Prophet Explore: A Simple Shiny App to Get Introduced to Prophet

April 16, 2017
By

(This article was first published on Once Upon Data, and kindly contributed to R-bloggers)

Last February, I read about prophet package, which was released by Facebook’s Core Data Science team. I skimmed the published paper Forecasting at Scale quickly and I got the main concept. I also liked how the creators; Sean Taylor and Ben Letham were trying to empower analysts to produce high quality forecasts by offering them a flexible and configurable model that requires general understanding, but not necessarily deep knowledge about time series models.

Later in April, I listened to Sean’s discussion with Roger Peng and Hilary Parker in Not So Standard Deviations 35th episode Special Guest Sean Taylor. It was an interesting espisode, where they discussed different aspects of the prophet project and the underlying challenges. They also discussed the different points of views on generic tools that give analysts some parameters to tune, with limited understanding of the underlying concepts.

At this phase, I was discovering the package, so I thought about creating a Shiny App (Prophet Explore) to play with the parameters and discover any issues quickly. But then I enhanced it a little bit, deployed it on Shinyapp.io to give access to more people and tweeted about it. Interestingly, in two days, it was active for 30 hours and ate up 1/3 of my hours on Shinyapp.io. I kept working on it, adding some validations and I am still enhancing it.

To use the interactive App, one should upload the data in the right format. And to tune the parameters, one should understand the significance of those parameters. Prophet documentation provides a detailed explanation with examples to follow for deeper understanding and guidance

Try Prophet Explore

Prophet Explore is available on Github Here.

In case I still have active hours on Shinyapp.io, you’ll see the App below.

To leave a comment for the author, please follow the link and comment on their blog: Once Upon Data.

R-bloggers.com offers daily e-mail updates about R news and tutorials on topics such as: Data science, Big Data, R jobs, visualization (ggplot2, Boxplots, maps, animation), programming (RStudio, Sweave, LaTeX, SQL, Eclipse, git, hadoop, Web Scraping) statistics (regression, PCA, time series, trading) and more...



If you got this far, why not subscribe for updates from the site? Choose your flavor: e-mail, twitter, RSS, or facebook...

Comments are closed.

Sponsors

Never miss an update!
Subscribe to R-bloggers to receive
e-mails with the latest R posts.
(You will not see this message again.)

Click here to close (This popup will not appear again)