The Meta Kaggle dataset

The Meta Kaggle dataset (https://www.kaggle.com/kaggle/meta-kaggle) is a collection of rich data about Kaggle’s community and activity, published by Kaggle itself as a public dataset. It contains CSV tables filled with public activity from Competitions, Datasets, Notebooks, and Discussions. All you have to do is to start a Kaggle Notebook (as you saw in Chapters 2 and 3), add to it the Meta Kaggle dataset, and start analyzing the data. The CSV tables are updated daily, so you’ll have to refresh your analysis often, but that’s worth it given the insights you can extract.

We will sometimes refer to the Meta Kaggle dataset in this book, both as inspiration for many interesting examples of the dynamics in a competition and as a way to pick up useful examples for your learning and competition strategies. Here, we are going to use it in order to figure out what evaluation metrics have been used most frequently for competitions in the last...