Icon

kn_​example_​h2o_​sparkling_​water

Combine Big Data, Spark and H2O.ai Sparkling Water

- load data into (local) Big Data environment
- load data into Spark context
- load data into H2O.ai Sparkling Water context
- build H2O model in Big Data environment
- use H2O model
- check accuracy of model
- store model as MOJO file
- reuse stored model on ‚new‘ data with or without the sparkling water context




Combine Big Data, Spark and H2O.ai Sparkling Waterhttps://forum.knime.com/t/integrating-knime-with-bigdata-platform/18164/3?u=mlauber71 - load data into (local) Big Data environment- load data into Spark context- load data into H2O.ai Sparkling Water context- build H2O model in Big Data environment- use H2O model- check accuracy of model- store model as MOJO file- reuse stored model on ‚new‘ data with or without the sparkling water context H2O.ai Auto-machine-learning models with Spark => deletes the wholelocal big data folder/big_datadecide in the configuration if you want sub-folders or parent foldersif you encouter any problems, closeKNIME and delete all data from the folder/big_data/train/testclean uplearnload datainto hivetabledefault.iris/data/my_model.zippredictscore newdata without H2Ocontext/data/my_model.zip1st cretae (empty)hive tableiris.tablelearnAutoMLfor 120 secondsand LogLossor automatic stoppingpredict using Sparkling Watercontextconvert the modelto MOJO file/data/my_automl_model.zip/data/my_automl_model.zippredict using MOJO without explicitSparkling Water contexttestmy_automl_model_non_mojo.zipmy_automl_model_non_mojo.zip local big datacontext create Create H2O SparklingWater Context H2O Partitioning H2O Model to MOJO H2O To Spark Spark Scorer Destroy SparkContext Hive to Spark H2O RandomForest Learner Spark to Table Column Rename DB Table Remover DB Loader DB Table Selector Spark to H2O H2O MOJO Writer H2O Predictor(Classification) Spark H2O MOJO Predictor(Classification) H2O MOJO Reader DB Table Creator Table Reader H2O AutoML Learner H2O Predictor(Classification) Spark Scorer H2O To Spark H2O Model to MOJO H2O MOJO Writer H2O MOJO Reader Spark H2O MOJO Predictor(Classification) H2O To Spark Spark Scorer Model Writer Model Reader Combine Big Data, Spark and H2O.ai Sparkling Waterhttps://forum.knime.com/t/integrating-knime-with-bigdata-platform/18164/3?u=mlauber71 - load data into (local) Big Data environment- load data into Spark context- load data into H2O.ai Sparkling Water context- build H2O model in Big Data environment- use H2O model- check accuracy of model- store model as MOJO file- reuse stored model on ‚new‘ data with or without the sparkling water context H2O.ai Auto-machine-learning models with Spark => deletes the wholelocal big data folder/big_datadecide in the configuration if you want sub-folders or parent foldersif you encouter any problems, closeKNIME and delete all data from the folder/big_data/train/testclean uplearnload datainto hivetabledefault.iris/data/my_model.zippredictscore newdata without H2Ocontext/data/my_model.zip1st cretae (empty)hive tableiris.tablelearnAutoMLfor 120 secondsand LogLossor automatic stoppingpredict using Sparkling Watercontextconvert the modelto MOJO file/data/my_automl_model.zip/data/my_automl_model.zippredict using MOJO without explicitSparkling Water contexttestmy_automl_model_non_mojo.zipmy_automl_model_non_mojo.zip local big datacontext create Create H2O SparklingWater Context H2O Partitioning H2O Model to MOJO H2O To Spark Spark Scorer Destroy SparkContext Hive to Spark H2O RandomForest Learner Spark to Table Column Rename DB Table Remover DB Loader DB Table Selector Spark to H2O H2O MOJO Writer H2O Predictor(Classification) Spark H2O MOJO Predictor(Classification) H2O MOJO Reader DB Table Creator Table Reader H2O AutoML Learner H2O Predictor(Classification) Spark Scorer H2O To Spark H2O Model to MOJO H2O MOJO Writer H2O MOJO Reader Spark H2O MOJO Predictor(Classification) H2O To Spark Spark Scorer Model Writer Model Reader

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: m_lauber
Created at: 2019-09-20
On NodePit since: 2019-10-03
Last update: 2024-11-18
Created with KNIME version: v4.7.8
Tags: knimeh2oh2o.aisparksparklingwatermodelmojobigdatabig data

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!