chainer_chemistry.training.extensions.roc_auc_evaluator.ROCAUCEvaluator

class chainer_chemistry.training.extensions.roc_auc_evaluator.ROCAUCEvaluator(iterator, target, converter=<function concat_examples>, device=None, eval_hook=None, eval_func=None, name=None, pos_labels=1, ignore_labels=None, raise_value_error=True, logger=None)[source]

Evaluator which calculates ROC AUC score

Note that this Evaluator is only applicable to binary classification task.

Parameters:
  • iterator – Dataset iterator for the dataset to calculate ROC AUC score. It can also be a dictionary of iterators. If this is just an iterator, the iterator is registered by the name 'main'.
  • target – Link object or a dictionary of links to evaluate. If this is just a link object, the link is registered by the name 'main'.
  • converter – Converter function to build input arrays and true label. concat_examples() is used by default. It is expected to return input arrays of the form [x_0, …, x_n, t], where x_0, …, x_n are the inputs to the evaluation function and t is the true label.
  • device – Device to which the training data is sent. Negative value indicates the host memory (CPU).
  • eval_hook – Function to prepare for each evaluation process. It is called at the beginning of the evaluation. The evaluator extension object is passed at each call.
  • eval_func – Evaluation function called at each iteration. The target link to evaluate as a callable is used by default.
  • name (str) – name of this extension. When name is None, default_name=’validation’ which is defined in super class Evaluator is used as extension name. This name affects to the reported key name.
  • pos_labels (int or list) – labels of the positive class, other classes are considered as negative.
  • ignore_labels (int or list or None) – labels to be ignored. None is used to not ignore all labels.
  • raise_value_error (bool) – If False, ValueError caused by roc_auc_score calculation is suppressed and ignored with a warning message.
  • logger
converter

Converter function.

device

Device to which the training data is sent.

eval_hook

Function to prepare for each evaluation process.

eval_func

Evaluation function called at each iteration.

pos_labels

labels of the positive class

Type:list
ignore_labels

labels to be ignored.

Type:list
__init__(iterator, target, converter=<function concat_examples>, device=None, eval_hook=None, eval_func=None, name=None, pos_labels=1, ignore_labels=None, raise_value_error=True, logger=None)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(iterator, target[, converter, …]) Initialize self.
evaluate() Evaluates the model and returns a result dictionary.
finalize() Finalizes the evaluator object.
get_all_iterators() Returns a dictionary of all iterators.
get_all_targets() Returns a dictionary of all target links.
get_iterator(name) Returns the iterator of the given name.
get_target(name) Returns the target link of the given name.
initialize(trainer) Initializes up the trainer state.
roc_auc_score(y_total, t_total)
serialize(serializer) Serializes the extension state.

Attributes

default_name
name
priority
trigger