GitLab Repo

amachine.am_fast._am_fast

HMM utilities (nanobind)

class ComplexityMeasures:
E: float

(self) -> float

T: float

(self) -> float

S: float

(self) -> float

E_L: Annotated[numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float64]], {'shape': 1, 'order': 'C'}]

(self) -> numpy.ndarray[dtype=float64, shape=(1), order='C']

T_L: Annotated[numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float64]], {'shape': 1, 'order': 'C'}]

(self) -> numpy.ndarray[dtype=float64, shape=(1), order='C']

S_L: Annotated[numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float64]], {'shape': 1, 'order': 'C'}]

(self) -> numpy.ndarray[dtype=float64, shape=(1), order='C']

H_L: Annotated[numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float64]], {'shape': 1, 'order': 'C'}]

(self) -> numpy.ndarray[dtype=float64, shape=(1), order='C']

h_mu_L: Annotated[numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float64]], {'shape': 1, 'order': 'C'}]

(self) -> numpy.ndarray[dtype=float64, shape=(1), order='C']

H_sync: Annotated[numpy.ndarray[tuple[Any, ...], numpy.dtype[numpy.float64]], {'shape': 1, 'order': 'C'}]

(self) -> numpy.ndarray[dtype=float64, shape=(1), order='C']

converged: bool

(self) -> bool

block_entropy_convergence_cpp = <nanobind.nb_func object>
generate_cpp = <nanobind.nb_func object>
strongly_connected_components_cpp = <nanobind.nb_func object>
class MinifyResult:
is_empty_language: bool

True if the minimised DFA accepts no strings.

n_classes: int

Number of equivalence classes (= states in the minimised DFA).

new_initial: int

Class id of the initial state.

eq_class: list[int]

eq_class[old_idx] = new class id, or -1 for trap-equivalent states.

class_trans: list[list[tuple[int, int]]]

class_trans[class] = list of DFTransition objects.

class_is_final: list[bool]

class_is_final[class] = True if the class is an accepting state.

minify_dfa_cpp = <nanobind.nb_func object>