Forbes Billionaires - Modified

Context

The Original dataset had some incongruencies in the collection of the data for the feature "Source".

The feature "Source" aims at capturing the main origin of the billionaires' accumulated wealth. However, Forbes had adopted an inconsistent approach in collecting these data. When the source of wealth is connected with a popular or well-known company, then the Company name is reported (i.e. Amazon, Microsoft, Google and so forth). In other instances, the economic sector where the billionaire business operates is reported (i.e., software, machinery, food and beverage, and so forth).

For instance, Bill Gates' source of wealth is recorded as "Microsoft", while for Larry Ellison (founder of Oracle), the dataset mentions a generic "software". Jeff Bezos's source is Amazon, but e-commerce is the provenience of Jack Ma's wealth. This approach creates series of difficulties when aggregating the data. When billionaires are grouped by the "Source" as it appears in the original dataset, billionaires like Jeff Bezos or Jack Ma would be classified in two different buckets. However, they both operate in the same economic sector. 

Therefore, the dataset was reviewed to standardize the "Source" entries. As a result, taking the first six wealthiest people in the world as an example, Amazon becomes e-commerce, Tesla is replaced by "electric vehicles", LVMH by "luxury good", Microsoft by "software", Facebook by "social media" and Berkshire Hathaway by "finance".

Acknowledgements
Skimmed the data from forbes.com
Based on the original dataset uploaded here by Alexander Bader : Link