Time Series Analysis and Visualization Using Python and Plotly
In 2006, Hans Rosling gave a lecture at a TED conference titled “The Best Stats You’ve Ever Seen,” where he used statistics to show a decrease in worldwide fertility and that the era of fast population growth would end by mid century. He also stated that the distinction between developed and developing countries has blurred, global health is improving, and extreme poverty in the world is decreasing. This has been considered one of the best implementations of data analysis, visualization, and storytelling.
In this project, we’ll endeavor to replicate that animated visualization using the Plotly library in Python. This analysis will revolve around how a country’s GDP per capita correlates with the life expectancy of its citizens over a period of 100+ years.
We’ll perform extensive cleaning and data manipulation to get the data ready for visualization, and also perform some feature engineering to derive new columns from existing columns that would aid our analysis. By the end of the project, we’ll be able to unpivot a dataset from the wide format to the long format, merge multiple datasets together using primary and foreign keys, animate a visual, and export it as a GIF file.