Data and machine learning

These APIs preserve event-time and label-availability boundaries when building historical datasets, replaying runs, backtesting, or evaluating predictions.

Point-in-time datasets

fraudtwin.ml.dataset.PointInTimeDataset	Stable rows and the manifest that describes their construction.
fraudtwin.ml.dataset.PointInTimeDatasetBuilder	Build historical features and labels using only available source data.
fraudtwin.ml.dataset.build_point_in_time_dataset	Convenience API for deterministic in-memory M9 construction.
fraudtwin.ml.dataset.write_point_in_time_dataset	Write the fixed-schema M9 Parquet table and its JSON manifest.
fraudtwin.ml.dataset.load_generated_run	Load one existing generated run without regenerating unrelated records.

Backtesting and prediction evaluation

fraudtwin.ml.backtest.BacktestResult	Fold rows, metrics, and the immutable result manifest.
fraudtwin.ml.backtest.run_backtest	Build reproducible rolling folds from one existing generated history.
fraudtwin.ml.backtest.run_model_backtest	Run selected M19 model adapters over the existing M10 temporal folds.
fraudtwin.ml.backtest.write_backtest	Persist fold rows, metrics, and the append-only backtest manifest.
fraudtwin.ml.baseline.PredictionRecord	One external prediction at a point in time.
fraudtwin.ml.baseline.EvaluationResult	EvaluationResult(predictions: tuple[dict[str, typing.Any], ...], metrics: tuple[dict[str, typing.Any], ...], manifest: dict[str, typing.Any], model_artifacts: dict[str, bytes] | None = None)
fraudtwin.ml.baseline.evaluate_predictions	Evaluate external scores against a leakage-safe dataset.
fraudtwin.ml.baseline.train_baselines	Train configured deterministic baselines on train rows only.

Drift analysis

Compare two point-in-time windows with deterministic PSI, Wasserstein, and Jensen–Shannon metrics. The report records window fingerprints and the label policy so an alert can be reproduced later.

fraudtwin.ml.drift.DriftConfig	Immutable policy controlling a drift comparison.
fraudtwin.ml.drift.DriftMetric	One measured drift value and its decision threshold.
fraudtwin.ml.drift.DriftReport	Reproducible comparison of two row windows.
fraudtwin.ml.drift.compare_windows	Compare two row windows using deterministic distribution metrics.
fraudtwin.ml.drift.compare_performance	Compare matching evaluation metrics under one threshold policy.