Putting the D'oh! in data

How many times has the name, "Dr Zaius" been uttered on The Simpsons? Which character has said the most over all these years? Have you ever noticed how few female characters there are?

Software engineer and data scientist Todd Schneider combed through 27 seasons of The Simpsons to find out. His project is called The Simpsons by the Data -- and it reveals enough insights to fill Moe's tavern.

From time to time on Spark, we look at the power of analytics and how analyzing huge datasets can turn up surprising correlations and insights. 

For a big Simpsons fan like Todd, it was an opportunity to make some interesting observations. One thing that became quite clear was the enormous gender imbalance on the show.

"I made this list of the top 50 characters," he says "and going down the list, it's just man, man, man, man and of the top 50, there were only five women."

It's amazing what you can find out by looking at a dataset that size. What you can do with those findings is, well, a little less clear.

Just lay off the insanity peppers.