The tenth week of the bootcamp brought the Hadoop ecosystem to the table. During the week we intertwined theory and practice as we started from first principles with Map-Reduce, and then worked our way up to Hadoop, Hive, and Apache Spark. The week also brought an enlightening talk from Tim Rich of Publicis, resume reviews with a representative of Five Star Resume, and another round of presentations on Machine Learning projects. I myself talked a bit of my work done in a competition hosted by Driven Data, the goal of which was to predict the status (functioning, in need of repair, non-functioning) of wells in Tanzania.
In the penultimate week we’ll look at Machine Learning for the last time. The agenda consists of some further topics from R’s perspective and doing Machine Learning using Spark’s MLlib library.