Prediction Options

PredictionOptions

A configurable base options class for relevance-based predictions, including predict, maxfit, and grid models. This class provides a comprehensive list of all possible input parameters, ensuring flexibility across different prediction models. While some parameters are shared across inherited models, setting an unused option for a specific model will have no effect, ensuring compatibility and ease of use.

Key	Type	Description
threshold	float or ndarray [1-by-], optional (default=None)	Evaluation threshold to determine whether observations will be included or excluded from the censor function in the partial-sample regression. If not specified (None), the censor function will evaluate across threshold from [0, 0.90) in 0.10 increments.
is_threshold_percent	bool, optional (default=True)	Specify whether threshold(s) are in percentage (decimal) units.
most_eval	bool, optional (default=True)	Specify the of the censor evaluation of the threshold.
eval_type	str, optional (default="both")	Specify the evaluation censor type: relevance, similarity, or both.

MaxFitOptions(PredictionOptions)

A specialized options class for MaxFit problems.

Inherits from `PredictionOptions` and adds additional parameters specific to MaxFit prediction tasks. This class ensures that users can leverage all standard prediction options while also configuring MaxFit-specific behaviors to optimize model fitting based on the highest (adjusted) fit.

Key	Type	Description
threshold	float or ndarray [1-by-], optional (default=[0, 0.20, 0.50, 0.80])	Thresholds for evaluating maxfit threshold, by default (0, 0.20, 0.50, 0.80).
objective	str, optional (default=adjusted_fit)	Specify the objective function of the max fit solver, by default this is adjusted fit.

GridOptions(MaxFitOptions)

A specialized options class for grid prediction tasks.

Inherits from `MaxFitOptions` and introduces additional parameters specific to grid-based prediction models. This class allows users to configure both standard MaxFit options and advanced settings required for relevance-based grid predictions, enabling flexible and optimized grid searches across thresholds and variable combinations.

Key	Type	Description
attribute_combi	ndarray [-by-], optional (default=None)	Matrix of binary row vectors to indicate variable choices. Each row is a combination of variables to evaluate. If not specified, function will evaluate all possible combinations.
k	float, optional (default=1)	Lower bound for the number of variables to include for any combination Q, by default 1.