Thoughts & Code
I’m thrilled to announce that I have officially started my PhD journey at Singidunum University in the Intelligent Software Engineering program! Balancing this alongside work and family will undoubtedly be challenging, but I’m excited to dive deeper into research. Looking forward to sharing more updates as I progress!
KFP sdk v2 is the current focus of the Kubeflow community, which means it will receive ongoing updates, improvements, and support. Kfp v1 is legacy and there will be no further updates or support. In this short blog post I will present some of the changes:
Full video can be found at https://www.youtube.com/watch?v=HAcXOs5Vdws
I’m thrilled to announce that I have been selected as a speaker at the Kubeflow Summit, a CNCF-hosted Co-located event. This prestigious event is taking place on March 19, 2024, at the Paris Expo Porte De Versailles in Paris, France. Alongside my colleague Chris Addy, we’ll be sharing insights and experiences at this summit. It’s […]
I’m excited to share my recent experience at DSC Europe ’23 in Belgrade, where I had the privilege of participating in the End-to-End Machine Learning panel. The discussion was incredibly engaging, filled with insightful perspectives and thought-provoking questions from a diverse audience. The event brought together experts and enthusiasts from various fields, creating a dynamic […]
When I started using WEKA java library to classify some adds for my employer some 10 years ago I was not aware of “data scientist” term. I consider myself as a programer that had to learn some new skills in order to use WEKA library. Time passed and although I was heavily involved in machine […]
I’ve just spent some significant amount of time working on notebook and restarted computer without saving or committing notebook. As soon as I have realized what happened I was devastated. Couple of hours of work were gone for good. 🙁 Luckily , it is possible to retrieve history of the commands from the notebook itself. […]
It can happen that some categorical features have lot of different values with small frequencies. This can often be a problem during modeling phase. Typical solution is to merge all categories with small (e.g. 5% , 1% etc… ) frequency of appearance in data set into one category e.g. Other Below is the pandas example […]
This year during Data Science Serbia 4.0 I had a privilege to talk with one of data scientist that I really admire. I have to admit that I was super excited to have a chance to talk with Hadley Wickham. This guy has contributed so much in the R- universe that there are some totally […]
Often we need to change sampling of a time series data set that we are working with. Imagine that you are working with time series that was sampled in 15 minutes chunks and need to do analysis/ forecast with different sampling e.g. daily , 3 hours, quarterly, yearly etc… There is method resample in pandas […]