quantlab.factor.config.MembershipMaskedFactorConfig#

class quantlab.factor.config.MembershipMaskedFactorConfig(*, warmup_bars=0, dataset=None, file_path=None, factor_names=None, kwargs=None, resample_freq=None, resample_how=None, name=None, factor, membership)[source]#

Bases: FactorViewConfig

Config of quantlab.factor.predefined.membership_mask.MembershipMaskedFactor.

factor is the factor masked; it keeps its own config, warm-up and store, and is computed on unmasked prices. membership is the point-in-time index membership (its is_member panel) the cells are judged by. dataset is filled with the wrapped factor’s dataset, so a model counts warm-up bars on the wrapped factor’s calendar. All three are component fields, so to_dict() nests their configs and MembershipMaskedFactor.from_config rebuilds them.

Examples

With alphas a RosterFactor over a market-wide store and membership the S&P 500 membership dataset:

>>> cfg = MembershipMaskedFactorConfig(factor=alphas, membership=membership)
>>> cfg.warmup_bars, cfg.file_path
(0, None)

membership#: The point-in-time membership the cells are judged by.