tidypredict

Run predictions inside the database. tidypredict parses a fitted R model object, and returns a formula in ‘Tidy Eval’ code that calculates the predictions.

It works with several databases back-ends because it leverages dplyr and dbplyr for the final SQL translation of the algorithm. It currently supports lm(), glm() and randomForest() models. Models from the ranger() package are now supported in the development version of the tidypredict

Installation

Install tidypredict from CRAN using:

install.packages("tidypredict")

Or install the development version using devtools as follows:

devtools::install_github("edgararuiz/tidypredict")

Intro

tidypredict is able to parse an R model object, such as:

model <- lm(mpg ~ wt + cyl, data = mtcars)

And then creates the SQL statement needed to calculate the fitted prediction:

tidypredict_sql(model, dbplyr::simulate_mssql())
## <SQL> ((39.6862614802529) + ((`wt`) * (-3.19097213898374))) + ((`cyl`) * (-1.5077949682598))

Supported models

The following R models are currently supported. For more info please review the corresponding vignette:

Skip to content This repository Search Pull requests Issues Marketplace Explore @edgararuiz Sign out Unwatch 9 Star 5 Fork 5 rstudio/db.rstudio.com Code Issues 6 Pull requests 0 Projects 0 Wiki Insights Settings Tree: 7a7548589f Find file Copy pathdb.rstudio.com/themes/hugo-material-docs/layouts/partials/footer_js.html 7a75485 on Apr 22, 2017 @edgararuiz edgararuiz Fix to theme's scrollspy 1 contributor RawBlameHistory 84 lines (73 sloc) 2.83 KB © 2018 GitHub, Inc. Terms Privacy Security Status Help Contact GitHub API Training Shop Blog About