Photo of asphalt separated from grass with a white dividing line, by Will Francis on Unsplash.
Photo by Will Francis on Unsplash

Geofencing is a useful technique with a wide range of applications whenever one is handling location data. It can be used to signal notifications or flag alerts based on proximity to an individual or landmark. In data science, it is often used in feature engineering and creating boundaries for visualizations.

While any of the applications…


Photo by Matthias Wagner on Unsplash

I have a confession to make: I keep this blog not entirely out of a desire to express myself. I don’t necessarily have an undying need to record my thoughts and share them with the public. In fact, I began writing out of obligation—it was integrated in to the curriculum of a program for data science, in which I had enrolled.

Last week, while biking with a friend down the Blackstone River Greenway, he offered praise for a recent post of mine and commented that it was cool that my program required blogging. …


Photo by Chris Yang on Unsplash

There is a frequency distribution often seen in the natural world that on first glance may challenge the intuitions of what may be expected of how data should be distributed. It can be seen in data distributions including those of populations, financial statements, and genomic data. It also appears in compounding phenomena such as the Fibonacci sequence, and powers of 2, and is especially useful for analysis when it comes to anomaly detection.

This distribution is described by Benford’s Law, and it finds practical application in fraud detection. The law states that in many numerical sets of data that occur…


Photo by Niklas Ohlrogge on Unsplash

Recently, a friend got a call from her local pharmacy, informing her that she could come in early to get her COVID-19 vaccine, though there was a catch—she had originally arranged to receive the Pfizer mRNA vaccine, but the pharmacy only had the Johnson & Johnson’s Janssen vaccine available for the early slot.

She really wanted the Pfizer, but with J&J’s Janssen only being single dose, she decided to move forward with the offer, hoping that she would feel immediate relief and security with the understanding that she would be fairly well covered after a single shot. …


Photo by Kind and Curious on Unsplash

The first utilities that an aspiring, python-wielding data scientist must learn include numpy and pandas. All provide an assortment of tools for a data scientist to apply thorough analysis and find deep insights, yet with so many built in functions and attributes, it can be difficult to know which to use at the start.

Once the data scientist has good data in hand, they must first explore and manipulate the data to ensure that it is manageable for analysis, visualization and machine learning. According to a poll conducted by Anaconda, 45% of a data scientist’s time is dedicated to data…


Photo by Michael Schiffer on Unsplash

Convolutional Neural Networks are a class of deep learning networks that can be used for high-complexity problems which many industries face, and they even push against limiting bounds of human possibility—from detection of terminal medical conditions from magnetic resonance imaging, to allowing for the possibility of fully autonomous vehicles, and even allowing for the advance of brain-computer interfaces.

With such mind-bending possibilities, imagining where to begin with an approach to a solution is crushingly perplexing. Understanding the capabilities of these sorts of networks, however, can allow one to follow the logical processes in approaching deeply complex problems. …


Photo by andrew kamyab on Unsplash

Researchers at NVIDIA just developed a new technology that will take video streaming compression, manipulation, and deepfakes to a new standard. Dubbed One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing, the GAN-based model will be presented at the 2021 Conference on Computer Vision and Pattern Recognition that takes place in June.


Photo by Sam Moqadam on Unsplash

On December 3rd, Luminar Technologies, a company that develops sensors and software for passenger vehicles and trucks, went public.

The Autonomy Solutions segment of the company designs, manufactures, and sells LiDAR(light detection and ranging) sensors, and the related perception and autonomy software solutions necessary in utilizing such sensors. This technology is likely to be critical in the progress towards automated vehicles (despite the dismissal of this fact by some other large players in this space), and for many reasons, may be one of the most important quality of life improvements to come in the next several decades.

For those of…


Photo by Mirza Babic on Unsplash

Just days in to hands-on learning data manipulation with Pandas, my instructor paused to make a point. “Do yourself a favor,” he said to the class, with more intention than ever before, “before going too much further in learning Pandas, watch this talk on vectorization.”

The value of vectorization seemed apparent, both from our instructor’s affect when he was directing us to the clip, and from the claim that the presenter in the clip was suggesting—vectorize your code to manipulate data 1000 times faster. The video breaks down several examples of using a variety of manipulation operations—Python for-loops, NumPy array…

Mike Flanagan

Data Scientist. Cyclist. Michaelist.

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