Bio.MarkovModel

Module MarkovModel

This is an implementation of a state-emitting MarkovModel. I am using terminology similar to Manning and Schutze. Functions: train_bw Train a markov model using the Baum-Welch algorithm. train_visible Train a visible markov model using MLE. find_states Find the a state sequence that explains some observations. load Load a MarkovModel. save Save a MarkovModel. Classes: MarkovModel Holds the description of a markov model

Functions

[hide private]

logaddexp(logx, logy)

source code

itemindex(values)

source code

_readline_and_check_start(handle, start)

source code

MarkovModel()

load(handle)

source code

save(mm, handle)

source code

train_bw(states, alphabet, training_data, pseudo_initial=None, pseudo_transition=None, pseudo_emission=None, update_fn=None)
train_bw(states, alphabet, training_data[, pseudo_initial] [, pseudo_transition][, pseudo_emission][, update_fn]) -> MarkovModel

source code

_baum_welch(N, M, training_outputs, p_initial=None, p_transition=None, p_emission=None, pseudo_initial=None, pseudo_transition=None, pseudo_emission=None, update_fn=None)

source code

_baum_welch_one(N, M, outputs, lp_initial, lp_transition, lp_emission, lpseudo_initial, lpseudo_transition, lpseudo_emission)

source code

_forward(N, T, lp_initial, lp_transition, lp_emission, outputs)

source code

_backward(N, T, lp_transition, lp_emission, outputs)

source code

train_visible(states, alphabet, training_data, pseudo_initial=None, pseudo_transition=None, pseudo_emission=None)
train_visible(states, alphabet, training_data[, pseudo_initial] [, pseudo_transition][, pseudo_emission]) -> MarkovModel

source code

_mle(N, M, training_outputs, training_states, pseudo_initial, pseudo_transition, pseudo_emission)

source code

_argmaxes(vector, allowance=None)

source code

list of (states, score)

find_states(markov_model, output)

source code

_viterbi(N, lp_initial, lp_transition, lp_emission, output)

source code

_normalize(matrix)

source code

_uniform_norm(shape)

source code

_random_norm(shape)

source code

_copy_and_check(matrix, desired_shape)

source code

_logsum(matrix)

source code

_logvecadd(logvec1, logvec2)

source code

_exp_logsum(numbers)

source code

Variables

[hide private]

VERY_SMALL_NUMBER = 1e-300

LOG0 = -690.77552789821368

MAX_ITERATIONS = 1000

__warningregistry__ = {('For optimal speed, please update to N...

Function Details

[hide private]

train_bw(states, alphabet, training_data, pseudo_initial=None, pseudo_transition=None, pseudo_emission=None, update_fn=None)

source code

train_bw(states, alphabet, training_data[, pseudo_initial]
[, pseudo_transition][, pseudo_emission][, update_fn]) -> MarkovModel

Train a MarkovModel using the Baum-Welch algorithm.  states is a list
of strings that describe the names of each state.  alphabet is a
list of objects that indicate the allowed outputs.  training_data
is a list of observations.  Each observation is a list of objects
from the alphabet.

pseudo_initial, pseudo_transition, and pseudo_emission are
optional parameters that you can use to assign pseudo-counts to
different matrices.  They should be matrices of the appropriate
size that contain numbers to add to each parameter matrix, before
normalization.

update_fn is an optional callback that takes parameters
(iteration, log_likelihood).  It is called once per iteration.

train_visible(states, alphabet, training_data, pseudo_initial=None, pseudo_transition=None, pseudo_emission=None)

source code

train_visible(states, alphabet, training_data[, pseudo_initial]
[, pseudo_transition][, pseudo_emission]) -> MarkovModel

Train a visible MarkovModel using maximum likelihoood estimates
for each of the parameters.  states is a list of strings that
describe the names of each state.  alphabet is a list of objects
that indicate the allowed outputs.  training_data is a list of
(outputs, observed states) where outputs is a list of the emission
from the alphabet, and observed states is a list of states from
states.

pseudo_initial, pseudo_transition, and pseudo_emission are
optional parameters that you can use to assign pseudo-counts to
different matrices.  They should be matrices of the appropriate
size that contain numbers to add to each parameter matrix

Variables Details

[hide private]

warningregistry

Value:

{('For optimal speed, please update to Numpy version 1.3 or later (cur
rent version is 1.2.0)',
  <type 'exceptions.UserWarning'>,
  29): 1}