.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "tutorials/2_convert.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

    .. note::
        :class: sphx-glr-download-link-note

        :ref:`Go to the end <sphx_glr_download_tutorials_2_convert.py>`
        to download the full example code.

.. rst-class:: sphx-glr-example-title

.. _sphx_glr_tutorials_2_convert.py:


Score Conversion
================

Currently, the majority of outlier detectors are on node level. However,
in some real-world applications, we may interest in the outlier edges or
outlier graphs. In this tutorial, we introduce score converters provided
in ``pygod.utils`` module, including ``to_edge_score`` and
``to_graph_score``.

(Time estimate: 3 minutes)

.. GENERATED FROM PYTHON SOURCE LINES 15-18

Data Loading
------------
We first load the data from PyGOD with ``load_data`` function.

.. GENERATED FROM PYTHON SOURCE LINES 18-25

.. code-block:: Python



    from pygod.utils import load_data

    data = load_data('weibo')
    print(data)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    Data(x=[8405, 400], edge_index=[2, 407963], y=[8405], train_mask=[8405], test_mask=[8405], val_mask=[8405])




.. GENERATED FROM PYTHON SOURCE LINES 26-31

Detector Training
-----------------
Initialize and train a detector in PyGOD. Here, we use
``pygod.detector.DOMINANT`` as an example. For faster demonstration,
we set ``epoch`` to 3.

.. GENERATED FROM PYTHON SOURCE LINES 31-38

.. code-block:: Python



    from pygod.detector import DOMINANT

    detector = DOMINANT(epoch=3)
    detector.fit(data)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none


    DOMINANT(act=<function relu at 0x7f605a972200>,
             backbone=<class 'torch_geometric.nn.models.basic_gnn.GCN'>,
             batch_size=8405, compile_model=False, contamination=0.1,
             dropout=0.0, epoch=3, gpu=None, hid_dim=64, lr=0.004,
             num_layers=4, num_neigh=[-1, -1, -1, -1], save_emb=False,
             sigmoid_s=False, verbose=0, weight=0.5, weight_decay=0.0)



.. GENERATED FROM PYTHON SOURCE LINES 39-43

Obtaining Node Score
--------------------
After training, we obtain raw outlier scores for each node with
``predict``. The shape of ``node_score`` is ``(N, )``.

.. GENERATED FROM PYTHON SOURCE LINES 43-48

.. code-block:: Python



    node_score = detector.predict(data, return_pred=False, return_score=True)
    print(node_score.shape)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    torch.Size([8405])




.. GENERATED FROM PYTHON SOURCE LINES 49-53

Converting Score to Edge Level
------------------------------
To detect outlier edges, we convert the outlier scores on node level
to edge level. The shape of ``edge_score`` is ``(E, )``.

.. GENERATED FROM PYTHON SOURCE LINES 53-60

.. code-block:: Python



    from pygod.utils import to_edge_score

    edge_score = to_edge_score(node_score, data.edge_index)
    print(edge_score.shape)





.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    torch.Size([407963])




.. GENERATED FROM PYTHON SOURCE LINES 61-66

Converting Score to Graph Level
-------------------------------
To detect outlier graphs, we convert the outlier scores on node level
to graph level for each graph. ``graph_score`` is a scalar for each
``Data`` object. Here, we give an example for scoring a list of graph.

.. GENERATED FROM PYTHON SOURCE LINES 66-78

.. code-block:: Python



    from pygod.utils import to_graph_score

    data_list = [data, data, data]
    graph_scores = []
    for data in data_list:
        node_score = detector.predict(data, return_pred=False, return_score=True)
        graph_score = to_graph_score(node_score)
        graph_scores.append(graph_score.item())

    print(graph_scores)




.. rst-class:: sphx-glr-script-out

 .. code-block:: none

    [17773.826171875, 17773.826171875, 17773.826171875]





.. rst-class:: sphx-glr-timing

   **Total running time of the script:** (0 minutes 19.528 seconds)


.. _sphx_glr_download_tutorials_2_convert.py:

.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-example

    .. container:: sphx-glr-download sphx-glr-download-jupyter

      :download:`Download Jupyter notebook: 2_convert.ipynb <2_convert.ipynb>`

    .. container:: sphx-glr-download sphx-glr-download-python

      :download:`Download Python source code: 2_convert.py <2_convert.py>`

    .. container:: sphx-glr-download sphx-glr-download-zip

      :download:`Download zipped: 2_convert.zip <2_convert.zip>`


.. only:: html

 .. rst-class:: sphx-glr-signature

    `Gallery generated by Sphinx-Gallery <https://sphinx-gallery.github.io>`_