UnderAnnotatedMetaDataSegments

class UnderAnnotatedMetaDataSegments

Search for under annotated data segments.

The check is designed to help you easily identify under annotated segments of your data. The segments are based on the metadata - which is data that is not part of the text, but is related to it, such as “user_id” and “user_age”. For more on metadata, see the NLP Metadata Guide.

In order to achieve this, the check trains several simple tree based models which try to predict given a sample metadata whether it will have a label. The relevant segments are detected by analyzing the different leafs of the trained trees.

Parameters

columnsUnion[Hashable, List[Hashable]] , default: None

Columns to check, if none are given checks all columns except ignored ones.

ignore_columnsUnion[Hashable, List[Hashable]] , default: None

Columns to ignore, if none given checks based on columns variable

n_top_columnsOptional[int] , default: 10

Number of features to use for segment search. Top columns are selected based on feature importance.

segment_minimum_size_ratio: float , default: 0.05

Minimum size ratio for segments. Will only search for segments of size >= segment_minimum_size_ratio * data_size.

n_samplesint , default: 10_000

Maximum number of samples to use for this check.

n_to_showint , default: 3

number of segments with the weakest performance to show.

categorical_aggregation_thresholdfloat , default: 0.05

In each categorical column, categories with frequency below threshold will be merged into “Other” category.

multiple_segments_per_columnbool , default: True

If True, will allow the same metadata column to be a segmenting column in multiple segments, otherwise each metadata column can appear in one segment at most.

__init__(columns: Optional[Union[Hashable, List[Hashable]]] = None, ignore_columns: Optional[Union[Hashable, List[Hashable]]] = None, n_top_columns: Optional[int] = 10, segment_minimum_size_ratio: float = 0.05, n_samples: int = 10000, categorical_aggregation_threshold: float = 0.05, n_to_show: int = 3, multiple_segments_per_column: bool = True, **kwargs)

__new__(*args, **kwargs)

Attributes

UnderAnnotatedMetaDataSegments.categorical_aggregation_threshold
UnderAnnotatedMetaDataSegments.min_category_size_ratio
UnderAnnotatedMetaDataSegments.n_to_show
UnderAnnotatedMetaDataSegments.n_top_features
UnderAnnotatedMetaDataSegments.random_state
UnderAnnotatedMetaDataSegments.segment_minimum_size_ratio

Methods

UnderAnnotatedMetaDataSegments.add_condition(...)	Add new condition function to the check.
UnderAnnotatedMetaDataSegments.add_condition_segments_annotation_ratio_greater_than([...])	Add condition - check that the in all segments annotation ratio is above the provided threshold.
UnderAnnotatedMetaDataSegments.add_condition_segments_relative_performance_greater_than([...])	Add condition - check that the score of the weakest segment is greater than supplied relative threshold.
UnderAnnotatedMetaDataSegments.clean_conditions()	Remove all conditions from this check instance.
UnderAnnotatedMetaDataSegments.conditions_decision(result)	Run conditions on given result.
UnderAnnotatedMetaDataSegments.config([...])	Return check configuration (conditions' configuration not yet supported).
UnderAnnotatedMetaDataSegments.from_config(conf)	Return check object from a CheckConfig object.
UnderAnnotatedMetaDataSegments.from_json(conf)	Deserialize check instance from JSON string.
UnderAnnotatedMetaDataSegments.metadata([...])	Return check metadata.
UnderAnnotatedMetaDataSegments.name()	Name of class in split camel case.
UnderAnnotatedMetaDataSegments.params([...])	Return parameters to show when printing the check.
UnderAnnotatedMetaDataSegments.remove_condition(index)	Remove given condition by index.
UnderAnnotatedMetaDataSegments.run(dataset)	Run check.
UnderAnnotatedMetaDataSegments.run_logic(...)	Run check.
UnderAnnotatedMetaDataSegments.to_json([...])	Serialize check instance to JSON string.

previous

UnknownTokens.to_json

next

UnderAnnotatedMetaDataSegments.categorical_aggregation_threshold