niftynet.evaluation.classification_evaluations module

This module defines built-in evaluation functions for classification applications

Many classification metrics only make sense computed over all subjects, so aggregation is used.

class accuracy(reader, app_param, eval_param)

Bases: niftynet.evaluation.base_evaluations.BaseEvaluation

layer_op(subject_id, data)

Perform one evaluation calculation for one subject :param subject_id: subject identifier string :param data: a data dictionary as built by ImageReader :return: a list of pandas.DataFrame objects

aggregate(df)

get_aggregations()

Returns aggregations to compute for the metric. Each aggregation is a callable that computes a list of DataFrames from a dictionary of metric dataframes (index by the DataFrame index). See BaseEvaluator.ScalarAggregator for an example.

Returns:list of aggregation callables