slim_gsgp.algorithms.GSGP

• slim_gsgp.algorithms.GSGP.operators
  • slim_gsgp.algorithms.GSGP.operators.crossover_operators module
    • geometric_crossover()
  • slim_gsgp.algorithms.GSGP.operators.mutators
    • product_one_trees_geometric_mutation()
    • product_two_trees_geometric_mutation()
    • standard_geometric_mutation()
    • standard_one_tree_geometric_mutation()
• slim_gsgp.algorithms.GSGP.representations
  • slim_gsgp.algorithms.GSGP.representations.population
    • Population
      • Population.calculate_semantics()
      • Population.evaluate()
  • slim_gsgp.algorithms.GSGP.representations.tree
    • Tree
      • Tree.structure
      • Tree.FUNCTIONS
      • Tree.TERMINALS
      • Tree.CONSTANTS
      • Tree.depth
      • Tree.nodes
      • Tree.train_semantics
      • Tree.test_semantics
      • Tree.fitness
      • Tree.test_fitness
      • Tree.calculate_semantics()
      • Tree.evaluate()
      • Tree.predict()
  • slim_gsgp.algorithms.GSGP.representations.tree_utils
    • apply_tree()
    • nested_depth_calculator()
    • nested_nodes_calculator()

slim_gsgp.algorithms.GSGP.gsgp

Geometric Semantic Genetic Programming (GSGP) module.

class slim_gsgp.algorithms.GSGP.gsgp.GSGP(pi_init, initializer, selector, mutator, ms, crossover, find_elit_func, p_m=0.8, p_xo=0.2, pop_size=100, seed=0, settings_dict=None)

Bases: object

Geometric Semantic Genetic Programming class.

solve(X_train, X_test, y_train, y_test, curr_dataset, n_iter=20, elitism=True, log=0, verbose=0, test_elite=False, log_path=None, run_info=None, ffunction=None, reconstruct=False, n_elites=1, n_jobs=1)

Execute the GSGP algorithm.

Parameters:

• X_train (torch.Tensor) – Training data features.

• X_test (torch.Tensor) – Test data features.

• y_train (torch.Tensor) – Training data labels.

• y_test (torch.Tensor) – Test data labels.

• curr_dataset (str) – Current dataset name.

• n_iter (int) – Number of iterations.

• elitism (bool) – Whether to use elitism.

• log (int) – Logging level. Default is 0.

• verbose (int) – Verbosity level. Default is 0.

• test_elite (bool) – Whether to evaluate elite individuals on test data. Default is False.

• log_path (str) – Path to save logs. Default is None.

• run_info (list) – Information about the current run. Default is None.

• ffunction (callable) – Fitness function. Default is None.

• reconstruct (bool) – Whether to reconstruct trees. Default is False.

• n_elites (int) – Number of elites. Default is 1.

• n_jobs (int) – The maximum number of jobs for parallel processing. Default is 1.