What is it a data scientist yearn for most? For me it’s Data Visualization. We know that under those massive layers of junk there is always something important hidden that can get noticed with the visualization. More importantly we need analytics for establishing relationship among all the values which could be quite hassling if done manually given how large and unstructured the dataset we may have.
While working on spark, I stumbled upon the most basic and very well structured dataset found from “Kaggle” competition “Titanic”. Now the very first thing I wanted was to visualize this dataset in graphical form to understand better relationship among constraints.
One of the way to do that is via Zeppelin. Zeppelin provides a web based notebook that allow user to build reports for data analytic. In this blog I am going to explain about Zeppelin installation,configuration and graphical representation on Titanic data set.
View original post 325 more words