In applied machine learning, there is usually a trade-off between model accuracy and interpretability. Some models like linear regression or decision trees are considered interpretable whereas others, such as tree ensembles or neural networks, are used as black-box algorithms. While this is partly true, there have been great advances in the model interpretability front in the past few months. In this post I will explain one I the newest methods in the field, the so-called SHAP, and show some practical…
The new season is finally starting and I can’t wait to watch the Australian GP. The new cars are an evolution of the previous ones since there was no major change in the rules. The most visible changes are the introduction of the much debated Halo device – which I’m not fan of although it doesn’t look as bad as I expected – and the removal of the shark fin and the T-wing. Of course, McLaren has switched engines with…
2017 season is, unfortunately, over and at the same time that was the end of the first season F1-predictor published qualifying and race predictions. In this post I would like to describe my experience from this first year of keeping this blog and – most importantly – provide an objective assessment of 2017 predictions!
The season is – unfortunately – coming to an end and both world championships have been already decided. Abu Dhabi is the last race of the season and we’ll only be interested in seeing whether Vettel can seal the 2nd position in the drivers championship.
Hamilton and Mercedes may have clinched the driver’s and the constructor’s championship respectively, but there’s a lot to play for in the lower positions. Just six points separates Toro Rosso in 6th position, Renault in 7th and Haas in 8th. I believe both teams will jump ahead of Torro Rosso mainly due to the inexperience of its current driver line-up.
In this post I’m going to talk about one of the most creative aspects of data science: feature encoding. If you haven’t followed my previous posts on feature engineering, you can find them in this link before reading this one.
Just three races remain this season, Mercedes is already crowned champion and Lewis Hamilton may clinch the driver’s title this weekend. We were sure hoping for more intrigue in the closing stages of the season. In the upcoming Mexican GP, Hamilton is expected to take pole and win the race as well.
Ferrari and Sebastian Vettel are still trying to recover from the past three nightmare race weekends and F1 is heading to the Circuit Of The Americas (COTA) in Austin, Texas. Pierre Gasly will be substituted with Kvyat who will partner with Brendon Hartley since Sainz is taking the Palmer’s race seat in Renault.
Just five races remain till the championship ends and next up is the Japanese GP in Suzuka circuit. Vettel and Scuderia Ferrari desperately need the victory here if they want to have a chance at the driver’s title. The two title contenders are expected to start and finish in the first two positions, with Hamilton first and Vettel second.
After creating all features, it is quickly evident that there are a lot of missing data. Missing data should be dealt with before going on to the next phases of our model building. In this post, I’m going to quickly describe the reasons behind the missing values and ways to treat them.