Loading…

Sam Kenkel

Data Science, Machine Learning, DevOps, CCNA, ACSR
Learn More

Kaggle_Titanic

One of the most famous modern  machine learning training datasets is to predict survival of passengers on the titanic. I used this project while experimenting with KNearestNeighbor classifiers, SVMs, LogReg, pipelines (and the problems with dummying categorical data in pandas), as well as the TFlearn front-end for Tensorflow. My sourcecode for that that project can be found here.

Anime_Rec: Generating recommended Animes based on MAL data.

Anime_Rec is a Data Science project to generate Anime recommendations based on publicly available data from the website myanimelist.net. I’m an Anime fan. In fact, I watch enough Anime to have hit that point where finding something to watch becomes difficult. As an Anime fan and Data Scientist,  the obvious solution was to build a Recommendation engine to recommend Anime for me to watch. This post explains my overall approach and architecture The first step in any machine learning or Data Science project is gathering the data, and thankfully for me, other Anime fans have done […]

Setting up an Nvidia-Docker workstation for DataScience/DeepLearning

After deciding, in my previous post, to switch my z620 to an Nvidia-Docker workstation, I wanted to give a writeup of how exactly I did that, because some of the specific technical steps (such as disabling a graphics card in bios to install the nvidia driver) aren’t all documented in one place. Part 1: HW Setup First I open up my z620, and remove the quad port NICs that I’m no longer going to use.  The z620 has two ‘compartments’ inside of the case: the pci-express ports sit on one side of a partition, and […]

Lol_Scout: League of Legends Champion Mastery Analytics

Lol_Scout was a Data Science/ Esports analytics project I pursued to answer questions about how League of Legends players champion choices can be optimized. The current soucecode and readme can be found here. Part 1: Background, Initial Design, Data Gathering,  data acquisition lessons learned, ways to pursue the project further in the future. Part 2: Modelling with Neural Net Classifiers with just champion selection. Comparing to XGBoost. Adding Data from Player’s experience at a character. Part 3:Modelling with Neural Nets and Xgboost with more features, conclusions.

A New Direction: ACSR CCNA consulting, Data Science Portfolio

After some time in dormancy, it is once again time for Drunken Thieves to be active. While originally a launchpad for some creative side projects (Film and Games), it became a blog that would go on to become insidethekraken. As one of the founding members of Drunken Thieves, I’ve decided that like me, it’s time for this site to transition.  Going forward, this site will be a portfolio/blog about my current focus on Data Science, Machine Learning, and DevOps. While that is  my current focus, I am still available for ACSR or CCNA consulting: I’ve […]

Another New Beginning

So, Emmy Live Blogs aside, you have probably noticed a bit of a lull in the blog for the past month or so. I announced a couple of months ago that some big changes were coming soon, and that time is now. Starting Monday, the Drunken Thieves blog will be no more, as we transition to a new blog. Drunken Thieves has been an incredibly positive experience for Kyu, Keskel, and I, but we all felt it was time for a change. When starting this blog, it was really more for us than for any potential readers, […]