Blog

"X1 and X2 have a super high correlation, let's drop one of them for feature selection". Are really sure about that?

Julia’s hype as the next programming language of Data Science is always rising each year. What does doing Data Science in Julia look like?

People tend to forget about existence of a confounding variable when concluding causality between events. Wait, what is confounding variable ?

You need to optimize RMSLE(L for Logarithmic), but your model only know RMSE optimization. Is there still anything love can do?

Do you know that 0.1 + 0.2 == 0.3 will gives False in most programming language?

It turns out that Sklearn quite slow for several task, can we make things better with Numba, or even Numpy ?