bluepyemodel.evaluation.efeature_configuration

EFeatureConfiguration

Classes

EFeatureConfiguration(efel_feature_name, ...)

Container for the definition of an EFeature
class EFeatureConfiguration(efel_feature_name, protocol_name, recording_name, mean, efeature_name=None, efel_settings=None, threshold_efeature_std=None, original_std=None, std=None, sample_size=None, default_std_value=0.001, weight=1.0)

Bases: object

Container for the definition of an EFeature

Init.

The arguments efeatures and protocols are expected to be in the format used for the storage of the fitness calculator configuration. To store the results of an extraction, use the method init_from_bluepyefe.

Parameters:

  • efel_feature_name (str) – name of the eFEl feature.

  • protocol_name (str) – name of the protocol to which the efeature is associated. For example “Step_200”.

  • recording_name (str or dict) – name of the recording(s) of the protocol. For example: “soma.v” or if and only if the feature depends on several recordings: {“”: “soma.v”, “location_AIS”: “axon.v”}.

  • mean (float) – mean of the efeature.

  • original_std (float) – unmodified standard deviation of the efeature

  • std (float) – kept for legacy purposes.

  • efeature_name (str) – given name for this specific feature. Can be different from the efel efeature name.

  • efel_settings (dict) – eFEl settings.

  • threshold_efeature_std (float) – lower limit for the std expressed as a percentage of the mean of the features value (optional).

  • sample_size (float) – number of data point that were used to compute the present average and standard deviation.

  • weight (float) – weight of the efeature. Basically multiplies the score of the efeature by this value.

as_dict()

Dictionary form

property std

Limit the standard deviation with a lower bound equal to a percentage of the mean.