ml4co_kit.generator.graph.base

Base classes for all graph problem generators.

Classes

GRAPH_TYPE(value)	Define the graph types as an enumeration.
GRAPH_WEIGHT_TYPE(value)	Define the weight types as an enumeration.
GraphGeneratorBase(task_type, ...)	Base class for all graph problem generators.
GraphWeightGenerator(weighted_type, ...)

class ml4co_kit.generator.graph.base.GRAPH_TYPE(value)

Bases: str, Enum

Define the graph types as an enumeration.

BA = 'ba'

ER = 'er'

HK = 'hk'

RB = 'rb'

WS = 'ws'

class ml4co_kit.generator.graph.base.GRAPH_WEIGHT_TYPE(value)

Bases: str, Enum

Define the weight types as an enumeration.

BINORMIAL = 'binomial'

EXPONENTIAL = 'exponential'

GAUSSIAN = 'gaussian'

LOGNORMAL = 'lognormal'

POISSON = 'poisson'

POWERLAW = 'powerlaw'

UNIFORM = 'uniform'

class ml4co_kit.generator.graph.base.GraphGeneratorBase(task_type: ~ml4co_kit.task.base.TASK_TYPE, distribution_type: ~ml4co_kit.generator.graph.base.GRAPH_TYPE = GRAPH_TYPE.ER, precision: ~numpy.float32 | ~numpy.float64 = <class 'numpy.float32'>, nodes_num_scale: tuple = (200, 300), er_prob: float = 0.15, ba_conn_degree: int = 10, hk_prob: float = 0.3, hk_conn_degree: int = 10, ws_prob: float = 0.3, ws_ring_neighbors: int = 2, rb_n_scale: tuple = (20, 25), rb_k_scale: tuple = (5, 12), rb_p_scale: tuple = (0.3, 1.0), node_weighted: bool = False, node_weighted_gen: ~ml4co_kit.generator.graph.base.GraphWeightGenerator = <ml4co_kit.generator.graph.base.GraphWeightGenerator object>, edge_weighted: bool = False, edge_weighted_gen: ~ml4co_kit.generator.graph.base.GraphWeightGenerator = <ml4co_kit.generator.graph.base.GraphWeightGenerator object>)

Bases: GeneratorBase

Base class for all graph problem generators.

class ml4co_kit.generator.graph.base.GraphWeightGenerator(weighted_type: ~ml4co_kit.generator.graph.base.GRAPH_WEIGHT_TYPE, precision: ~numpy.float32 | ~numpy.float64 = <class 'numpy.float32'>, gaussian_mean: float = 0.0, gaussian_std: float = 1.0, poisson_lambda: float = 1.0, exponential_scale: float = 1.0, lognormal_mean: float = 0.0, lognormal_sigma: float = 1.0, powerlaw_a: float = 1.0, powerlaw_b: float = 10.0, powerlaw_sigma: float = 1.0, binomial_n: int = 10, binomial_p: float = 0.5)

Bases: object

binormal_gen(size: int) → ndarray

exponential_gen(size: int) → ndarray

gaussian_gen(size: int) → ndarray

generate(size: int) → ndarray

lognormal_gen(size: int) → ndarray

poisson_gen(size: int) → ndarray

powerlaw_gen(size: int) → ndarray

uniform_gen(size: int) → ndarray