The penultimate week of the bootcamp bought around round of Machine Learning. First we explored Machine Learning in Apache Spark, then we looked at Association Rule Mining and used R to explore Naive Bayes after previously seeing it in Python. Our other classroom activities included practicing interview questions and data set challenges.
Outside of this, we continued to work on either capstone projects or company projects. One institutional addition to the latter was Data Science For Good, the non-profit arm of NYC Data Science Academy.
Another notable event was a talk given by Booz Allen Hamilton’s Principal Data Scientist, Kirk Borne. His anecdotes of about the application of simple clustering techniques to Astrophysics were fascinating. He also spoke about the second annual Data Science Bowl, a competition planned by both Booz Allen Hamilton and Kaggle. I felt out of my depth when I attempted the first edition of the challenge, but I am definitely better prepared to tackle this year’s offering.
Next week the bootcamp draws to a close as we end off by talking about our capstone projects.