Output Prediction Model from Execute R Script Module in Azure ML

Question

I'm doing an experiment to predict energy demand using 3 types of machine learning method which is ANN-MLP, SVM RBF and k-NN. I'm utilizing the Execute R Script module to run the R code. My questions is how to output the executed model, so that the model can be used to predict in another dataset. Basically I have 2 datasets - June dataset and July dataset. The prediction model is created using June data set, and I wanted to test July dataset using the model.

predictor <- maml.mapInputPort(1) 
datafull <- maml.mapInputPort(2) 

library(caret)

#data splitting
datasplit <- createDataPartition(y = predictor$demand, p = 0.7, list = FALSE)
datatrain <- predictor[datasplit,] 
datatest <- predictor[-datasplit,] 

#repeated cv, 10 cross validation
ctrl <- trainControl(method="repeatedcv", repeats =5)
knnFit <- train(demand ~ ., data = datatrain, method = "knn", trControl = ctrl, preProcess = c("center", "scale"), tuneLength = 20)
knnFit
plot(knnFit)

#Prediction
datapredict <- predict(knnFit, predictor)

plot(datafull$cdate, datafull$demand, xlab = "Time", ylab = "Demand", col = "#0441d9")
lines(datafull$cdate, datafull$demand, xlab = "Time", ylab = "Demand", col = "#0441d9")
lines(datafull$cdate, datapredict, xlab = "Time", ylab = "Demand", col = "#cc0000")

Right now the code only output the original dataset with a new column consist of the predicted value.

datafull$data.predict <- datapredict 
str(datafull)

# Select data.frame to be sent to the output Dataset port
maml.mapOutputPort('datafull');

Answer 1

You can convert you experiment to a predictive experiment. Then the model is saved and you can use predictive experiement to have any data evaluated you want.