This past Friday I resigned from my position as a Civil Engineering Manager at SYSTRA, my employer of the last 6+ years. I did this because an opportunity of a lifetime knocked on my door, an opportunity that will give me a chance to pursue my passion in an exciting and growing field. In short, an opportunity to follow my dreams. I've accepted a position as a senior consultant at Rapidminer, in their Boston headquarters, and I couldn't be more excited about this. Not only will I be leveraging my engineering, predictive analytic, presentation/teaching and Rapidminer skills, but I will be empowering organizations to utilize and adopt Rapidminer in ways they've never dreamed of. ...

I was fooling around yesterday with the Random Forest Tree operator in Rapidminer because of this post on Revolution Analytics (great website BTW). I downloaded their data set, imported it into a repository, built a simple process, and sampled a % of the data. I did this all without the programming that R demands. Oh, I even got a nice plot of tree. Now, I'm not knocking R. I have great respect for the language and I dabble in it myself, but if I want fast results (*ahem*, rapid), I turn to Rapidminer ever time.

I'm playing around with the Rapidminer Finance and Economics extension, from Broad Reach Analytics, and I like it. It's a slick and fast way to get financial data into your processes and there are lots of operators that let you get data from Bloomberg, the World Bank, and Yahoo. It would normally take me 30 minutes to an hour to cobble together stock quote data from Yahoo into a spreadsheet, then validate the dates, and import them into Rapidminer. Now, using the extension's operator, it took me 5 minutes. ...

I finally got my Personal Weather Station (PWS) to upload current weather data to Wunderground1 last night. You have no idea how happy this made me, considering I started this project over a year ago but then got interrupted with “life.” I dedicated my first Raspberry Pi to Bitcoin mining, so I needed a second one (Pi’s are addicting, and cheap) to finally get my PWS up and running on the Internet. Luckily I saved the original SD card with all my Wifi settings on it and just plugged it in and fired up the Pi. ...

Below you’ll find a merged set of posts on my Raspberry Pi Tutorials and fun links I found. The Raspberry Pi is a cheap credit card sized computer that helps kid ‘hack’ and learn computing. It’s a great way to build lots of fun projects too. I hope to add to this list as time goes on but I thought my readers would like to see an updated list from my archives. ...

The image below is my first Raspberry Pi computer.  It's an amazing little thing and I decided to purchase one ($35 USD) so I can connect it to my weather station and upload its data, in 15 minute intervals, to the Internet and my FTP site.  Why?  Well I love data if you haven't figured that out by now, and I want to give back to the community. So far I've installed the Raspbian Linux kernel on a 4GB SD card and got it to recognize and connect an Edimax Wifi dongle(sp). I did all this while hooked up to my big screen TV.  I even booted into the X windows server that came with the kernel, very nice and slick. ...

I’ve been traveling a lot lately and managed to catch up on a bit of reading when I’m crusing at 30,000 feet. On my nook right now is a fascinating book that all text miners should at least browse in a book store. It’s called “The Secret Life of Pronouns,” by James Pennebaker. The premise of the book is that your social status, sex, personality, and secret intentions can be determined by analyzing pronouns (I, you, they), artciles (a, an, the), and few other functional words. In the beginning of his research, James used the Liguisitic Inquiry and Word Count (LIWC) program but appears to have modified it with proprietary word dictionaries. ...

I came across a fantastic R script from blogger Milk Trader. It’s about generating something called violin plots of volatility for the S&P500 index and the VIX, which he got from this CBOE paper. I took that script a bit further and added in one of my current trend positions, $ARLP, just for fun. The plot is essentially a “combination of a box plot and a kernel density plot” and shows us the absolute value of volatility (negative returns are represented as positive) on the y axis. ...

It’s probably no surprise to my readers that in addition to trading and building neural net models, I like to collect coins and paper money, especially paper money that’s worthless. As a Numismatic, my approach to coin collecting is simple; collect items I like and add in a few items for their metal value (gold and silver). I probably do more collecting nowadays than trading because the markets have become one highly frequent casino. ...

There's a whole new set of text mining tutorial videos currently being produced, and they're not by me!  Neil over at Vancouver Data Blog is rolling out 5 brand new tutorial videos over the course of the week on how to use Rapidminer for text mining.  His first video on how to load text in Rapidminer is a great way for novice text miners to get started and learn how to wield unstructured data. ...