R Dependencies

install.packages("randomForest")
	library(randomForest)

This example trains a model to classify flower species from an iris dataset. With this data, the model is intended to predict the species using the other data available in the dataset.

fit <- randomForest(Species ~ ., data=iris)
print(fit)
Call:
 randomForest(formula = Species ~ ., data = iris)
               Type of random forest: classification
                     Number of trees: 500
No. of variables tried at each split: 2

        OOB estimate of  error rate: 4%
Confusion matrix:
           setosa versicolor virginica class.error
setosa         50          0         0        0.00
versicolor      0         47         3        0.06
virginica       0          3        47        0.06

To prepare this model for deployment to the Promote server, include randomForest in model.require.

The input to model.transform will be a a new flower record coming from the API. The output of this function will be sent into the model.predict function.

library(promote)

promote.library('randomForest',src="CRAN")

# model.require <- function() {
#   library(randomForest)
# }

model.predict <- function(df) {
  data.frame("predictedSpecies"=predict(fit, newdata=df))
}

To deploy this model to the Promote server, add your username and apikey to the R session and execute promote.deploy.

promote.config  <- c(
  username="YOUR_USERNAME",
  apikey="YOUR_APIKEY",
  env="https://promote.yourcompany.com"
)
promote.deploy("irisPredictor")

To make predictions with this model, use promote.predict. Verify the results from the Promote server are the same as the results obtained from your local machine.

promote.predict(model_name="irisPredictor", iris[1,])
predict(fit, iris[1,])