如何将 H2O 苏打水模型保存到磁盘

Question

I have a PySpark code to train an H2o DRF model. I need to save this model to disk and then load it.

from pysparkling.ml import H2ODRF
drf = H2ODRF(featuresCols = predictors,
                labelCol = response,
                columnsToCategorical = [response])

I can not find any document on this so I am asking this question here.

Answer 1

I think the section of the docs on deploying pipeline models might be relevant: https://docs.h2o.ai/sparkling-water/2.3/latest-stable/doc/deployment/pysparkling_pipeline.html

Pipelines may not be what you're looking for depending on the use case.

Something like the following might work for your use case.

drf = H2ODRF(featuresCols = predictors,
                labelCol = response,
                columnsToCategorical = [response])

pipeline = Pipeline(stages=[drf])

model = pipeline.fit(data)
model.save("drf_model")