Icon

17107_​Sparkling_​Water

17107_Sparkling_Water
Set up Hive Environment Train Churn Prediction Model on Spark using H2O Sparkling Water Deploy Mojo Model on KNIME Server Description:The first workflow sets up the local big data environment and loads the CustomerData into Hive. The secondworkflow trains a chun prediction model in the a big data enviroment using the Spakling Water integration. Thelast workflow can be used as a deployment workflow on a KNIME Server and can be executed via a REST call. Requirements:- KNIME Analytics Platform + KNIME Extension for Local Big Data Environments + H2O Sparkling Water Integration + KNIME Extension for Apache SparkCreated with KNIME 3.6 on 14/09/2018 Input from REST callResult of REST callcreate HDFScompatible path70% Training30% TestingSave Churn PredictionModelRead Churn Prediction Modelcreate structureLoad tableNode 272SELECT * FROM customer_dataNode 275Node 276Node 277Node 278Node 279ContainerInput (JSON) ContainerOutput (JSON) JSON to Table Columns to JSON Create Temp Dir String Manipulation(Variable) H2O Partitioning Create H2O SparklingWater Context Spark to H2O H2O Model to MOJO H2O MOJO Writer H2O MOJO Reader Create Local BigData Environment DB Table Creator DB Loader Read Data Create Local BigData Environment DB Table Selector Hive to Spark H2O Gradient BoostingMachine Learner H2O Predictor(Classification) H2O Binomial Scorer H2O MOJO Predictor(Classification) Set up Hive Environment Train Churn Prediction Model on Spark using H2O Sparkling Water Deploy Mojo Model on KNIME Server Description:The first workflow sets up the local big data environment and loads the CustomerData into Hive. The secondworkflow trains a chun prediction model in the a big data enviroment using the Spakling Water integration. Thelast workflow can be used as a deployment workflow on a KNIME Server and can be executed via a REST call. Requirements:- KNIME Analytics Platform + KNIME Extension for Local Big Data Environments + H2O Sparkling Water Integration + KNIME Extension for Apache SparkCreated with KNIME 3.6 on 14/09/2018 Input from REST callResult of REST callcreate HDFScompatible path70% Training30% TestingSave Churn PredictionModelRead Churn Prediction Modelcreate structureLoad tableNode 272SELECT * FROM customer_dataNode 275Node 276Node 277Node 278Node 279ContainerInput (JSON) ContainerOutput (JSON) JSON to Table Columns to JSON Create Temp Dir String Manipulation(Variable) H2O Partitioning Create H2O SparklingWater Context Spark to H2O H2O Model to MOJO H2O MOJO Writer H2O MOJO Reader Create Local BigData Environment DB Table Creator DB Loader Read Data Create Local BigData Environment DB Table Selector Hive to Spark H2O Gradient BoostingMachine Learner H2O Predictor(Classification) H2O Binomial Scorer H2O MOJO Predictor(Classification)

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: kathrinmelcher
Created at: 2018-09-06
On NodePit since: 2019-09-23
Last update: 2020-03-23
Created with KNIME version: v4.0.1
Tags: Big DataEducation

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

Try NodePit Runner!