GENETIC MUTATOR¶
Runs a genetic-algorithm mutation loop over a dataset to find input configurations that minimize or maximize a target objective. Given a population of candidate designs, it iterates through mutation steps and returns both the evolved population and the best-found optimum point(s).
When to use¶
Tagged: doe, evolutionary, genetic, genetic algorithm, genetic mutator, mutation, mutator, optimization.
Inputs¶
| Label | ID | Type | Default | Required | Description |
|---|---|---|---|---|---|
| Dataset | dataset | dataset | — | Input dataset containing the design space; each row is a candidate design point (tabular format, columns must include the chosen independent and target variables). | |
| Independents | independents | select | — | ✓ | Column name(s) from the dataset representing the independent/input variables (design parameters) to be mutated by the genetic algorithm. |
| Targets | targets | select | — | ✓ | Column name(s) from the dataset representing the target/response variable(s) that the objective function will minimize or maximize. |
| Objective | objective | select | min | ✓ | Optimization direction: ‘min’ to minimize the target or ‘max’ to maximize it; defaults to ‘min’. |
| Population Size | population_size | text | 30 | ✓ | Number of candidate individuals maintained in the population at each generation; larger values improve coverage but increase compute cost (default: 30). |
| Number Of Iterations | num_iterations | text | 100 | ✓ | Total number of mutation/generation cycles the algorithm will execute before stopping; increase for more thorough search (default: 100). |
| Mutation Probability | mut_prob | text | 0.2 | ✓ | Per-gene mutation probability in the range [0, 1]; controls how often individual design parameters are randomly perturbed each generation (default: 0.2). |
| NOPTR | num_points_to_return | text | 1 | ✓ | Number of top-ranked (optimum) design points to return in the output optimum dataset; set to 1 to return only the single best solution (default: 1). |
Outputs¶
| Label | ID | Type | Description |
|---|---|---|---|
| Input Dataset | new_population | dataset | Dataset containing the full final-generation population of candidate design points after all mutation iterations, preserving independent variable columns. |
| Optimum | optimum | dataset | Dataset containing the top N best-performing design points (N = num_points_to_return) ranked by the chosen objective, with their independent variable values and predicted target responses. |
Disciplines¶
- ai_ml.preprocessing
- design_exploration.doe
- design_exploration.optimization
Auto-generated from platform schema. Worker id: genetic_mutator. Schema hash: ad8fa705888b. Hand-curated docs in workerexamples/ override this page when present.