GitHub

MultitargetSRTestRegressor

MultitargetSRTestRegressor

A model type for constructing a Multi-Target Symbolic Regression via Evolutionary Search, based on SymbolicRegression.jl, and implementing the MLJ model interface.

From MLJ, the type can be imported using

MultitargetSRTestRegressor = @load MultitargetSRTestRegressor pkg=SymbolicRegression

Do model = MultitargetSRTestRegressor() to construct an instance with default hyper-parameters. Provide keyword arguments to override hyper-parameter defaults, as in MultitargetSRTestRegressor(defaults=...).

Hyper-parameters

  • defaults = nothing
  • binary_operators = nothing
  • unary_operators = nothing
  • maxsize = nothing
  • maxdepth = nothing
  • expression_spec = nothing
  • populations = nothing
  • population_size = nothing
  • ncycles_per_iteration = nothing
  • elementwise_loss = nothing
  • loss_function = nothing
  • loss_function_expression = nothing
  • dimensional_constraint_penalty = nothing
  • parsimony = nothing
  • constraints = nothing
  • nested_constraints = nothing
  • complexity_of_operators = nothing
  • complexity_of_constants = nothing
  • complexity_of_variables = nothing
  • warmup_maxsize_by = nothing
  • adaptive_parsimony_scaling = nothing
  • mutation_weights = nothing
  • crossover_probability = nothing
  • annealing = nothing
  • alpha = nothing
  • tournament_selection_n = nothing
  • tournament_selection_p = nothing
  • early_stop_condition = nothing
  • batching = nothing
  • batch_size = nothing
  • dimensionless_constants_only = false
  • complexity_mapping = nothing
  • use_frequency = true
  • use_frequency_in_tournament = true
  • should_simplify = nothing
  • perturbation_factor = nothing
  • probability_negate_constant = nothing
  • skip_mutation_failures = true
  • `optimizer_algorithm = Optim.BFGS{LineSearches.InitialStatic{Float64}, LineSearches.BackTracking{Float64, Int64}, Nothing, Nothing, Optim.Flat}(LineSearches.InitialStatic{Float64} alpha: Float64 1.0 scaled: Bool false

, LineSearches.BackTracking{Float64, Int64} c1: Float64 0.0001 ρhi: Float64 0.5 ρ_lo: Float64 0.1 iterations: Int64 1000 order: Int64 3 maxstep: Float64 Inf cache: Nothing nothing , nothing, nothing, Optim.Flat())`

  • optimizer_nrestarts = 2
  • optimizer_probability = 0.14
  • optimizer_iterations = nothing
  • optimizer_f_calls_limit = nothing
  • optimizer_options = nothing
  • should_optimize_constants = true
  • migration = true
  • hof_migration = true
  • fraction_replaced = nothing
  • fraction_replaced_hof = nothing
  • topn = nothing
  • timeout_in_seconds = nothing
  • max_evals = nothing
  • input_stream = Base.TTY(RawFD(9) paused, 0 bytes waiting)
  • turbo = false
  • bumper = false
  • autodiff_backend = nothing
  • deterministic = false
  • seed = nothing
  • verbosity = nothing
  • print_precision = 5
  • progress = nothing
  • output_directory = nothing
  • save_to_file = true
  • bin_constraints = nothing
  • una_constraints = nothing
  • terminal_width = nothing
  • use_recorder = false
  • recorder_file = pysr_recorder.json
  • define_helper_functions = true
  • expression_type = nothing
  • expression_options = nothing
  • node_type = nothing
  • output_file = nothing
  • fast_cycle = false
  • npopulations = nothing
  • npop = nothing
  • niterations = 1
  • parallelism = multithreading
  • numprocs = nothing
  • procs = nothing
  • addprocs_function = nothing
  • heap_size_hint_in_bytes = nothing
  • worker_imports = nothing
  • logger = nothing
  • runtests = true
  • run_id = nothing
  • loss_type = Nothing
  • selection_method = choose_best
  • dimensions_type = DynamicQuantities.SymbolicDimensions{DynamicQuantities.FixedRational{Int32, 25200}}