jono/PolySolve
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(ga, api): Implement advanced GA strategy and refactor API for v0.4.0 #16

Merged
jono merged 3 commits from v0.4.0-dev into main 2025-10-27 14:20:56 +00:00
Conversation 0 Commits 3 Files Changed 4 +16 -12
1 changed files with 16 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Showing only changes of commit 663e72eabf - Show all commits

28
src/polysolve/__init__.py
View File

@@ -310,15 +310,17 @@ class Function:
parent_pool = solutions[:data_size // 2] parent_pool = solutions[:data_size // 2]
# 2. Crossover: Breed two parents to create a child # 2. Crossover: Breed two parents to create a child
parent1_indices = np.random.randint(0, parent_pool.size, crossover_size) # Select from the full list (indices 0 to data_size-1)
parent2_indices = np.random.randint(0, parent_pool.size, crossover_size) parent1_indices = np.random.randint(0, data_size, crossover_size)
parents1 = parent_pool[parent1_indices] parent2_indices = np.random.randint(0, data_size, crossover_size)
parents2 = parent_pool[parent2_indices] parents1 = solutions[parent1_indices]
parents2 = solutions[parent2_indices]
# Simple "average" crossover # Simple "average" crossover
crossover_solutions = (parents1 + parents2) / 2.0 crossover_solutions = (parents1 + parents2) / 2.0
# 3. Mutation: Apply your original mutation logic # 3. Mutation:
mutation_candidates = parent_pool[np.random.randint(0, parent_pool.size, mutation_size)] # Select from the full list (indices 0 to data_size-1)
mutation_candidates = solutions[np.random.randint(0, data_size, mutation_size)]
# Use mutation_strength (the new name) # Use mutation_strength (the new name)
mutation_factors = np.random.uniform( mutation_factors = np.random.uniform(
@@ -400,15 +402,17 @@ class Function:
parent_pool_size = d_parent_pool.size parent_pool_size = d_parent_pool.size
# 2. Crossover # 2. Crossover
parent1_indices = cupy.random.randint(0, parent_pool_size, crossover_size) # Select from the full list (indices 0 to data_size-1)
parent2_indices = cupy.random.randint(0, parent_pool_size, crossover_size) parent1_indices = cupy.random.randint(0, data_size, crossover_size)
d_parents1 = d_parent_pool[parent1_indices] parent2_indices = cupy.random.randint(0, data_size, crossover_size)
d_parents2 = d_parent_pool[parent2_indices] d_parents1 = d_solutions[parent1_indices]
d_parents2 = d_solutions[parent2_indices]
d_crossover_solutions = (d_parents1 + d_parents2) / 2.0 d_crossover_solutions = (d_parents1 + d_parents2) / 2.0
# 3. Mutation # 3. Mutation
mutation_indices = cupy.random.randint(0, parent_pool_size, mutation_size) # Select from the full list (indices 0 to data_size-1)
d_mutation_candidates = d_parent_pool[mutation_indices] mutation_indices = cupy.random.randint(0, data_size, mutation_size)
d_mutation_candidates = d_solutions[mutation_indices]
# Use mutation_strength (the new name) # Use mutation_strength (the new name)
d_mutation_factors = cupy.random.uniform( d_mutation_factors = cupy.random.uniform(