.. DO NOT EDIT.
.. THIS FILE WAS AUTOMATICALLY GENERATED BY SPHINX-GALLERY.
.. TO MAKE CHANGES, EDIT THE SOURCE PYTHON FILE:
.. "examples/04_bars_one_per_doc/run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py"
.. LINE NUMBERS ARE GIVEN BELOW.

.. only:: html

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

        Click :ref:`here <sphx_glr_download_examples_04_bars_one_per_doc_run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py>`
        to download the full example code

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

.. _sphx_glr_examples_04_bars_one_per_doc_run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py:


=================================================
04: Training HDP Topic Model with merge proposals
=================================================

.. GENERATED FROM PYTHON SOURCE LINES 8-20

.. code-block:: default

    import bnpy
    import numpy as np
    import os
    import sys

    from matplotlib import pylab
    import seaborn as sns

    FIG_SIZE = (3, 3)
    SMALL_FIG_SIZE = (1,1)
    pylab.rcParams['figure.figsize'] = FIG_SIZE


.. GENERATED FROM PYTHON SOURCE LINES 21-22

Read dataset from file.

.. GENERATED FROM PYTHON SOURCE LINES 22-27

.. code-block:: default


    dataset_path = os.path.join(bnpy.DATASET_PATH, 'bars_one_per_doc')
    dataset = bnpy.data.BagOfWordsData.read_npz(
        os.path.join(dataset_path, 'dataset.npz'))


.. GENERATED FROM PYTHON SOURCE LINES 28-29

Set the local step algorithmic keyword args

.. GENERATED FROM PYTHON SOURCE LINES 30-46

.. code-block:: default


    local_step_kwargs = dict(
        # Perform at most this many iterations at each document
        nCoordAscentItersLP=100,
        # Stop local iters early when max change in doc-topic counts < this thr
        convThrLP=0.001,
        restartLP=0,
        doMemoizeLocalParams=0,
        )

    merge_kwargs = dict(
        m_startLap=5,
        m_pair_ranking_procedure='total_size',
        m_pair_ranking_direction='descending',
        )


.. GENERATED FROM PYTHON SOURCE LINES 47-51

Run the VB+proposals algorithm
with only merges and re-shuffling.

Initialization: 10 topics, using randomlikewang

.. GENERATED FROM PYTHON SOURCE LINES 52-65

.. code-block:: default



    trained_model, info_dict = bnpy.run(
        dataset, 'HDPTopicModel', 'Mult', 'memoVB',
        output_path=
            '/tmp/bars_one_per_doc/' + 
            'trymoves-model=hdp+mult-K=10-moves=merge,shuffle/',
        nLap=50, convergeThr=0.001, nBatch=1,
        K=10, initname='randomlikewang',
        alpha=0.5, lam=0.1,
        moves='merge,shuffle',
        **dict(list(merge_kwargs.items()) + list(local_step_kwargs.items())))


.. GENERATED FROM PYTHON SOURCE LINES 68-95

.. code-block:: default


    def show_bars_over_time(
            task_output_path=None,
            query_laps=[0, 1, 2, 5, None],
            ncols=10):
        ''' Show square-image visualization of estimated topics over time.

        Post Condition
        --------------
        New matplotlib figure with visualization (one row per lap).
        '''
        nrows = len(query_laps)
        fig_handle, ax_handles_RC = pylab.subplots(
            figsize=(SMALL_FIG_SIZE[0] * ncols, SMALL_FIG_SIZE[1] * nrows),
            nrows=nrows, ncols=ncols, sharex=True, sharey=True)
        for row_id, lap_val in enumerate(query_laps):
            cur_model, lap_val = bnpy.load_model_at_lap(task_output_path, lap_val)
            cur_topics_KV = cur_model.obsModel.getTopics()
            # Plot the current model
            cur_ax_list = ax_handles_RC[row_id].flatten().tolist()
            bnpy.viz.BarsViz.show_square_images(
                cur_topics_KV,
                vmin=0.0, vmax=0.06,
                ax_list=cur_ax_list)
            cur_ax_list[0].set_ylabel("lap: %d" % lap_val)
        pylab.tight_layout()


.. GENERATED FROM PYTHON SOURCE LINES 96-97

Examine the bars over time

.. GENERATED FROM PYTHON SOURCE LINES 98-100

.. code-block:: default

    show_bars_over_time(info_dict['task_output_path'])



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

   **Total running time of the script:** ( 0 minutes  0.000 seconds)


.. _sphx_glr_download_examples_04_bars_one_per_doc_run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py:

.. only:: html

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


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

      :download:`Download Python source code: run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py <run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py>`

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

      :download:`Download Jupyter notebook: run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.ipynb <run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.ipynb>`


.. only:: html

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

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