I remain pleasantly surprised at Microsoft's enthusiasm for adding R to its analytics ecosystem (and not [at least yet] fulfilling suspicions its end game is to fork a version of R that is semi-proprietary). Today offered another example, with an R for the Masses with Power BI webinar touting R as an option for data heavy-lifting within its Power BI platform. Granted, as an R user I'm biased, but it makes a lot more sense to lean on a language already in wide use for data work, as opposed to expecting people to learn its own DAX and M. During today's webinar, Microsoft revealed that its own survey showed more than 80% of respondents wanted to use R for advanced data work.
Power BI users could already run R scripts within the software to pull in data, to reshape and otherwise wrangle data, and to visualize data. During the webinar, Microsoft announced an R Script Showcase with examples designed to "find inspiration for leveraging R scripts in Power BI. There are already examples for using R to find clusters within your data, generate forecasts and create decision trees.
In addition, during this afternoon's webinar, Microsoft's Sharon Laivand said Power BI desktop will soon release a preview feature that allows users one-click access from Power BI directly into the RStudio IDE (or Microsoft's Visual Studio) -- pulling in not only an R script you may be working on but all the Power BI data in your session. This will make it vastly easier to create and debug more complex R scripts as part of a Power BI workflow, since the basic text-box editor currently available is really only useful for fairly simple code. (The preview won't likely have one click back, however, with the demo showing the need to cut and paste a final script back from RStudio to Power BI).
How much more compelling does all this R functionality make the platform? I like Power BI as a concept -- it's quick to use and reasonably intuitive -- but the ease-of-use interface is also somewhat limited. Interactive bar charts with filters? Check. Choropleth maps with even basic customization? Frustrating. Data cleaning with the point-and-click UI? That can get even more frustrating if you're doing much beyond basics like changing column data types.
Some of the limitations have to do with the newness of the platform; and Microsoft is in fact working to update it pretty frequently. But other limits are due to the tension between easy-to-use on the one hand and robustness on the other. And that's where R comes in. Microsoft can keep its basic GUI simple and let more advanced users turn to R for more sophisticated data cleaning, analysis and visualization.
Limits remain, though. It's not so simple to share interactive R visuals: Within reports, only paying Pro account users can view them; on dashboards, they're static images. And, only packages that generate images can be used within Power BI for now, not those that generate JavaScript or HTML. I also continue to find the differences between sharing reports and dashboards non-intuitive, even after working with Power BI since March.
For complex interactive applications, I'm still more likely to turn to a platform like the R Web framework Shiny. There, the limits are mostly due to my own coding skills. However, to quickly go from spreadsheet data to basic visualizations, I'm finding Power BI often up to the task. I'll be interested to see how much R will improve the Power BI experience.
Note: Today's R for the Masses with Power BI webinar should be available for on-demand viewing at Microsoft shortly.
Want to learn more? See my Beginner's Guide to R and Step-by-Step Guide to Power BI (with video).