schema.processors.marketing_processor.MarketingAnalysisSpec

Stores parameters needed for processing a model into MarketingAnalysiss.

Inherits From: DatedSpec

schema.processors.marketing_processor.MarketingAnalysisSpec(
    start_date: (datetime.date | None) = None,
    end_date: (datetime.date | None) = None,
    date_interval_tag: str = '',
    *,
    media_summary_spec: (schema.processors.marketing_processor.MediaSummarySpec | None) = None,
    incremental_outcome_spec: (schema.processors.marketing_processor.IncrementalOutcomeSpec | None) = None,
    response_curve_spec: schema.processors.marketing_processor.ResponseCurveSpec = dataclasses.field(default_factory=ResponseCurveSpec),
    confidence_level: float = constants.DEFAULT_CONFIDENCE_LEVEL
)

Either media_summary_spec or incremental_outcome_spec must be provided, but not both.

media_summary_spec Parameters for creating media summary metrics. Mutually exclusive with incremental_outcome_spec.
incremental_outcome_spec Parameters for creating incremental outcome. Mutually exclusive with media_summary_spec. If new_data is provided, then the start and end dates of this MarketingAnalysisSpec must be within the new_data.time.
response_curve_spec Parameters for creating response curves. Response curves are only computed for specs that aggregate times and have a media_summary_spec selected.
confidence_level Confidence level for credible intervals, represented as a value between zero and one. Defaults to 0.9.
start_date Dataclass field
end_date Dataclass field
date_interval_tag Dataclass field

Methods

resolver

View source

resolver(
    time_coordinates: tc.TimeCoordinates
) -> 'DatedSpecResolver'

Returns a date resolver for this spec, with the given Meridian model.

validate

View source

validate()

Overrides the Spec.validate() method to check that dates are valid.

__eq__

__eq__(
    other
)

Return self==value.

confidence_level 0.9
date_interval_tag ''
end_date None
incremental_outcome_spec None
media_summary_spec None
start_date None