credit.applications.preprocess

Functions

_scaler_probe_range(scaler)	Return (lo, hi, label) normalized probe endpoints for a fitted scaler.
_scaler_device(scaler)	Best-effort lookup of the torch device holding a scaler's fitted stats.
_log_single_scaler(scaler, name, logger)	Log the fitted parameters of one leaf scaler, one line per channel/level.
log_fitted_scalers(scaler_dict, logger[, path])	Recursively log every fitted scaler in a nested scaler[data_type][source][var] dict.
main()

Module Contents

credit.applications.preprocess._scaler_probe_range(scaler)

Return (lo, hi, label) normalized probe endpoints for a fitted scaler.

The endpoints span the range of normalized values the scaler typically produces, so an inverse transform reveals what physical values each scaler maps that range to:

• minmax -> [0, 1]

• standard -> [-4, 4] (±4 standard deviations)

• quantile -> [0, 1] for a uniform output distribution, otherwise

  [-4, 4] (e.g. normal/logistic)

credit.applications.preprocess._scaler_device(scaler)

Best-effort lookup of the torch device holding a scaler’s fitted stats.

credit.applications.preprocess._log_single_scaler(scaler, name, logger)

Log the fitted parameters of one leaf scaler, one line per channel/level.

credit.applications.preprocess.log_fitted_scalers(scaler_dict, logger, path=())

Recursively log every fitted scaler in a nested scaler[data_type][source][var] dict.

credit.applications.preprocess.main()