Databricks ML 模型导出 Databricks ML Model Export


Databricks ML 模型导出已在 Databricks Runtime 5.3(不受支持)中弃用,而且已从 Databricks Runtime 6.0(不受支持)中删除。Databricks ML Model Export was deprecated in Databricks Runtime 5.3 (Unsupported) and is removed in Databricks Runtime 6.0 (Unsupported). 请改用 MLeap 来导入和导出模型。Use MLeap for importing and exporting models instead.

Databricks ML 模型导出会从 Apache Spark 导出模型和完整的 ML 管道。Databricks ML Model Export exports models and full ML pipelines from Apache Spark. 可将这些导出的模型和管道导入到其他平台,以进行评分和预测。These exported models and pipelines can be imported into other platforms to do scoring and make predictions.

模型导出面向低延迟、轻型且支持 ML 的应用程序 。Model Export is targeted at low-latency, lightweight ML-powered applications. 通过模型导出,你可以:With Model Export, you can:

  • 使用现有模型部署系统Use an existing model deployment system
  • 实现非常低的延迟(毫秒)Achieve very low latency (milliseconds)
  • 在自定义部署中使用 ML 模型和管道Use ML models and pipelines in custom deployments

评分(推理)库采用 JSON 编码的功能。The scoring (inference) library takes JSON-encoded features.

{"id":5923937,  // any metadata
"features:": { // MLlib vector format: 0 for sparse vector, 1 for dense vector
   "type": 1,
   "values":[0.1, 1.3, 8.4, 4.2]}}

结果也以 JSON 编码。The result is also encoded in JSON.

 "prediction": 1.0}