Icon

17105_​Parameter_​Optimization_​in_​Spark

17105_Parameter_Optimization_in_Spark
Mix and Match Description:This workflow mixes existing KNIME nodes with the new Spark nodes to find the optimal parameters for a k-means clustering using the hillclimbing approach. Requirements:- KNIME Analytics Platform + KNIME Optimization extension + KNIME Extension for Apache Spark + KNIME Extensions for Local Big Data EnvironmentsFor details see https://www.knime.com/knime-extension-for-apache-sparkCreated with KNIME 3.7 on 25/02/2019 training datatrain model in Spark with k controlled by optimization loope.g. hillclimbinge.g. entropytest dataKNIME tableto RDDNode 174File Reader Spark k-Means Parameter OptimizationLoop Start Spark MLlib to PMML Cluster Assigner ParameterOptimization Loop End Scoring File Reader Table to Spark Create Local BigData Environment Mix and Match Description:This workflow mixes existing KNIME nodes with the new Spark nodes to find the optimal parameters for a k-means clustering using the hillclimbing approach. Requirements:- KNIME Analytics Platform + KNIME Optimization extension + KNIME Extension for Apache Spark + KNIME Extensions for Local Big Data EnvironmentsFor details see https://www.knime.com/knime-extension-for-apache-sparkCreated with KNIME 3.7 on 25/02/2019 training datatrain model in Spark with k controlled by optimization loope.g. hillclimbinge.g. entropytest dataKNIME tableto RDDNode 174File Reader Spark k-Means Parameter OptimizationLoop Start Spark MLlib to PMML Cluster Assigner ParameterOptimization Loop End Scoring File Reader Table to Spark Create Local BigData Environment

Nodes

Extensions

Links