Author: Audris Mockus

Coke vs. Pepsi? data.table vs. tidy? Part 2

By Beth Milhollin, Russell Zaretzki, and Audris Mockus
Coke vs. Pepsi is an age-old rivalry, but I am from Atlanta, so it’s Coke for me. Coca-Cola, to be exact. But I am relatively new to R, so when it comes to data.table vs. tidy, I am open to input from experienced users.  A group of researchers at the University of Tennessee recently sent out a survey to R users identified by their commits to repositories, such as GitHub.  The results of the full survey can be seen here. The project contributors were identified as “data.table” users or “tidy” users by their inclusion of these R libraries in their projects.  Both libraries are an answer to some of the limitations associated with the basic R data frame. In the first installment of this series (found here) we used the survey data to calculate the Net Promoter Score for data.table and tidy. To recap, the Net Promoter Score (NPS) is a measure of consumer enthusiasm for a product or service based on a single survey question – “How likely are you to recommend the brand to your friends or colleagues, using a scale from 0 to 10?”  Detractors of the product will respond with a 0-6, while promoters of the product will offer up a 9 or 10. A passive user will answer with a score of 7 or 8. To calculate the NPS, subtract the percentage of detractors from the percentage of promoters.  When the percentage of promoters exceeds the percentage of detractors, there is potential to expand market share as the negative chatter is drowned out by the accolades. We were surprised when our survey results indicated data.table had an NPS of 28.6, while tidy’s NPS was double, at 59.4.  Why are tidy user’s so much more enthusiastic? What do tidy-lovers “love” about their dataframe enhancement choice? Fortunately, a few of the other survey questions may offer some insights. The survey question shown below asks the respondents how important 13 common factors were when selecting their package.  Respondents select a factor-tile, such as “Package’s Historic Reputation”, and drag it to the box that presents the priority that user places on that factor.  A user can select/drag as many or as few tiles as they choose. 
Pages: Page 1, Page 2

Coke vs. Pepsi? data.table vs. tidy? Examining Consumption Preferences for Data Scientists

By Beth Milhollin ([email protected]), Russell Zaretzki ([email protected]), and Audris Mockus ([email protected])

Coke and Pepsi have been fighting the cola wars for over one hundred years and, by now, if you are still willing to consume soft drinks, you are either a Coke person or a Pepsi person. How did you choose? Why are you so convinced and passionate about the choice? Which side is winning and why? Similarly, some users of R prefer enhancements to data frame provided by data.table while others lean towards tidy-related framework. Both popular R packages provide functionality that is lacking in the built-in R data frame. While the competition between them spans much less than one hundred years, can we draw similarities and learn from the deeper understanding of consumption choices exhibited in Coke vs Pepsi battle? One of the basic measures of consumer enthusiasm is a so-called Net Promoter Score (NPS).

In the business world, the NPS is widely used for products and services and it can be a leading indicator for market share growth. One simple question is the basis for the NPS – How likely are you to recommend the brand to your friends or colleagues, using a scale from 0 to 10? Respondents who give a score of 0-6 belong to the Detractors group. These unhappy customers will tend to voice their displeasure and can damage a brand. The Passive group gives a score of 7-8, and they are generally satisfied, but they are also open to changing brands. The Promoters are the loyal enthusiasts who give a score of 9-10, and these coveted cheerleaders will fuel the growth of a brand. To calculate the NPS, subtract the percentage of Detractors from the percentage of Promoters. A minimum score of -100 means everyone is a Detractor, and the elusive maximum score of +100 means everyone is a Promoter.

How does the NPS play out in the cola wars? For 2019 there is a standoff, with Coca-cola and Pepsi tied at 20. Instinct tells us that a NPS over 0 is good, but how good? The industry average for fast moving consumer goods is 30 (“Pepsi Net Promoter Score 2019 Benchmarks”, 2019). We will let you be the judge.
In the Fall of 2018 we surveyed R users identified by the first commit that added a dependency on either package to a public repository (a repository hosted on GitHub, BitBucket, and other so-called software forges) with some code written in R language. The results of the full survey can be seen here. The responding project contributors were identified as “data.table” users or “tidy” users by their inclusion of the corresponding R libraries in their projects. The survey responses were used to obtain a Net Promoter Score.

Unlike the cola wars, the results of the survey indicate that data.table has an industry average NPS of 28.6, while tidy brings home the gold with a 59.4. What makes tidy users so much more enthusiastic in their choice of data structure library? Tune in for next installment where we try to track down what factors drive a users choice. 


References: “Pepsi Net Promoter Score 2019 Benchmarks.” Pepsi Net Promoter Score 2019 Benchmarks | Customer.guru, customer.guru/net-promoter-score/pepsi.