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

.. only:: html

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

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

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

.. _sphx_glr_auto_examples_document_retrieval_example.py:


==============================================================================
Retrieval of most similar document using the Weisfeiler-Lehman subtree kernel.
==============================================================================
Script makes use of :class:`grakelx.WeisfeilerLehman`, :class:`grakelx.VertexHistogram`

.. GENERATED FROM PYTHON SOURCE LINES 7-61

.. code-block:: Python


    from __future__ import print_function

    print(__doc__)

    import time

    import numpy as np
    from nltk.corpus import sentence_polarity

    from grakelx import Graph
    from grakelx.kernels import VertexHistogram, WeisfeilerLehman

    sents = sentence_polarity.sents()
    sents = [sent for sent in sents if len(sent) > 1]
    n_sents = 3000
    sents = sents[:n_sents]
    print("Loaded %d sentences\n" % n_sents)

    print("Creating word co-occurrence networks\n")
    word_networks = list()
    for sent in sents:
        node_labels = dict()
        tokens_to_ids = dict()
        for token in sent:
            if token not in tokens_to_ids:
                tokens_to_ids[token] = len(tokens_to_ids)
                node_labels[tokens_to_ids[token]] = token

        edges = list()
        for i in range(len(sent) - 1):
            edges.append((tokens_to_ids[sent[i]], tokens_to_ids[sent[i + 1]]))

        word_networks.append(Graph(edges, node_labels=node_labels))

    query_sent_id = 54
    query_sent = [word_networks[query_sent_id]]

    # Initialize Weisfeiler-Lehman subtree kernel
    gk = WeisfeilerLehman(niter=2, normalize=True, base_graph_kernel=VertexHistogram)

    print("Computing similarities\n")
    t0 = time.time()
    gk.fit(query_sent)
    K = gk.transform(word_networks)
    print("done in %0.3fs\n" % (time.time() - t0))

    print("Query sentence")
    print("--------------")
    print(" ".join(sents[query_sent_id]))
    print()
    print("Most similar sentence")
    print("---------------------")
    print(" ".join(sents[np.argsort(K[:, 0])[-2]]))


.. _sphx_glr_download_auto_examples_document_retrieval_example.py:

.. only:: html

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

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

      :download:`Download Jupyter notebook: document_retrieval_example.ipynb <document_retrieval_example.ipynb>`

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

      :download:`Download Python source code: document_retrieval_example.py <document_retrieval_example.py>`

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

      :download:`Download zipped: document_retrieval_example.zip <document_retrieval_example.zip>`


.. only:: html

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

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