This is a short exploratory data analysis (EDA) and visualisation of two random datasets that was required for an interview process; inspired by the work by Tyler Vigen. The data chosen was of Tesla Vehicle Production (units) and US Nonfarm Business Productivity (index) from 2012-Q4 to 2018-Q1.
It might suggest that Tesla cars are improving Nonfarm Productivity in the USA!?!
Kidding aside, it's a exploration of two datasets and highlights the possible directions you could go in with further analysis; whilst still highlighting all the statistical flaws and their remedies a long the way. Aside from anything else it has pretty visualization which can be universally appreciatted. In future I would like to work with broader datasets (>2) to enable the application of the more interesting Plotly/Cufflinks featureas such as Heatmaps, 3d Scatter Plots and Funnel Charts.
To see it online I refer you to Bug Note, alternatively you can clone the repo and use the requirements.txt to setup your own virtual environment and run it!
The graphs are written in plot.ly and seem to be struggerling to render in gist, please view on nbviewer or another notebook viewer.
For those too lazy to type, the link as of now is here for nbviewer.