Learn how to use Docker when sharing data analysis scripts — NOTE: This was written on my personal GitHub website on Apr 15, 2019. I’m republishing here, as this is still very useful for personal data science projects. What is Docker? Docker is a tool designed to make it easier to create, deploy, and run applications by using containers. Containers allow a developer to…

A top tech company’s resurgence has a lot in common with a professional sports league’s fast-paced evolution — NOTE: This article was written in April 2017. I published it in my company’s newsletter when I was still working at Microsoft. A lot has changed since then. All my friends joke about how much of an NBA junkie I am. I grew up mesmerized by the clutch fade-aways by…

The world is always changing — “So. What do you do?” “Oh, I’m a data scientist at <so and so>” “Oh wow! You’re going to write machines to take over our jobs, huh?” I hear this conversation a lot at parties. And I chuckle. It’s true. Artificial intelligence and machine learning has made considerable strides in…

Utilize a python library to speed up data processing tasks for personal data science projects — NOTE: This was written on my personal GitHub website on Apr 23, 2019. I’m republishing here, as the package is still very useful for personal data science projects. Introduction Scaling applications through distributed systems have surged in popularity. With more data being stored, more computing resources are needed to process/clean/store/transfer such…

Decide which deep learning framework works best for you — So, you want to get your hands wet in Deep Learning. You google common libraries and pulled up this list. Theano Keras TensorFlow PyTorch CNTK That’s just the tip of the iceberg. There’s far more deep learning libraries out there. Top 16 Open Source Deep Learning Libraries and Platforms - KDnuggets Deep Learning is an continuously-growing, popular part of a broader family of machine learning methods, based on data…www.kdnuggets.com

Overview of how object detection works, and where to get started — Note: This assumes you have a general idea of what convolutional neural networks are. If you need a refresher, this IBM post is excellent. You know how convolutional neural networks (or CNNs) detect and classify images. But you can expand on that CNN to detect objects within that image. How…

Using multi-linear regression to analyze player impact — Oakland Athletics general manager Billy Beane needed to construct a good baseball team, even though they lost all three stars to free agency (Johnny Damon, Jason Giambi, and Jason Isringhausen). Given they were a small market team, the Athletics didn’t have the money, location, or limelight to retain the big…

How to write and optimize serverless functions effectively — Serverless is not a buzzword. It’s a misnomer. The idea that you can run applications without a server sounds like black magic. How on earth can you avoid the expensive costs of having a server run 24/7? The truth is that you can’t. Serverless is nothing more than a server…

Create a pipeline that extracts data from PDF documents via OCR and human review in 13 minutes — Optical character recognition (OCR) tools such as Amazon Textract do a fantastic job in extracting text information from various files: PDFs, PNGs, JPEGs. While these tools have done a fantastic job in collecting clean data (and subsequently help building better models), they are far from perfect. Tools still haven’t perfected…