pyreal.explanation_types.example_based.SimilarExampleExplanation

class pyreal.explanation_types.example_based.SimilarExampleExplanation(explanation, values=None)

A type wrapper for explanations that include most similar rows from the training set.

Contains a dict of dataframes

__init__(explanation, values=None)

Set the wrapped explanation to explanation and values to values and validate :param explanation: wrapped explanation :type explanation: object :param values: Values corresponding with the object being explained :type values: DataFrame of shape (n_instances, n_features) or None

Methods

__init__(explanation[, values])	Set the wrapped explanation to explanation and values to values and validate :param explanation: wrapped explanation :type explanation: object :param values: Values corresponding with the object being explained :type values: DataFrame of shape (n_instances, n_features) or None
apply_feature_descriptions(feature_descriptions)	No-op because feature descriptions are applied at produce time for similar examples explanation, to improve performance
get()	Get the explanation wrapped by this type.
get_all()	Get the explanation and wrapped values as a tuple.
get_examples([row_id, rank])	Get the example in rank-th position for the given row_id. :param row_id: ID of row to get explanation of. :type row_id: int :param rank: Which example to return (ie, rank=0 returns the first example generated). If none, return all examples :type rank: int.
get_explanation()	Get the explanation wrapped by this type
get_row_ids()	Return all row_ids held by this explanation
get_targets([row_id, rank])	Get the targets in rank-th position for the given row_id. :param row_id: ID of row to get explanation of. :type row_id: int :param rank: Which example to return (ie, rank=0 returns the first example generated). If none, return all examples :type rank: int.
get_values()	Return the values associated with the explanation
update_examples(func[, inplace])	Update every example using the provided function :param func: Function to apply to every example :type func: function :param inplace: If True, change the explanation on this object. Otherwise, create a new object identical to this one but with a new explanation :type inplace: Boolean.
update_explanation(new_explanation[, ...])	Sets this object's explanation to the new value.
update_values(values[, inplace])	Updates this objects values, and validates
validate()	Validate that self.explanation is a valid dict of DataFrames :returns: None
validate_values()	Validate that self.values are valid values for this Explanation.