:py:mod:`rofunc.learning.ml.hmm`
================================

.. py:module:: rofunc.learning.ml.hmm

.. autodoc2-docstring:: rofunc.learning.ml.hmm
   :allowtitles:

Module Contents
---------------

Classes
~~~~~~~

.. list-table::
   :class: autosummary longtable
   :align: left

   * - :py:obj:`HMM <rofunc.learning.ml.hmm.HMM>`
     -

API
~~~

.. py:class:: HMM(nb_states, nb_dim=2)
   :canonical: rofunc.learning.ml.hmm.HMM

   Bases: :py:obj:`rofunc.learning.ml.gmm.GMM`

   .. py:property:: init_priors
      :canonical: rofunc.learning.ml.hmm.HMM.init_priors

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.init_priors

   .. py:property:: trans
      :canonical: rofunc.learning.ml.hmm.HMM.trans

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.trans

   .. py:property:: Trans
      :canonical: rofunc.learning.ml.hmm.HMM.Trans

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.Trans

   .. py:method:: make_finish_state(demos, dep_mask=None)
      :canonical: rofunc.learning.ml.hmm.HMM.make_finish_state

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.make_finish_state

   .. py:method:: viterbi(demo, reg=True)
      :canonical: rofunc.learning.ml.hmm.HMM.viterbi

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.viterbi

   .. py:method:: split_kbins(demos)
      :canonical: rofunc.learning.ml.hmm.HMM.split_kbins

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.split_kbins

   .. py:method:: obs_likelihood(demo=None, dep=None, marginal=None, sample_size=200, demo_idx=None)
      :canonical: rofunc.learning.ml.hmm.HMM.obs_likelihood

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.obs_likelihood

   .. py:method:: online_forward_message(x, marginal=None, reset=False)
      :canonical: rofunc.learning.ml.hmm.HMM.online_forward_message

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.online_forward_message

   .. py:method:: compute_messages(demo=None, dep=None, table=None, marginal=None, sample_size=200, demo_idx=None)
      :canonical: rofunc.learning.ml.hmm.HMM.compute_messages

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.compute_messages

   .. py:method:: init_params_random(data, left_to_right=False, self_trans=0.9)
      :canonical: rofunc.learning.ml.hmm.HMM.init_params_random

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.init_params_random

   .. py:method:: gmm_init(data, **kwargs)
      :canonical: rofunc.learning.ml.hmm.HMM.gmm_init

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.gmm_init

   .. py:method:: init_loop(demos)
      :canonical: rofunc.learning.ml.hmm.HMM.init_loop

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.init_loop

   .. py:method:: em(demos, dep=None, reg=1e-08, table=None, end_cov=False, cov_type='full', dep_mask=None, reg_finish=None, left_to_right=False, nb_max_steps=40, loop=False, obs_fixed=False, trans_reg=None)
      :canonical: rofunc.learning.ml.hmm.HMM.em

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.em

   .. py:method:: score(demos)
      :canonical: rofunc.learning.ml.hmm.HMM.score

      .. autodoc2-docstring:: rofunc.learning.ml.hmm.HMM.score

   .. py:method:: condition(data_in, dim_in, dim_out, h=None, return_gmm=False)
      :canonical: rofunc.learning.ml.hmm.HMM.condition