.. _`ROC from Probabilities`:

.. _`org.sysess.sympathy.machinelearning.roc_prob`:

ROC from Probabilities
~~~~~~~~~~~~~~~~~~~~~~

.. image:: roc_curve.svg
   :width: 48


Computes Receiver operating characteristics (ROC) based on calculated Y-probabilities and from true Y.

*Configuration*:


  - *pos_label*

    Label considered as positive and others are considered negative.


  - *drop_intermediate*

    Whether to drop some suboptimal thresholds which would not appear
    on a plotted ROC curve. This is useful in order to create lighter
    ROC curves.

    .. versionadded:: 0.17
       parameter *drop_intermediate*.


  - *header as label*

    Use header of Y-prob as the target label



*Attributes*:




*Input ports*:
    **Y-prob** : table
        Y-prob
    **Y-true** : table
        Y-true

*Output ports*:
    **roc** : table
        roc



**pos_label** (pos_label)
    Label considered as positive and others are considered negative.
**drop_intermediate** (drop_intermediate)
    Whether to drop some suboptimal thresholds which would not appear
    on a plotted ROC curve. This is useful in order to create lighter
    ROC curves.

    .. versionadded:: 0.17
       parameter *drop_intermediate*.
**header as label** (header as label)
    Use header of Y-prob as the target label

.. automodule:: node_metrics

.. class:: ROCFromProb