Icon

20230214 Pikairos Analyse Random Forest error improvement with additional trees

This workflow illustrates how to measure the error performance of a Random Forest Classifier based on the number of trees.

THe workflow brings a possible answer to question asked by Molly123 at post number 61664 in the KNIME forum.

ReadTitanic ClassificationDatasetPartition Datainto70% Training Set30% Test SetTrain RFConfigured withCurrent IterationNb of ModelsPredict RFSurvival onTest SetLoop 500 TimesUse Current Iteration Valueto Set the Number of Treesin RF LearnerStarting from 1Test Performanceon Test SetGather ScoringfromScorer VariablesPlot RF Errorsversus# of Modelsfrom 1 to 500File Reader Partitioning Random ForestLearner Random ForestPredictor Counting Loop Start Math Formula(Variable) Scorer Variable Loop End Line Plot ReadTitanic ClassificationDatasetPartition Datainto70% Training Set30% Test SetTrain RFConfigured withCurrent IterationNb of ModelsPredict RFSurvival onTest SetLoop 500 TimesUse Current Iteration Valueto Set the Number of Treesin RF LearnerStarting from 1Test Performanceon Test SetGather ScoringfromScorer VariablesPlot RF Errorsversus# of Modelsfrom 1 to 500File Reader Partitioning Random ForestLearner Random ForestPredictor Counting Loop Start Math Formula(Variable) Scorer Variable Loop End Line Plot

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: Molina
Created at: 2023-02-14
On NodePit since: 2023-02-14
Last update: 2024-04-27
Created with KNIME version: v4.5.2
Tags: File ReaderPartitioningCounting Loop StartMath Formula VariableRandorm Forest LearnerRandom Forest PredictorScorerVariable Loop EndLin Plot

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

Try NodePit Runner!