Operationalizing SKLearn with Azure Machine Learning

web_servic-ified

Hello World!

So I just completed an incredible project with Brain Thermal Tunnel Genix, where I learned so much about pattern recognition, machine learning and taking research and algorithms and pushing those into a production environment where it can be integrated into a real product.  Today’s article takes those lessons and provides a sample on how to perform complex modelling and operationalize it in the cloud.  The accompanying Gallery Example can be found here.

Continue reading

Functional Coding in Python – The right way

Hello World!

So I’ve been on a bender with this Python thing not having proper functional piping.  I just can’t beleive it was not built in.  Every language should have this.  It cleans up your code so much its unbeleive-able.  Fear not however, I have built one for Python :D.  Now I just need to figure out how to create pip packages.  Anyways, lets just do a quick walk through on what it is, how it works etc.

Continue reading

Machine Learning Study Group Recap – Week 4

Hello World,

So here we go with another recap. This week we did a deep dive into binary classification using Logistic Regression. Logistic regression and binary classification is the underpinnings for modern neural networks so a deep and complete understanding of this is necessary to be proficient in machine learning.

Continue reading

Basic Gradient Descent

Hello World!

In this article we are going to cover a simple version of Gradient Descent. It is important to note that this version of gradient descent is using Sum of Squares as its cost function to reduce. This implementation utilizes vectorized algorithms. Lets start off with…

What is Gradient Descent

Continue reading

R Jump Start – Beautiful Data Visualizations

Hello World!

This is a video tutorial for building beautiful data visualizations in R.  You will learn about what Data Viz is, basic charting libraries and finally a full walk through for how I built the Miami Jail Interactive graphic you see in this article.

Part 1: Introduction to Microsoft R Open.

Part 2: Introduction to R Data Structures

Part 3: Data Manipulation with R

Part 4: Beautiful Visualizations with R

Continue reading

Pi for Brains Robot – Part 1 – Setup

Hello World!

Welcome to my blog’s version of the #IDevThis project that will be coming out.  This full series will be made available on instructables and channel9 once it has been completed as a full unit.

Pi for Brains Robot (aka Danger-Bot)

These days it seems like I’m always dealing with a robot, they are on the phone, in my car, at the grocery store, just about everywhere.  It also seems like every single one of them had Pie for brains, because it just couldn’t do what I told it to.  This project is going to build a robot that ACTUALLY has PI for brains!  Get out your breadboards, your Raspberry Pis and follow along. We will use a high performance cross platform robotics framework, Cylon, Raspberry Pi, and an Arduino Robotics Kit to build this internet connected robot.

Continue reading

First Look – Intel Edison and Grove Starter Kit

Hello World!

In an attempt to learn something that I can connect with a new crowd on, I’ve decided to pick up embedded systems, IoT, Robotics, whatever the cool kids are calling it these days.  So I called up my buddies over at Intel and asked if they could ship me something useful.  Boy did they ship me something fun!  This article is all about playing with the Grove Starter Kit and Intel Edison + Arduino Board.

Continue reading

How to Datamine Zillow

Hello World,

As many of you may know at this point, I am relocating to South Florida.  Final location to be determined, but will probably be renting around Pompano Beach or Fort Lauderdale while working out of Venture Hive and the Microsoft Fort Lauderdale Offices.  So what does this have to do with Zillow?  Well, It has EVERYTHING to do with Zillow.  What I’ve found while searching for homes is that between Realtors, Zillow and Trulia, they really just don’t have a predictive analytics solution that works for me.  So I decided to give a shot at AzureML to mash together a few datasets to send me notifications more to my liking than is currently being sent.  So step 1 in this plan is to data mine Zillow.  Luckily, Zillow has an api for that.  Or if you are feeling particularly frisky, Zillow gets their data from ArcGIS (example for Raleigh).  So lets get cracking…

Continue reading

Intro to C# – Switches and Errors

Hello World!

One of my good friends is going through a reskill to become a software developer, so I have decided to help him out, because, isn’t that really my job? Help everybody be successful with programming? Anyways, this has provided some new insight into challenges people face learning to code that you just don’t remember as a seasoned developer. Anyways, he was working through some code and sent me his code to look over. I want to go over both code bases and why I chose to change even code as simple as that to what it has become. The code written derives from the Microsoft Virtual Academy Intro to C# series, located here.

Continue reading

Manage Azure Blobs with F#

Hello World!

So you are going to notice a slight shift in this blog to start incorporating not only video game development, but hardcore data analytics.  As part of that shift, I am going to start incorporating F# into my standard set of languages as it is the language of hardcore data analytics if you roll with the .NET stack.

This particular article is about building a console based blob manager in F# instead of C#.  The very first thing I noticed about using F# to manage my blobs as opposed to C# is just the sheer reduction in lines of code.  The code presented here is a port of the C# article located here.  This code will eventually make its way into a production system which is part of a big data solution I am building.  New data sets that we acquire will be uploaded into blob storage, an entry stored into a queue, with a link to the data set.  Once a job is prepared to run, the data will be moved to Hadoop to do the processing and then stored in its final location.  So step 1 is…Store data in Blob storage.

Continue reading