Module orchestrate 

Orchestrates one full ensemble-predict call: builds the n_estimators member configs, runs each member’s preprocessing + a single TabFMModel::predict forward pass (reusing the core model unchanged), then aggregates — optionally applying calibration/NNLS ensemble weighting fit via oof.rs’s out-of-fold procedure.

Structs

ClassificationOutput

EnsembleParams

Parameters for one ensemble-predict call — the sklearn-wrapper-equivalent counterpart to TabFMClassifier(...)/TabFMRegressor(...)’s constructor kwargs. Fields are private; build one by chaining .with_*() off EnsembleParams::default (defaults match the wrapper’s own constructor defaults).

RegressionOutput

Functions

run_classification

run_members_classification

Runs every ensemble member’s forward pass for classification, given a train/query row split (query rows may be real held-out test rows, or an OOF fold’s validation rows). Members are grouped into batch_size-sized chunks (default: DEFAULT_BATCH_CHUNK_SIZE) and each chunk runs as a single TabFMModel::predict_batch call — sharing the fixed cost of the model’s deepest stage (24-block ICL) across the whole chunk instead of paying it once per member. Chunks run in parallel via rayon, combining with Round 1’s parallelism. Returns [member][query_row][class] logits, already un-shifted back to original class order.

run_members_regression

Same idea for regression: returns [member][query_row] scaled (not yet inverse-transformed) predictions.

run_regression