Forbes Celebrity 100: The World’s Highest Paid Entertainers (2005–2019)
I started my journey into data science and analytics probably at the beginning of 2019. I took a 6 months online course in data analytics where I learnt the basics of SQL, Tableau and Python to analyze and visualize data. After the course was done, I was really looking forward to getting a job and applying the skills I had learnt in real world situations. However, it’s not so easy to do that in the real world. I did get some opportunities but I never made it past the second to the final recruitment stage or even the final recruitment stage. I was able to get in touch with one of such companies to find out what I needed to improve on and they advised me to learn how to better clean and analyze data with Python rather than doing most of the data cleaning stage on Excel. I read somewhere recently about how taking a lot of MOOCs won’t help you till you actually put into practice what you’ve learnt on real world data and that’s what I decided to do.
This is the first of my real world projects I’m working on to challenge myself, build my portfolio and also learn a lot by JUST DOING! I would also be documenting each project here once its completed.
I obtained this dataset from Kaggle and you can find my full codes and visualizations here https://www.kaggle.com/sofuwaoo/forbes-celebrity-100-eda. This project challenged me A LOT and it kind of took a while to complete it because there were days when I was just frustrated when my code wouldn’t do something I needed it to do but Google and a friend of mine helped me out and then my laptop developed a fault which took almost a week before I got it back. Nevertheless, I’m so proud that I completed this project.
Forbes Celebrity 100, according to Wikipedia is an annual list and its purpose is to list the world’s highest paid celebrities. The methodology used by Forbes to determine which celebrities are paid the most is by ranking ‘front of the camera’ stars around the globe using pretax earnings, over the course of a year, before deducting fees for managers, lawyers and agents.
Tools and packages I utilized:
· Jupyter Notebook from the Anaconda Navigator
· Pandas
· Plotly Express because of its interactivity
I started out by exploring my dataset to find out if there was any missing data, to get a general idea of the data I was working on and to come up with questions about what insights or information I could get from the data. I came up with six questions but I’ll be addressing two of those here. To view my codes and visualizations check out my kaggle notebook https://www.kaggle.com/sofuwaoo/forbes-celebrity-100-eda. There was no missing data and the data was pretty much clean.
All I did in the data cleaning stage was to group certain categories together which helped me reduce the number of categories from 13 to 9.
One of the questions I wanted to find an answer to was which category had the most listing per year between 2005 and 2019. I began by creating the category_nom dataframe by grouping my data by year, category and calculating a count aggregate. Then, I created a new dataframe to filter the data in category_nom to show just data for the year 2019.
From the visualizations below, it shows that Actors and Athletes had the most listing in 2005. Musicians, on the other hand, took the spot for most listed category between 2017 and 2019. Over the years, however, the Actors category generally had the most listings.
The second question was to analyze and show the ten celebrities to make it to the top of the Forbes Celebrity 100 list in 2019 along with their earnings.
The visualization below shows that Taylor Swift, was the highest earning entertainer in 2019 earning $185M. Kylie Jenner and Kanye West took the second and third spots respectively having $170M and $150M each.
Once again to view the entirety of my codes and visualizations, you can do that here https://www.kaggle.com/sofuwaoo/forbes-celebrity-100-eda
Till next time
Stay Safe!
