moscot.base.problems.CompoundProblem.prepare

CompoundProblem.prepare(policy, key, subset=None, reference=None, xy=mappingproxy({}), x=mappingproxy({}), y=mappingproxy({}), xy_callback=None, x_callback=None, y_callback=None, xy_callback_kwargs=mappingproxy({}), x_callback_kwargs=mappingproxy({}), y_callback_kwargs=mappingproxy({}), a=None, b=None, marginal_kwargs=mappingproxy({}))

Prepare the individual OT subproblems.

See also

• See Subset policy on how to use different policies.

Parameters:

• policy (Literal['sequential', 'star', 'external_star', 'explicit', 'triu', 'tril']) – Rule which defines how to construct the subproblems.

• key (Optional[str]) – Key in obs for the SubsetPolicy.

• subset (Optional[Sequence[Tuple[TypeVar(K, bound= Hashable), TypeVar(K, bound= Hashable)]]]) – Subset of obs['{key}'] for the ExplicitPolicy. Only used when policy = 'explicit'.

• reference (Optional[Any]) – Reference for the SubsetPolicy. Only used when policy = 'star'.

• xy (Mapping[str, Any]) – Data for the linear term.

• x (Mapping[str, Any]) – Data for the source quadratic term.

• y (Mapping[str, Any]) – Data for the target quadratic term.

• xy_callback (Union[Literal['local-pca'], Callable[[Literal['xy', 'x', 'y'], AnnData, Optional[AnnData]], Optional[TaggedArray]], None]) – Callback function used to prepare the data in the linear term.

• x_callback (Union[Literal['local-pca'], Callable[[Literal['xy', 'x', 'y'], AnnData, Optional[AnnData]], Optional[TaggedArray]], None]) – Callback function used to prepare the data in the source quadratic term.

• y_callback (Union[Literal['local-pca'], Callable[[Literal['xy', 'x', 'y'], AnnData, Optional[AnnData]], Optional[TaggedArray]], None]) – Callback function used to prepare the data in the target quadratic term.

• xy_callback_kwargs (Mapping[str, Any]) – Keyword arguments for the xy_callback.

• x_callback_kwargs (Mapping[str, Any]) – Keyword arguments for the x_callback.

• y_callback_kwargs (Mapping[str, Any]) – Keyword arguments for the y_callback.

• a (Union[bool, str, ndarray[tuple[int, ...], dtype[floating]], Array, None]) –

  Source marginals. Valid options are:

  • str - key in obs where the source marginals are stored.

  • bool - if True, estimate the marginals, otherwise use uniform marginals.

  • None - uniform marginals.

• b (Union[bool, str, ndarray[tuple[int, ...], dtype[floating]], Array, None]) –

  Target marginals. Valid options are:

  • str - key in obs where the target marginals are stored.

  • bool - if True, estimate the marginals, otherwise use uniform marginals.

  • None - uniform marginals.

• marginal_kwargs (Mapping[str, Any]) – Keyword arguments for the estimate_marginals() method.

Return type:

BaseCompoundProblem[TypeVar(K, bound= Hashable), TypeVar(B, bound= OTProblem)]

Returns:

: Returns self and updates the following fields:

• problems - the prepared subproblems.

• solutions - set to an empty dict.

• stage - set to 'prepared'.

• problem_kind - kind of the OT problem.