install.packages("r2pmml")

library("devtools")

install_git("git://github.com/jpmml/r2pmml.git")

library("r2pmml")

library("randomForest")
library("r2pmml")

data(iris)

# Train a model using raw Iris dataset
iris.rf = randomForest(Species ~ ., data = iris, ntree = 7)
print(iris.rf)

# Export the model to PMML
r2pmml(iris.rf, "iris_rf.pmml")

library("caret")
library("randomForest")
library("r2pmml")

data(iris)

# Create a preprocessor
iris.preProcess = preProcess(iris, method = c("range"))

# Use the preprocessor to transform raw Iris dataset to pre-processed Iris dataset
iris.transformed = predict(iris.preProcess, newdata = iris)

# Train a model using pre-processed Iris dataset
iris.rf = randomForest(Species ~., data = iris.transformed, ntree = 7)
print(iris.rf)

# Export the model to PMML.
# Pass the preprocessor as the `preProcess` argument
r2pmml(iris.rf, "iris_rf.pmml", preProcess = iris.preProcess)

library("plyr")
library("r2pmml")

# Load and prepare the Auto-MPG dataset
auto = read.table("http://archive.ics.uci.edu/ml/machine-learning-databases/auto-mpg/auto-mpg.data", quote = "\"", header = FALSE, na.strings = "?", row.names = NULL, col.names = c("mpg", "cylinders", "displacement", "horsepower", "weight", "acceleration", "model_year", "origin", "car_name"))
auto$origin = as.factor(auto$origin)
auto$car_name = NULL
auto = na.omit(auto)

# Train a model
auto.glm = glm(mpg ~ (. - horsepower - weight - origin) ^ 2 + I(displacement / cylinders) + cut(horsepower, breaks = c(0, 50, 100, 150, 200, 250)) + I(log(weight)) + revalue(origin, replace = c("1" = "US", "2" = "Europe", "3" = "Japan")), data = auto)

# Export the model to PMML
r2pmml(auto.glm, "auto_glm.pmml")

library("ranger")
library("r2pmml")

data(iris)

# Train a model.
# Keep the forest data structure by specifying `write.forest = TRUE`
iris.ranger = ranger(Species ~ ., data = iris, num.trees = 7, write.forest = TRUE)
print(iris.ranger)

# Export the model to PMML.
# Pass the training dataset as the `data` argument
r2pmml(iris.ranger, "iris_ranger.pmml", data = iris)

library("xgboost")
library("r2pmml")

data(iris)

iris_X = iris[, 1:4]
iris_y = as.integer(iris[, 5]) - 1

# Generate R model matrix
iris.matrix = model.matrix(~ . - 1, data = iris_X)

# Generate XGBoost DMatrix and feature map based on R model matrix
iris.DMatrix = xgb.DMatrix(iris.matrix, label = iris_y)
iris.fmap = as.fmap(iris.matrix)

# Train a model
iris.xgb = xgboost(data = iris.DMatrix, missing = NULL, objective = "multi:softmax", num_class = 3, nrounds = 13)

# Export the model to PMML.
# Pass the feature map as the `fmap` argument.
# Pass the name and category levels of the target field as `response_name` and `response_levels` arguments, respectively.
# Pass the value of missing value as the `missing` argument
# Pass the optimal number of trees as the `ntreelimit` argument (analogous to the `ntreelimit` argument of the `xgb::predict.xgb.Booster` function)
r2pmml(iris.xgb, "iris_xgb.pmml", fmap = iris.fmap, response_name = "Species", response_levels = c("setosa", "versicolor", "virginica"), missing = NULL, ntreelimit = 7, compact = TRUE)

Sys.setenv(JAVA_TOOL_OPTIONS = "-Xms4G -Xmx8G")

r2pmml(iris.rf, "iris_rf.pmml")

r2pmml(iris.rf, "iris_rf.pmml", converter = "com.mycompany.MyRandomForestConverter", converter_classpath = "/path/to/myconverter-1.0-SNAPSHOT.jar")

remove.packages("r2pmml")