:orphan:

.. _examples_index:

Example Gallery
===============




.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    </div>


Asterisk toy dataset
--------------------
Training mixture models and DP mixture models on well-separated 2D Gaussian blobs.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to initialize Gaussian observation models.">

.. only:: html

  .. image:: /examples/01_asterisk_K8/images/thumb/sphx_glr_plot-01-demo=init_methods-model=mix+gauss_thumb.png
    :alt: Initialization for Mixtures of Gaussians

  :ref:`sphx_glr_examples_01_asterisk_K8_plot-01-demo=init_methods-model=mix+gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Initialization for Mixtures of Gaussians</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to do Variational Bayes (VB) coordinate descent for GMM.">

.. only:: html

  .. image:: /examples/01_asterisk_K8/images/thumb/sphx_glr_plot-02-demo=vb_single_run-model=dp_mix+gauss_thumb.png
    :alt: Variational coordinate descent for Mixture of Gaussians

  :ref:`sphx_glr_examples_01_asterisk_K8_plot-02-demo=vb_single_run-model=dp_mix+gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Variational coordinate descent for Mixture of Gaussians</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to train a DP mixture model.">

.. only:: html

  .. image:: /examples/01_asterisk_K8/images/thumb/sphx_glr_plot-03-demo=vb+proposals-model=dp_mix+gauss_thumb.png
    :alt: Variational with birth and merge proposals for DP mixtures of Gaussians

  :ref:`sphx_glr_examples_01_asterisk_K8_plot-03-demo=vb+proposals-model=dp_mix+gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Variational with birth and merge proposals for DP mixtures of Gaussians</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Here, we show how to &quot;warm start&quot; from an existing model.">

.. only:: html

  .. image:: /examples/01_asterisk_K8/images/thumb/sphx_glr_plot-04-demo=vb_warm_start_from_existing_model-model=dp_mix+gauss_thumb.png
    :alt: Warm Starting from a Previously Trained Mixture of Gaussians

  :ref:`sphx_glr_examples_01_asterisk_K8_plot-04-demo=vb_warm_start_from_existing_model-model=dp_mix+gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Warm Starting from a Previously Trained Mixture of Gaussians</div>
    </div>


.. raw:: html

    </div>


Standard Normal dataset
-----------------------

Variational training of DP mixture models on thousands of points from a single 1D Gaussian with mean 0 and variance 1. 



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How delete moves can be more effective than merges.">

.. only:: html

  .. image:: /examples/02_stdnormal_K1/images/thumb/sphx_glr_plot-01-demo=deletes-model=dp_mix+gauss_thumb.png
    :alt: Variational with merge and delete proposals for DP mixtures of Gaussians

  :ref:`sphx_glr_examples_02_stdnormal_K1_plot-01-demo=deletes-model=dp_mix+gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Variational with merge and delete proposals for DP mixtures of Gaussians</div>
    </div>


.. raw:: html

    </div>


Old faithful dataset
-----------------------

Variational training of DP mixture models on classic dataset on eruption times from Old Faithful geyser in Yellowstone National Park.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Showcase of different models and algorithms applied to same dataset.">

.. only:: html

  .. image:: /examples/03_faithful/images/thumb/sphx_glr_plot-01-demo=vb_algs-model=mix_gauss_thumb.png
    :alt: Variational training for Mixtures of Gaussians

  :ref:`sphx_glr_examples_03_faithful_plot-01-demo=vb_algs-model=mix_gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Variational training for Mixtures of Gaussians</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How delete moves can be more effective than merges.">

.. only:: html

  .. image:: /examples/03_faithful/images/thumb/sphx_glr_plot-02-demo=merge_and_delete-model=dp_mix+gauss_thumb.png
    :alt: Variational with merge and delete proposals for DP mixtures of Gaussians

  :ref:`sphx_glr_examples_03_faithful_plot-02-demo=merge_and_delete-model=dp_mix+gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Variational with merge and delete proposals for DP mixtures of Gaussians</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="This demo illustrates &quot;sparse responsibilities&quot; for mixture models.">

.. only:: html

  .. image:: /examples/03_faithful/images/thumb/sphx_glr_plot-03-demo=sparse_resp_vb-model=mix_gauss_thumb.png
    :alt: Demonstration of Sparse Responsibilities for Mixtures of Gaussians

  :ref:`sphx_glr_examples_03_faithful_plot-03-demo=sparse_resp_vb-model=mix_gauss.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Demonstration of Sparse Responsibilities for Mixtures of Gaussians</div>
    </div>


.. raw:: html

    </div>


Toy bars dataset: one bar per doc
---------------------------------

Variational training of mixture models and topic models with Multinomial likelihoods on simple toy "bars" dataset.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to train a mixture of multinomials.">

.. only:: html

  .. image:: /examples/04_bars_one_per_doc/images/thumb/sphx_glr_plot-01-demo=vb_single_run-model=mix+mult_thumb.png
    :alt: 01: Standard variational training for mixture model

  :ref:`sphx_glr_examples_04_bars_one_per_doc_plot-01-demo=vb_single_run-model=mix+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">01: Standard variational training for mixture model</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to train a DP mixture of multinomials.">

.. only:: html

  .. image:: /examples/04_bars_one_per_doc/images/thumb/sphx_glr_plot-02-demo=vb+proposals-model=dp_mix+mult_thumb.png
    :alt: 02: Training DP mixture model with birth and merge proposals

  :ref:`sphx_glr_examples_04_bars_one_per_doc_plot-02-demo=vb+proposals-model=dp_mix+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">02: Training DP mixture model with birth and merge proposals</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="03: Standard variational training for topic model">

.. only:: html

  .. image:: /examples/04_bars_one_per_doc/images/thumb/sphx_glr_run-03-demo=topic_model_vb_single_run-model=hdp_topic+mult_thumb.png
    :alt: 03: Standard variational training for topic model

  :ref:`sphx_glr_examples_04_bars_one_per_doc_run-03-demo=topic_model_vb_single_run-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">03: Standard variational training for topic model</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="04: Training HDP Topic Model with merge proposals">

.. only:: html

  .. image:: /examples/04_bars_one_per_doc/images/thumb/sphx_glr_run-04-demo=topic_model_vb+merges-model=hdp_topic+mult_thumb.png
    :alt: 04: Training HDP Topic Model with merge proposals

  :ref:`sphx_glr_examples_04_bars_one_per_doc_run-04-demo=topic_model_vb+merges-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">04: Training HDP Topic Model with merge proposals</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="05: Training for HDP Topic Model with birth and merge proposals">

.. only:: html

  .. image:: /examples/04_bars_one_per_doc/images/thumb/sphx_glr_run-05-demo=topic_model_vb+births-model=hdp_topic+mult_thumb.png
    :alt: 05: Training for HDP Topic Model with birth and merge proposals

  :ref:`sphx_glr_examples_04_bars_one_per_doc_run-05-demo=topic_model_vb+births-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">05: Training for HDP Topic Model with birth and merge proposals</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to train a mixture of multinomials.">

.. only:: html

  .. image:: /examples/04_bars_one_per_doc/images/thumb/sphx_glr_run-06-demo=topic_model_vb-model=finite_topic+bern_thumb.png
    :alt: 01: Standard variational training for mixture model

  :ref:`sphx_glr_examples_04_bars_one_per_doc_run-06-demo=topic_model_vb-model=finite_topic+bern.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">01: Standard variational training for mixture model</div>
    </div>


.. raw:: html

    </div>


Toy bars dataset: many bars per doc
-----------------------------------

Variational training of mixture models and topic models with Multinomial likelihoods on toy "bars" dataset with multiple bars per document.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to train a mixture of multinomials.">

.. only:: html

  .. image:: /examples/05_bars_many_per_doc/images/thumb/sphx_glr_run-01-demo=vb_single_run-model=mix+mult_thumb.png
    :alt: 01: Standard variational training for mixture model

  :ref:`sphx_glr_examples_05_bars_many_per_doc_run-01-demo=vb_single_run-model=mix+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">01: Standard variational training for mixture model</div>
    </div>


.. raw:: html

    </div>


we8there bag-of-words text dataset
----------------------------------

Text from some restaurant reviews (Taddy 2012). Variational training of mixture models and topic models with Multinomial likelihoods.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="VB coordinate descent for Mixture of Multinomials">

.. only:: html

  .. image:: /examples/06_we8there/images/thumb/sphx_glr_run-01-demo=mix_vb_single_run-model=mix+mult_thumb.png
    :alt: VB coordinate descent for Mixture of Multinomials

  :ref:`sphx_glr_examples_06_we8there_run-01-demo=mix_vb_single_run-model=mix+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">VB coordinate descent for Mixture of Multinomials</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="VB coordinate descent for DP Mixture of Multinomials">

.. only:: html

  .. image:: /examples/06_we8there/images/thumb/sphx_glr_run-02-demo=mix_vb+proposals-model=dp_mix+mult_thumb.png
    :alt: VB coordinate descent for DP Mixture of Multinomials

  :ref:`sphx_glr_examples_06_we8there_run-02-demo=mix_vb+proposals-model=dp_mix+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">VB coordinate descent for DP Mixture of Multinomials</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Standard variational training for topic model">

.. only:: html

  .. image:: /examples/06_we8there/images/thumb/sphx_glr_run-03-demo=topic_vb_single_run-model=hdp_topic+mult_thumb.png
    :alt: Standard variational training for topic model

  :ref:`sphx_glr_examples_06_we8there_run-03-demo=topic_vb_single_run-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Standard variational training for topic model</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Birth and merge variational training for topic model">

.. only:: html

  .. image:: /examples/06_we8there/images/thumb/sphx_glr_run-04-demo=topic_vb+proposals-model=hdp_topic+mult_thumb.png
    :alt: Birth and merge variational training for topic model

  :ref:`sphx_glr_examples_06_we8there_run-04-demo=topic_vb+proposals-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Birth and merge variational training for topic model</div>
    </div>


.. raw:: html

    </div>


Small wikipedia bag-of-words text dataset
-----------------------------------------

Text from a few thousand wikipedia articles.
Variational training of mixture models and topic models with Multinomial likelihoods.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="In this demo, we&#x27;ll review the scalable memoized training of HDP topic models.">

.. only:: html

  .. image:: /examples/07_wiki/images/thumb/sphx_glr_plot-02-demo=scalable_topic_model-model=hdp_topic+mult_thumb.png
    :alt: Scalable training of HDP topic models

  :ref:`sphx_glr_examples_07_wiki_plot-02-demo=scalable_topic_model-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Scalable training of HDP topic models</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Birth and merge variational training for topic model">

.. only:: html

  .. image:: /examples/07_wiki/images/thumb/sphx_glr_run-01-demo=topic_vb+proposals-model=hdp_topic+mult_thumb.png
    :alt: Birth and merge variational training for topic model

  :ref:`sphx_glr_examples_07_wiki_run-01-demo=topic_vb+proposals-model=hdp_topic+mult.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Birth and merge variational training for topic model</div>
    </div>


.. raw:: html

    </div>


Small dataset of 6 motion-capture sequences
-------------------------------------------

Variational training of mixture models and HMM models with various Gaussian observation models.



.. raw:: html

    <div class="sphx-glr-thumbnails">


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to train mixtures and HMMs with various observation models on the same dataset.">

.. only:: html

  .. image:: /examples/08_mocap6/images/thumb/sphx_glr_plot-01-demo=many_models_same_data_thumb.png
    :alt: Comparing models for sequential data

  :ref:`sphx_glr_examples_08_mocap6_plot-01-demo=many_models_same_data.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Comparing models for sequential data</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="How to try merge moves efficiently for time-series datasets.">

.. only:: html

  .. image:: /examples/08_mocap6/images/thumb/sphx_glr_plot-02-demo=merge_moves_for_hdphmm_thumb.png
    :alt: Merge moves with HDP-HMM

  :ref:`sphx_glr_examples_08_mocap6_plot-02-demo=merge_moves_for_hdphmm.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Merge moves with HDP-HMM</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Train a sticky HDP-HMM model on small motion capture data, then visualize the MAP state sequenc...">

.. only:: html

  .. image:: /examples/08_mocap6/images/thumb/sphx_glr_plot-03-demo=interpret_hdphmm_params_and_run_viterbi_thumb.png
    :alt: Visualizing learned state sequences and transition probabilities

  :ref:`sphx_glr_examples_08_mocap6_plot-03-demo=interpret_hdphmm_params_and_run_viterbi.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Visualizing learned state sequences and transition probabilities</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Train a sticky HMM model with auto-regressive Gaussian likelihoods on small motion capture data...">

.. only:: html

  .. image:: /examples/08_mocap6/images/thumb/sphx_glr_plot-04-demo_ar_gaussian_prior_hypers_thumb.png
    :alt: Visualizing learned state sequences and transition probabilities

  :ref:`sphx_glr_examples_08_mocap6_plot-04-demo_ar_gaussian_prior_hypers.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Visualizing learned state sequences and transition probabilities</div>
    </div>


.. raw:: html

    <div class="sphx-glr-thumbcontainer" tooltip="Quick demonstration that you can easily use bnpy to perform mixed membership modeling of groupe...">

.. only:: html

  .. image:: /examples/08_mocap6/images/thumb/sphx_glr_plot-05-topic_model_gaussian_likelihood_thumb.png
    :alt: Topic models with Gaussian likelihoods

  :ref:`sphx_glr_examples_08_mocap6_plot-05-topic_model_gaussian_likelihood.py`

.. raw:: html

      <div class="sphx-glr-thumbnail-title">Topic models with Gaussian likelihoods</div>
    </div>


.. raw:: html

    </div>


.. toctree::
   :hidden:
   :includehidden:

   /examples//01_asterisk_K8/index.rst
   /examples//02_stdnormal_K1/index.rst
   /examples//03_faithful/index.rst
   /examples//04_bars_one_per_doc/index.rst
   /examples//05_bars_many_per_doc/index.rst
   /examples//06_we8there/index.rst
   /examples//07_wiki/index.rst
   /examples//08_mocap6/index.rst


.. only:: html

  .. container:: sphx-glr-footer sphx-glr-footer-gallery

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

      :download:`Download all examples in Python source code: examples_python.zip </examples/examples_python.zip>`

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

      :download:`Download all examples in Jupyter notebooks: examples_jupyter.zip </examples/examples_jupyter.zip>`


.. only:: html

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

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