting several days, in which a large number of people meet to engage in collaborative computer programming.

The journey began shortly after starting my fellowship at the Vermont Center for Geographic Information (VCGI), the State of Vermont’s office of geospatial data and technology, when a friend reached out from HackVT. HackVT is a technology focused event and they were interested in using the State’s geospatial data in their 24 hour hackathon event. It proved to be a unique way to collaborate with local organization and technical talent to promote VCGI’s mission and the Open Geodata…


Roadside Marker Locations around Burlington, VT

Geospatial data has become an increasingly important subject in the modern world and what is where has become a driving force both in tradition realms as well as the rapidly growing digital one.

Geospatial data usually refers to data with Latitude/Longitude or other reference points to geographic locations along with attributes that describe features like images, points, lines or polygons. In truth all data is geospatial and includes anything with an address, city, region, state or country. …


When I was a kid I was watching Star Wars with my Dad and he asked me if the dogfighting spaceship were going up or down. My response, “Dad, that’s silly, there is no up or down in space!”

In space there is no constant reference when you are in space to make an “up” or a “down” and in many ways the same problem is presented when providing a reference for terrestrial data. This problem has evolved in complexity over the years but at the core it still is the same.

The power of Geographic Information Systems (GIS) is…


In an increasingly data driven world, charts have started appearing everywhere from news feeds to activity tracker. Some are beautifully visualized (the NY Times Visualization Lab does amazing work) but more often than not the quality can be lacking and the results confusing or even misleading.

We use visualizations to compress data to create intuitive understanding of trends. We will go through some of the basic mistakes that can be made when presenting data, but first a quick look at the anatomy of a chart:

Elements of a visualization can be modified in ways that can either emphasize or diminish…


Burlington is a small city on the shore of Lake Champlain in Vermont with a population of 42,000 people give or take. The city has a portal for their Open Data project that they describe as:

“Funded in part through a grant, the City has committed to a trial partnership with Socrata, a cloud-based software company facilitating the “open data” shift for state and city governments like Vermont and New York City. The arrangement has enabled Burlington to post up to 20 datasets on its open data platform. …


In the spirit of my ongoing series like the Titanic Kaggle competition, here is another machine learning Kaggle competition. This time it is for using regression to figure out the missing house prices.

As always here is the shortcut to my submission here

The Data

You never knew you wanted to go to Ames, Iowa but by the end you will know more than you ever thought possible from a data set compiled by Dean De Cock. …

Kendall Fortney

Self-taught Data Scientist focused on Python, machine learning and Geospatial Data with degree in Art and years of experience in tech in Vermont.

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