HiddenMarkovModel#
- class pyopenms.HiddenMarkovModel#
Bases:
object
Cython implementation of _HiddenMarkovModel
Original C++ documentation is available here
- __init__()#
Overload:
- __init__(self) → None
Hidden Markov Model implementation of PILIS
Overload:
- __init__(self, in_0: HiddenMarkovModel) → None
Methods
Overload:
Overload:
addSynonymTransition
(self, name1, name2, ...)Add a new synonym transition to the given state names
clear
(self)Clears all data
Clears the initial probabilities
Clear the emission probabilities
disableTransition
(self, s1, s2)Disables the transition; deletes the nodes from the predecessor/successor list respectively
disableTransitions
(self)Disables all transitions
dump
(self)Writes some stats to cerr
enableTransition
(self, s1, s2)Enables a transition; adds s1 to the predecessor list of s2 and s2 to the successor list of s1
Estimates the transition probabilities of not trained transitions by averages similar trained ones
evaluate
(self)Evaluate the HMM, estimates the transition probabilities from the training
forwardDump
(self)Writes some info of the forward "matrix" to cerr
getNumberOfStates
(self)Returns the number of states
getPseudoCounts
(self)Returns the pseudo counts
getState
(self, name)Returns the state with the given name
getTransitionProbability
(self, s1, s2)Returns the transition probability of the given state names
setInitialTransitionProbability
(self, state, ...)Sets the initial transition probability of the given state to prob
setPseudoCounts
(self, pseudo_counts)Sets the pseudo count that are added instead of zero
setTrainingEmissionProbability
(self, state, prob)Sets the emission probability of the given state to prob
setTransitionProbability
(self, s1, s2, prob)Sets the transition probability of the given state names to prob
setVariableModifications
(self, modifications)train
(self)Trains the HMM.
writeGraphMLFile
(self, filename)Writes the HMM into a file in GraphML format
- addNewState()#
Overload:
- addNewState(self, state: HMMState) → None
Registers a new state to the HMM
Overload:
- addNewState(self, name: bytes | str | String) → None
Registers a new state to the HMM
- addSynonymTransition(self, name1: bytes | str | String, name2: bytes | str | String, synonym1: bytes | str | String, synonym2: bytes | str | String) → None#
Add a new synonym transition to the given state names
- clear(self) → None#
Clears all data
- clearInitialTransitionProbabilities(self) → None#
Clears the initial probabilities
- clearTrainingEmissionProbabilities(self) → None#
Clear the emission probabilities
- disableTransition(self, s1: bytes | str | String, s2: bytes | str | String) → None#
Disables the transition; deletes the nodes from the predecessor/successor list respectively
- disableTransitions(self) → None#
Disables all transitions
- dump(self) → None#
Writes some stats to cerr
- enableTransition(self, s1: bytes | str | String, s2: bytes | str | String) → None#
Enables a transition; adds s1 to the predecessor list of s2 and s2 to the successor list of s1
- estimateUntrainedTransitions(self) → None#
Estimates the transition probabilities of not trained transitions by averages similar trained ones
- evaluate(self) → None#
Evaluate the HMM, estimates the transition probabilities from the training
- forwardDump(self) → None#
Writes some info of the forward “matrix” to cerr
- getNumberOfStates(self) → int#
Returns the number of states
- getPseudoCounts(self) → float#
Returns the pseudo counts
- getTransitionProbability(self, s1: bytes | str | String, s2: bytes | str | String) → float#
Returns the transition probability of the given state names
- setInitialTransitionProbability(self, state: bytes | str | String, prob: float) → None#
Sets the initial transition probability of the given state to prob
- setPseudoCounts(self, pseudo_counts: float) → None#
Sets the pseudo count that are added instead of zero
- setTrainingEmissionProbability(self, state: bytes | str | String, prob: float) → None#
Sets the emission probability of the given state to prob
- setTransitionProbability(self, s1: bytes | str | String, s2: bytes | str | String, prob: float) → None#
Sets the transition probability of the given state names to prob
- setVariableModifications(self, modifications: List[bytes]) → None#
- train(self) → None#
Trains the HMM. Initial probabilities and emission probabilities of the emitting states should be set