Icon

Biomass Analysis & Predictive Modeling for the Bioenergy Sector

There has been no title set for this workflow's metadata.

There has been no description set for this workflow's metadata.

Model tuning Training and prediction Remaining missingvalues ​​are replacedwith the column median A high number ofvalidations providesa stable estimate ofthe MAE An independentpartition is created fromthe train data forperformance evaluation Find hyperparametersthat provide the bestMAE Remaining missing values ​​are replaced with thecolumn median Training is set with the best hyperparameterscalculated with tuning Train readerValidation predictionsPerformance metrics (validation)Test predictionsPerformance metrics (test)Tuning loop startTest readerSave predictionsModel trainingCross validation endEnd tuning loopTrain readerModel trainingTest predictionM.V. imputation(train)M.V. imputation(test)Cross validation startM.V. imputation(train)M.V. imputation(validation)Train (85%)Test (15%)Train preprocessing(missing values)M.V. imputation(test)Train preprocessingTest preprocessingPredicted valuesextractionData visualizationSave trained modelCSV Reader Gradient Boosted TreesPredictor (Regression) Numeric Scorer Gradient Boosted TreesPredictor (Regression) Numeric Scorer Parameter OptimizationLoop Start CSV Reader CSV Writer Gradient Boosted TreesLearner (Regression) X-Aggregator ParameterOptimization Loop End CSV Reader Gradient Boosted TreesLearner (Regression) Gradient Boosted TreesPredictor (Regression) Missing Value Missing Value(Apply) X-Partitioner Missing Value Missing Value(Apply) Partitioning Preprocessing Missing Value(Apply) Preprocessing Preprocessing Postprocessing Scatter Plot Statistics Model Writer Model tuning Training and prediction Remaining missingvalues ​​are replacedwith the column median A high number ofvalidations providesa stable estimate ofthe MAE An independentpartition is created fromthe train data forperformance evaluation Find hyperparametersthat provide the bestMAE Remaining missing values ​​are replaced with thecolumn median Training is set with the best hyperparameterscalculated with tuning Train readerValidation predictionsPerformance metrics (validation)Test predictionsPerformance metrics (test)Tuning loop startTest readerSave predictionsModel trainingCross validation endEnd tuning loopTrain readerModel trainingTest predictionM.V. imputation(train)M.V. imputation(test)Cross validation startM.V. imputation(train)M.V. imputation(validation)Train (85%)Test (15%)Train preprocessing(missing values)M.V. imputation(test)Train preprocessingTest preprocessingPredicted valuesextractionData visualizationSave trained modelCSV Reader Gradient Boosted TreesPredictor (Regression) Numeric Scorer Gradient Boosted TreesPredictor (Regression) Numeric Scorer Parameter OptimizationLoop Start CSV Reader CSV Writer Gradient Boosted TreesLearner (Regression) X-Aggregator ParameterOptimization Loop End CSV Reader Gradient Boosted TreesLearner (Regression) Gradient Boosted TreesPredictor (Regression) Missing Value Missing Value(Apply) X-Partitioner Missing Value Missing Value(Apply) Partitioning Preprocessing Missing Value(Apply) Preprocessing Preprocessing Postprocessing Scatter Plot Statistics Model Writer

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: saver
Created at: 2023-11-29
On NodePit since: 2024-01-29
Last update: 2024-04-27
Created with KNIME version: v5.1.2

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

Try NodePit Runner!