Semi-Supervised Ensemble Learning

---

Documentation for package ‘ssel’ version 0.3.1

• DESCRIPTION file
• User guides, package vignettes and other documentation
• Package NEWS
• Package README

Help Pages

activeByImportance	Select chain responses by mean normalized importance
activeByShadow	Select chain responses by a shadow comparison
aggregateResponses	Select and assemble final response deliveries
auditOverfit	Audit package-defined in-sample optimism
auditQuantiles	Estimate signed OOF-residual offsets
buildDataset	Build per-response training and prediction files
chainPipeline	Fit an iterative multi-response companion chain
computeActiveByImportance	Extract, threshold, and intersect fixed-gate chain responses
detectOutliers	Flag regression training outliers
extractChainImportance	Extract normalized importance for response companions
modelPipeline	Orchestrate the supervised ssel workflow
oofEnsemble	Reconstruct a projected OOF ensemble
postProcess	Assemble user-facing prediction deliverables.
predictModel	Evaluate fitted cells and select response-level deliveries
removeOutliersIQR	Remove rows outside feature IQR envelopes
semiSupervisedPipeline	Fit a range-ratio pseudo-label promotion loop
toNumeric	Convert supported numeric strings to numeric values
trainModel	Fit a discovered response-dataset grid
trainRegressionModel	Fit cells or reconstruct their OOF metrics and predictions
which.nonnum	Locate values outside base R's numeric grammar