Parent
#91
What to build
Replace the hardcoded BayesianRidge inside the MICE fitting block with adaptive estimator selection driven by NonlinearityTag. Collect the tag from each MICE column's NumericStats, take the most-complex tag across the block (ComplexNonlinear > MonotonicNonlinear > Linear > Unpredictable), and pass it with n_rows to RegressionEstimatorFactory. If every MICE column is Unpredictable, skip the MICE block entirely and fall each column back to Median via _fallback_to_median. Record the chosen estimator name and the driving NonlinearityTag in every MICE column's ColumnImputationRecord.signals.
This is the foundation slice — slices for dynamic max_iter/tol, initial_strategy, and n_nearest_features all build on the parameterised IterativeImputer construction introduced here.
Acceptance criteria
Blocked by
Parent
#91
What to build
Replace the hardcoded
BayesianRidgeinside the MICE fitting block with adaptive estimator selection driven byNonlinearityTag. Collect the tag from each MICE column'sNumericStats, take the most-complex tag across the block (ComplexNonlinear>MonotonicNonlinear>Linear>Unpredictable), and pass it withn_rowstoRegressionEstimatorFactory. If every MICE column isUnpredictable, skip the MICE block entirely and fall each column back to Median via_fallback_to_median. Record the chosen estimator name and the drivingNonlinearityTagin every MICE column'sColumnImputationRecord.signals.This is the foundation slice — slices for dynamic
max_iter/tol,initial_strategy, andn_nearest_featuresall build on the parameterisedIterativeImputerconstruction introduced here.Acceptance criteria
IterativeImputerwith the estimator returned byRegressionEstimatorFactoryinstead of the defaultBayesianRidgeComplexNonlinear>MonotonicNonlinear>Linear>UnpredictableUnpredictable: no MICE model is stored; each column's record is updated toMedianstrategy via_fallback_to_medianwith a clear signalsignalscontains an entry recording the estimator name (e.g."mice_estimator: GradientBoostingRegressor (tag=ComplexNonlinear)")signalscontains an entry recording the drivingNonlinearityTagGradientBoostingRegressoris selected forComplexNonlinearblocks abovegradient_boost_min_rows;RandomForestRegressorforComplexNonlinearblocks at or below that thresholdComplexNonlinearcolumn produces a non-linear estimator signal on all MICE column recordsUnpredictableproduces no MICE model and each column's record showsMedianstrategy with a fallback signalBlocked by