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(), randomForest() and ranger() models.


Install tidypredict from CRAN using:


Or install the development version using devtools as follows:



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: