Running R programs at scale using Dataflow

calling_r.java

double[] inputx = c.element(); // from input
engine.put("x", inputx);

// run R program, get output from R, send to Dataflow
ListVector result = (ListVector) engine.eval(new InputStreamReader(rprog));

double pvalue = result.getElementAsDouble(1);

myprog.r

library(exptest)

co.exp.test(x, simulate.p.value=FALSE, nrepl=2000)

pom.xml

<repositories>
  <repository>
    <id>bedatadriven</id>
    <name>bedatadriven public repo</name>
    <url>https://nexus.bedatadriven.com/content/groups/public/</url>
  </repository>
</repositories>

  <dependencies>
  <dependency>
    <groupId>org.renjin</groupId>
    <artifactId>renjin-script-engine</artifactId>
    <version>RELEASE</version>
  </dependency>
  <dependency>
    <groupId>org.renjin.cran</groupId>
    <artifactId>exptest</artifactId>
    <version>1.2-b214</version>
  </dependency>
  
  <!-- rest of your dependencies go here -->

script_engine.java

ScriptEngineManager manager = new ScriptEngineManager();
ScriptEngine engine = manager.getEngineByName("Renjin");
InputStream rprog = CallingRFromJava.class.getResourceAsStream("myprog.r");