Aggregation

Step 5 of the pipeline.

Aggregation combines the different user models to construct a global model. The aggregation may also adjust the user models to the learned global model.

Aggregation

__call__

__call__(
    voting_rights: VotingRights,
    user_models: Mapping[int, ScoringModel],
    users: DataFrame,
    entities: DataFrame,
) -> tuple[dict[int, ScoringModel], ScoringModel]

Returns scaled user models

Parameters:

Name	Type	Description	Default
voting_rights	VotingRights	voting_rights[user, entity]: float	required
user_models	Mapping[int, ScoringModel]	user_models[user] is user's scoring model	required
users	DataFrame	user_id (int, index) trust_score (float)	required
entities	DataFrame	entity_id (int, ind)	required

Returns:

Name	Type	Description
	updated_user_models[user]: ScoringModel	Returns a scaled user model
global_model	ScoringModel	Returns a global scoring model

Average

Bases: Aggregation

__call__

__call__(
    voting_rights: VotingRights,
    user_models: dict[int, ScoringModel],
    users: DataFrame,
    entities: DataFrame,
) -> tuple[dict[int, ScoringModel], ScoringModel]

Returns scaled user models

Parameters:

Name	Type	Description	Default
voting_rights	VotingRights	voting_rights[user, entity]: float	required
user_models	dict[int, ScoringModel]	user_models[user] is user's scoring model	required
users	DataFrame	user_id (int, index) trust_score (float)	required
entities	DataFrame	entity_id (int, ind)	required

Returns:

Name	Type	Description
	updated_user_models[user]: ScoringModel	Returns a scaled user model
global_model	ScoringModel	Returns a global scoring model

EntitywiseQrQuantile

EntitywiseQrQuantile(
    quantile=0.2, lipschitz=0.1, error=1e-05
)

Bases: Aggregation

Aggregates the scores per entity with qr_quantile.

Parameters:

Name	Type	Description	Default
quantile			0.2
lipschitz			0.1
error			1e-05

__call__

__call__(
    voting_rights: VotingRights,
    user_models: dict[int, ScoringModel],
    users: DataFrame,
    entities: DataFrame,
) -> tuple[dict[int, ScoringModel], ScoringModel]

Returns scaled user models

Parameters:

Name	Type	Description	Default
voting_rights	VotingRights	voting_rights[user, entity]: float	required
user_models	dict[int, ScoringModel]	user_models[user] is user's scoring model	required
users	DataFrame	user_id (int, index) trust_score (float)	required
entities	DataFrame	entity_id (int, ind)	required

Returns:

Name	Type	Description
	updated_user_models[user]: ScoringModel	Returns a scaled user model
global_model	ScoringModel	Returns a global scoring model

StandardizedQrQuantile

StandardizedQrQuantile(
    quantile=0.2,
    dev_quantile=0.9,
    lipschitz=0.1,
    error=1e-05,
)

Bases: Aggregation

Standardize scores so that only a fraction 1 - dev_quantile of the scores is further than 1 away from the requested quantile, and then run qr_quantile to aggregate the scores.

Parameters:

Name	Type	Description	Default
quantile			0.2
dev_quantile			0.9
lipschitz			0.1
error			1e-05

__call__

__call__(
    voting_rights: VotingRights,
    user_models: dict[int, ScoringModel],
    users: DataFrame,
    entities: DataFrame,
) -> tuple[dict[int, ScaledScoringModel], ScoringModel]

Returns scaled user models

Parameters:

Name	Type	Description	Default
voting_rights	VotingRights	voting_rights[user, entity]: float	required
user_models	dict[int, ScoringModel]	user_models[user] is user's scoring model	required
users	DataFrame	user_id (int, index) trust_score (float)	required
entities	DataFrame	entity_id (int, ind)	required

Returns:

Name	Type	Description
	updated_user_models[user]: ScoringModel	Returns a scaled user model
global_model	ScoringModel	Returns a global scoring model