2

我想用MLeap来部署Spark ML机器学习模型,并用它们来实时预测。Scala to Java 8 MLeap Translation

创作者推出了Scala教程,但我需要支持Java 8代码库。

我将如何在Java中实现8以下代码:

val pipeline = SparkUtil.createPipelineModel(uid = "pipeline", Array(featureModel, rfModel)) 

val sbc = SparkBundleContext() 
for(bf <- managed(BundleFile("jar:file:/tmp/mnist.model.rf.zip"))) { 
     pipeline.writeBundle.save(bf)(sbc).get 
     } 

val bundle = (for(bundleFile <- managed(BundleFile("jar:file:/tmp/simple-spark-pipeline.zip"))) yield { 
    bundleFile.loadMleapBundle().get 
}).opt.get 

回答

0

如果使用普通的星火ML变压器而已,你可以使用SimpleSparkSerializer轻松保存和载入您的模型。

保存:

new SimpleSparkSerializer().serializeToBundle(model, "jar:file:/tmp/model.zip", trainData); 

加载:

Transformer model = new SimpleSparkSerializer().deserializeFromBundle("jar:file:/tmp/model.zip"); 
+0

如果我有自定义估计/变形金刚? – Gevorg