Configuration

The following are configuration options for various Sequentia classes and functions.

API Reference

CovarianceMode	Covariance matrix types for GaussianMixtureHMM.
PriorMode	Prior probability types for HMMClassifier.
TopologyMode	Topology types for Hidden Markov Models.
TransitionMode	Initial state and transition probability types for Hidden Markov Models.

Configuration values for Sequentia classes and functions.

enum sequentia.enums.CovarianceMode(value)

Covariance matrix types for GaussianMixtureHMM.

Member Type:

str

Valid values are as follows:

FULL = <CovarianceMode.FULL: 'full'>

All values are fully learnable independently for each component.

DIAGONAL = <CovarianceMode.DIAGONAL: 'diag'>

Only values along the diagonal may be learned independently for each component.

SPHERICAL = <CovarianceMode.SPHERICAL: 'spherical'>

Same as DIAGONAL, with a single value shared along the diagonal for each component.

TIED = <CovarianceMode.TIED: 'tied'>

Same as FULL, with all components sharing the same single covariance matrix.

enum sequentia.enums.PriorMode(value)

Prior probability types for HMMClassifier.

Member Type:

str

Valid values are as follows:

UNIFORM = <PriorMode.UNIFORM: 'uniform'>

Equal probability for each class.

FREQUENCY = <PriorMode.FREQUENCY: 'frequency'>

Inverse count of the occurrences of the class in the training data.

enum sequentia.enums.TopologyMode(value)

Topology types for Hidden Markov Models.

Member Type:

str

Valid values are as follows:

ERGODIC = <TopologyMode.ERGODIC: 'ergodic'>

All states have a non-zero probability of transitioning to any state.

LEFT_RIGHT = <TopologyMode.LEFT_RIGHT: 'left-right'>

States are arranged in a way such that any state may only transition to itself or any state ahead of it, but not to any previous state.

LINEAR = <TopologyMode.LINEAR: 'linear'>

Same as LEFT_RIGHT, but states are only permitted to transition to the next state.

enum sequentia.enums.TransitionMode(value)

Initial state and transition probability types for Hidden Markov Models.

Member Type:

str

Valid values are as follows:

UNIFORM = <TransitionMode.UNIFORM: 'uniform'>

Equal probability of starting in or transitioning to each state according to the topology.

RANDOM = <TransitionMode.RANDOM: 'random'>

Random probability of starting in or transitioning to each state according to the topology. State probabilities are sampled from a Dirichlet distribution with unit concentration parameters.