saealib.CrossoverTwoPoint

class saealib.CrossoverTwoPoint(prob)

ベースクラス: Crossover

Two-point crossover operator.

パラメータ:

prob (float)

prob

Individual-level crossover probability.

Type:

float

Methods

__init__	Initialize two-point crossover operator.
contract	Return the crossover contract.
crossover	Execute crossover for one parent group.
crossover_batch	Execute two-point crossover on a batch of parent pairs at once.
post_crossover	Post-crossover lifecycle hook; override to inject custom processing.
post_crossover_batch	Run the post-crossover lifecycle hook for a batch.
with_post	Return a copy of this operator with fn appended to the hook.

Method Details

CrossoverTwoPoint.__init__(prob)

Initialize two-point crossover operator.

パラメータ:

prob (float) -- Individual-level crossover probability.

CrossoverTwoPoint.contract()

Return the crossover contract.

戻り値の型:

ComponentContract

CrossoverTwoPoint.crossover(parent, bounds=None, rng=Generator(PCG64) at 0x7FE0F4773140)

Execute crossover for one parent group.

This method is derived from crossover_batch() by passing a single-pair batch.

メモ

Overriding only this method (not crossover_batch()) has no effect under GA's default variation_execution="batch": the batch path calls crossover_batch() directly and never calls crossover(). Such an override only takes effect under variation_execution="sequential". To customize behavior under both modes, override crossover_batch().

パラメータ:

• parent (np.ndarray) -- Parent individuals. shape = (n_parents, dim)

• bounds (tuple of (np.ndarray, np.ndarray) or None) -- Lower and upper bounds for each variable. None means unbounded.

• rng (np.random.Generator, optional) -- Random number generator, by default np.random.default_rng()

戻り値:

Offspring individuals. shape = (n_offspring, dim)

戻り値の型:

np.ndarray

CrossoverTwoPoint.crossover_batch(parents_batch, bounds=None, rng=Generator(PCG64) at 0x7FE0F47A9D20)

Execute two-point crossover on a batch of parent pairs at once.

Unlike every other crossover_batch in this module, the cut-point sampling itself is not vectorized here: rng.choice(dim + 1, size=2, replace=False) draws two values without replacement from the same row's range(dim + 1) population. Calling rng.choice with a multi-row size and replace=False would instead draw that many DISTINCT values across the WHOLE output (not independently per row), which is a different -- and wrong -- sampling semantics, and there is no algebraic substitute that reproduces replace=False choice exactly. So the two cut points are still drawn with a small per-row Python loop, preserving the single-pair rng.choice semantics and RNG consumption order row by row. The vectorization benefit instead comes from reconstructing the offspring (the dim-sized part) for the whole batch at once via a broadcast mask.

パラメータ:

• parents_batch (np.ndarray) -- Batch of parent pairs. shape = (n_pair, 2, dim)

• bounds (tuple of (np.ndarray, np.ndarray) or None) -- Ignored.

• rng (np.random.Generator, optional) -- Random number generator, by default np.random.default_rng()

戻り値:

Offspring individuals. shape = (n_pair, 2, dim)

戻り値の型:

np.ndarray

メモ

Because the cut-point loop consumes rng in the same per-row order as separate single-pair crossover_batch calls (equivalently, separate crossover() calls), every row reproduces the corresponding result from that loop with an identically seeded rng.

CrossoverTwoPoint.post_crossover(offspring, parents, rng, ctx=None)

Post-crossover lifecycle hook; override to inject custom processing.

パラメータ:

• offspring (np.ndarray) -- Offspring produced by crossover. shape = (n_children, dim)

• parents (np.ndarray) -- Parent individuals. shape = (n_parents, dim)

• rng (np.random.Generator) -- Random number generator.

• ctx (ExecutionContext or None, optional) -- Current optimization context.

戻り値:

Processed offspring. shape = (n_children, dim)

戻り値の型:

np.ndarray

CrossoverTwoPoint.post_crossover_batch(offspring_batch, parents_batch, rng, ctx=None)

Run the post-crossover lifecycle hook for a batch.

The default implementation calls post_crossover() once per parent group, in order. Override this method to provide genuinely vectorized post-processing.

パラメータ:

• offspring_batch (np.ndarray) -- Offspring produced by crossover. shape = (n_pair, n_children, dim)

• parents_batch (np.ndarray) -- Batch of parent groups. shape = (n_pair, n_parents, dim)

• rng (np.random.Generator) -- Random number generator.

• ctx (ExecutionContext or None, optional) -- Current optimization context.

戻り値:

Processed offspring. shape = (n_pair, n_children, dim)

戻り値の型:

np.ndarray

メモ

with_post() reassigns only the instance's post_crossover() hook. A subclass override of this method is responsible for composing that hook itself. If the override does not call self.post_crossover, a hook installed with with_post() will not run in GA batch mode. It still runs in GA sequential mode, which calls post_crossover() directly.

CrossoverTwoPoint.with_post(fn)

Return a copy of this operator with fn appended to the hook.

パラメータ:

fn (callable) -- fn(offspring, parents, rng, ctx) -> np.ndarray

戻り値:

Shallow copy with the hook registered.

戻り値の型:

Crossover