Reference¶

class Workspace(create_key, workspace: Workspace)¶
classmethod create_from_config(config: Config) Workspace¶
classmethod create_from_json_model(model_json: Dict[str, Any]) Workspace¶
classmethod create_from_model(data: bytearray) Workspace¶
create_parser(format_type: Literal[FormatType.VwText]) TextParser¶
create_parser(format_type: Union[Literal[FormatType.DsJson], Literal[FormatType.Json]]) JsonParser
property entry_reduction_types: ReductionTypesDescription¶
learn(features: SparseFeatures | CbAdfFeatures, label: SimpleLabel | CbLabel) None¶
predict(features: SparseFeatures | CbAdfFeatures) ScalarPred | ActionScoresPred | ActionProbsPred¶
predict_then_learn(features: SparseFeatures | CbAdfFeatures, label: SimpleLabel | CbLabel) ScalarPred | ActionScoresPred | ActionProbsPred¶
serialize() bytearray¶
serialize_to_json() Dict[str, Any]¶
class JsonParser¶
parse(input: Union[Dict[str, Any], str]) Tuple[Union[SparseFeatures, CbAdfFeatures], Optional[SimpleLabel | CbLabel]]¶
class TextParser¶
parse(input: str) Tuple[Union[SparseFeatures, CbAdfFeatures], Optional[SimpleLabel | CbLabel]]¶
class ReductionTypesDescription(self, input_label_type: LabelType, output_prediction_type: PredictionType, input_features_type: FeaturesType, output_label_type: LabelType | None = None, input_prediction_type: PredictionType | None = None, output_features_type: FeaturesType | None = None)¶
input_features_type¶

The features type expected as input for this reduction

Return type:

FeaturesType

input_label_type¶

The label type expected as input for this reduction

Return type:

LabelType

input_prediction_type¶

The prediction type expected as input for this reduction. If this is a base reduction, this will be None

Return type:

Optional[PredictionType]

output_features_type¶

The features type expected as output for this reduction. If this is a base reduction, this will be None

Return type:

Optional[FeaturesType]

output_label_type¶

The label type expected as output for this reduction. If this is a base reduction, this will be None

Return type:

Optional[LabelType]

output_prediction_type¶

The prediction type expected as output for this reduction

Return type:

PredictionType

class FormatType¶
DsJson = FormatType.DsJson¶
Json = FormatType.Json¶
VwText = FormatType.VwText¶

Configuration¶

class Config¶

While this shows up as a class, it is actually a TypedDict. So it can be instantiated as a dict or as a class.

entryReduction: EntryReductionConfig¶
globalConfig: GlobalConfig¶
class GlobalConfig¶

While this shows up as a class, it is actually a TypedDict. So it can be instantiated as a dict or as a class.

constantFeatureEnabled: NotRequired[bool]¶
hashSeed: NotRequired[int]¶
interactions: NotRequired[List[Literal['Default'] | NameInteraction]]¶
numBits: NotRequired[int]¶
class EntryReductionConfig¶

While this shows up as a class, it is actually a TypedDict. So it can be instantiated as a dict or as a class.

config: NotRequired[Dict[str, Any]]¶
typename: str¶
Interaction¶

alias of Literal[‘Default’] | NameInteraction

class NameInteraction¶
name: str¶

Labels¶

class LabelType¶

Type of label

Binary = LabelType.Binary¶
CB = LabelType.CB¶
Simple = LabelType.Simple¶
class SimpleLabel(value: float, weight: float = 1.0)¶
Parameters:
  • value (float) – Label value

  • weight (float) – Label weight

value¶

The label’s value

Return type:

float

weight¶

Weight of example to be used in update

Return type:

float

class CbLabel(action: int, cost: float, probability: float)¶
Parameters:
  • action (int) – Chosen action (zero based)

  • cost (float) – Cost of chosen action

  • probability (float) – Probability of chosen action

action¶

The label’s action

Return type:

int

cost¶

The label’s cost

Return type:

float

probability¶

The label’s probability

Return type:

float

Predictions¶

class PredictionType¶

Type of prediction

ActionProbs = PredictionType.ActionProbs¶
ActionScores = PredictionType.ActionScores¶
Binary = PredictionType.Binary¶
Scalar = PredictionType.Scalar¶
class ScalarPred(prediction: float, raw_prediction: float)¶
Parameters:
  • prediction (float) – Prediction value (including clamping by the seen range and link function)

  • raw_prediction (float) – Raw prediction value

prediction¶
raw_prediction¶
class ActionScoresPred(value: List[Tuple[int, float]])¶
Parameters:

value – A list of tuples of the form (action, score)

value¶
class ActionProbsPred(value: List[Tuple[int, float]])¶
Parameters:

value – A list of tuples of the form (action, probability)

value¶

Features¶

class FeaturesType¶

Type of features

SparseCbAdf = FeaturesType.SparseCbAdf¶
SparseSimple = FeaturesType.SparseSimple¶
class CbAdfFeatures¶
class SparseFeatures¶
class typing_extensions.NotRequired¶

See typing_extensions.NotRequired