Icon

Conformal predictive systems (simple)

This demo describes how to enrich the regression workflow with conformal prediction methods that allows to estimate model prediction certainity and control the desired error rate. The workflow is also implemented with Integrated deployment extension, so it automatically creates production code. Conformal prediction is agnostic to prediction algorithm, so users can easily replace it with any other classification algorithm.



Traininig/calibrationcontrolRead dataSelect producerModel trainingGet predictions forcalibration tableSigma - absolute errorcalibrationTrainingcalibrationGet predictionsfor unlabelled/testCreate car notationIterateproducersAppendproducersRename withnew notationRegex patternfor renamingEstimate predictionsif test is availableSet normalizationerror rateand betaSigma - absolute errorunlabelled/testDeploy workflowCapture training and calibrationUpdatetable specCapture predictionsprocessingNode 839Combine partsExecute deployed workflowRead deployed workflowNormalize features andtarget variableVisualize producersand modelsAssign percentileintervals hereReduce the sizeof the data setPartitioning Table Reader Select producer Random Forest Learner(Regression) Random Forest Predictor(Regression) Math Formula Partitioning Random Forest Predictor(Regression) RowID Column Aggregator Group Loop Start Loop End (ColumnAppend) Column Filter Column Rename(Regex) String Manipulation(Variable) Conformal Scorer(Regression) Conformal predictionconfiguration Math Formula Workflow Writer CaptureWorkflow End CaptureWorkflow Start Domain Calculator CaptureWorkflow Start CaptureWorkflow End Workflow Combiner Workflow Executor Column Filter Workflow Reader Normalizer Data visualization Predictive SystemsRegression Row Sampling Explanation example Significance leveloptimization results Traininig/calibrationcontrolRead dataSelect producerModel trainingGet predictions forcalibration tableSigma - absolute errorcalibrationTrainingcalibrationGet predictionsfor unlabelled/testCreate car notationIterateproducersAppendproducersRename withnew notationRegex patternfor renamingEstimate predictionsif test is availableSet normalizationerror rateand betaSigma - absolute errorunlabelled/testDeploy workflowCapture training and calibrationUpdatetable specCapture predictionsprocessingNode 839Combine partsExecute deployed workflowRead deployed workflowNormalize features andtarget variableVisualize producersand modelsAssign percentileintervals hereReduce the sizeof the data setPartitioning Table Reader Select producer Random Forest Learner(Regression) Random Forest Predictor(Regression) Math Formula Partitioning Random Forest Predictor(Regression) RowID Column Aggregator Group Loop Start Loop End (ColumnAppend) Column Filter Column Rename(Regex) String Manipulation(Variable) Conformal Scorer(Regression) Conformal predictionconfiguration Math Formula Workflow Writer CaptureWorkflow End CaptureWorkflow Start Domain Calculator CaptureWorkflow Start CaptureWorkflow End Workflow Combiner Workflow Executor Column Filter Workflow Reader Normalizer Data visualization Predictive SystemsRegression Row Sampling Explanation example Significance leveloptimization results

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: artem
Created at: 2023-03-11
On NodePit since: 2023-11-14
Last update: 2024-11-21
Created with KNIME version: v4.7.6
Tags: Conformal predictionRegressionIntegrated deploymentMachine learningPrediction analysis

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

Try NodePit Runner!