citrine.informatics.predictor_evaluation_result module

class citrine.informatics.predictor_evaluation_result.CategoricalPredictedVsActual

Bases: Serializable[CategoricalPredictedVsActual], MetricValue

List of predicted vs. actual data points for a categorical value.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

classmethod get_type(data) → Type[Serializable]

Return the subtype.

typ = 'CategoricalPredictedVsActual'

value = None

List of predicted vs. actual data computed during a predictor evaluation. This is a flattened list that contains data for all trials and folds.

Type:

List[PredictedVsActualCategoricalPoint]

class citrine.informatics.predictor_evaluation_result.CrossValidationResult

Bases: Serializable[CrossValidationResult], PredictorEvaluationResult

Result of performing a cross-validation evaluation on a predictor.

Results for a cross-validated response can be accessed via cvResult['response_name'], where cvResult is a citrine.informatics.predictor_evaluation_result.CrossValidationResult and 'response_name' is a response analyzed by a citrine.informatics.predictor_evaluator.CrossValidationEvaluator.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

classmethod get_type(data) → Type[Serializable]

Return the subtype.

property evaluator: CrossValidationEvaluator

Evaluator that produced this result.

Type:

PredictorEvaluator

property metrics: Set[PredictorEvaluationMetric]

Metrics for which results are present.

Type:

Set[PredictorEvaluationMetric]

property responses: Set[str]

Responses for which results are present.

typ = 'CrossValidationResult'

class citrine.informatics.predictor_evaluation_result.MetricValue

Bases: PolymorphicSerializable[MetricValue]

Value associated with a metric computed during a Predictor Evaluation Workflow.

classmethod build(data: dict) → SelfType

Build the underlying type.

classmethod get_type(data) → Type[Serializable]

Return the subtype.

class citrine.informatics.predictor_evaluation_result.PredictedVsActualCategoricalPoint

Bases: Serializable[PredictedVsActualCategoricalPoint]

Predicted vs. actual data for a single categorical data point.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

actual = None

Actual class probabilities defined as a map from each class name to its relative frequency

Type:

Dict[str, float]

fold = None

1-based index of the fold this candidate belonged to

Type:

int

identifiers = None

Set of globally unique identifiers given to the candidate

Type:

Set[str]

predicted = None

Predicted class probabilities defined as a map from each class name to its relative frequency

Type:

Dict[str, float]

trial = None

1-based index of the trial this candidate belonged to

Type:

int

uuid = None

Unique Citrine id given to the candidate

Type:

UUID

class citrine.informatics.predictor_evaluation_result.PredictedVsActualRealPoint

Bases: Serializable[PredictedVsActualRealPoint]

Predicted vs. actual data for a single real-valued data point.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

actual = None

Actual value

Type:

RealMetricValue

fold = None

1-based index of the fold this candidate belonged to

Type:

int

identifiers = None

Set of globally unique identifiers given to the candidate

Type:

Set[str]

predicted = None

Predicted value

Type:

RealMetricValue

trial = None

1-based index of the trial this candidate belonged to

Type:

int

uuid = None

Unique Citrine id given to the candidate

Type:

UUID

class citrine.informatics.predictor_evaluation_result.PredictorEvaluationResult

Bases: PolymorphicSerializable[PredictorEvaluationResult]

A Citrine Predictor Evaluation Result.

This class represents a set of metrics computed by a Predictor Evaluator.

classmethod build(data: dict) → SelfType

Build the underlying type.

classmethod get_type(data) → Type[Serializable]

Return the subtype.

property evaluator: PredictorEvaluator

Evaluator that produced the result.

Type:

PredictorEvaluator

property metrics: Set[PredictorEvaluationMetric]

Metrics computed for predictor responses.

Type:

Set[PredictorEvaluationMetric]

property responses: Set[str]

Predictor responses that were evaluated.

class citrine.informatics.predictor_evaluation_result.RealMetricValue

Bases: Serializable[RealMetricValue], MetricValue

Mean and standard error computed for a real-valued metric.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

classmethod get_type(data) → Type[Serializable]

Return the subtype.

mean = None

Mean value

Type:

float

standard_error = None

Standard error of the mean

Type:

Optional[float]

typ = 'RealMetricValue'

class citrine.informatics.predictor_evaluation_result.RealPredictedVsActual

Bases: Serializable[RealPredictedVsActual], MetricValue

List of predicted vs. actual data points for a real value.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

classmethod get_type(data) → Type[Serializable]

Return the subtype.

typ = 'RealPredictedVsActual'

value = None

List of predicted vs. actual data computed during a predictor evaluation. This is a flattened list that contains data for all trials and folds.

Type:

List[PredictedVsActualRealPoint]

class citrine.informatics.predictor_evaluation_result.ResponseMetrics

Bases: Serializable[ResponseMetrics]

Set of metrics computed by a Predictor Evaluator for a single response.

Results computed for a metric can be accessed by the metric’s __repr__ or by the metric itself.

classmethod build(data: dict) → Self

Build an instance of this object from given data.

dump() → dict

Dump this instance.

metrics = None

Metrics computed for a single response, keyed by the metric’s __repr__.

Type:

Dict[str, MetricValue]