jMetalPy

https://jmetal.github.io/jMetalPy/
Admin
jMetalPy is a Python framework for multi-objective optimization with metaheuristics, providing...
Tokens:221,423
Snippets:1,151
Trust Score:9.7
Update:6 months ago
Show doc for...
Tokens:
Raw
### Dynamic NSGA-II Example

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/nsgaii_dynamic.html

A practical example demonstrating how to use the DynamicNSGAII algorithm with FDA2 problem, including observer setup and algorithm execution.

```python
from jmetal.algorithm.multiobjective.nsgaii import DynamicNSGAII
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem.multiobjective.fda import FDA2
from jmetal.util.observable import TimeCounter
from jmetal.util.observer import PlotFrontToFileObserver, WriteFrontToFileObserver
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = FDA2()

time_counter = TimeCounter(delay=1)
time_counter.observable.register(problem)
time_counter.start()

max_evaluations = 25000
algorithm = DynamicNSGAII(
    problem=problem,
    population_size=100,
    offspring_population_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.observable.register(observer=PlotFrontToFileObserver('front_plot'))
algorithm.observable.register(observer=WriteFrontToFileObserver('front_files'))

algorithm.run()

```

--------------------------------

### Install jMetalPy with specific options

Source: https://jmetal.github.io/jMetalPy/getting-started.html

Alternative installation commands for specific dependency sets.

```bash
$ pip install "jmetalpy[core]"        # Core components only
$ pip install "jmetalpy[docs]"        # Documentation building
$ pip install "jmetalpy[distributed]" # Parallel computing
$ pip install "jmetalpy[complete]"    # All dependencies
```

--------------------------------

### Install jMetalPy from source

Source: https://jmetal.github.io/jMetalPy/getting-started.html

Commands to clone the repository and install the package from source code.

```bash
$ git clone https://github.com/jMetal/jMetalPy.git
$ python setup.py install
```

--------------------------------

### ProgressBar Output Example

Source: https://jmetal.github.io/jMetalPy/tutorials/observer.html

Example of the console output generated by the ProgressBarObserver.

```text
$ Progress:  50%|#####     | 12500/25000 [13:59<14:12, 14.66it/s]
```

--------------------------------

### Quick Example of NSGA-II Algorithm

Source: https://jmetal.github.io/jMetalPy/index.html

This snippet demonstrates how to initialize and run the NSGA-II algorithm with the ZDT1 problem. Ensure jmetalpy is installed and necessary imports are available.

```python
from jmetal.algorithm.multiobjective.nsgaii import NSGAII
from jmetal.problem import ZDT1

problem = ZDT1()
algorithm = NSGAII(problem=problem, population_size=100)
algorithm.run()
solutions = algorithm.get_result()
```

--------------------------------

### OMOPSO Usage Example

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/psos/omopso.html

Example demonstrating how to use the OMOPSO algorithm with ZDT1 problem.

```APIDOC
## Example Usage of OMOPSO

This example shows how to instantiate and run the OMOPSO algorithm for the ZDT1 problem.

### Setup
```python
from jmetal.algorithm.multiobjective.omopso import OMOPSO
from jmetal.operator.mutation import UniformMutation
from jmetal.operator.mutation import NonUniformMutation
from jmetal.problem import ZDT1
from jmetal.util.archive import CrowdingDistanceArchive
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT1()

mutation_probability = 1.0 / problem.number_of_variables
max_evaluations = 25000
swarm_size = 100

algorithm = OMOPSO(
    problem=problem,
    swarm_size=swarm_size,
    epsilon=0.0075,
    uniform_mutation=UniformMutation(probability=mutation_probability, perturbation=0.5),
    non_uniform_mutation=NonUniformMutation(mutation_probability, perturbation=0.5,
                                            max_iterations=int(max_evaluations / swarm_size)),
    leaders=CrowdingDistanceArchive(100),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)
```

### Running the Algorithm
```python
algorithm.run()
solutions = algorithm.get_result()
```

### Visualizing Results
```python
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='OMOPSO-ZDT1')
```
```

--------------------------------

### NSGA-II Example Usage

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/nsgaii.html

Example of how to instantiate and run the NSGA-II algorithm with ZDT1 problem.

```APIDOC
## Example: Running NSGA-II

### Description
This example demonstrates how to configure and execute the NSGA-II algorithm using the ZDT1 problem, and then visualize the resulting Pareto front approximation.

### Method
N/A (Script execution)

### Endpoint
N/A

### Code Example
```python
from jmetal.algorithm.multiobjective.nsgaii import NSGAII
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT1
from jmetal.util.termination_criterion import StoppingByEvaluations
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

# Problem definition
problem = ZDT1()

# Algorithm configuration
max_evaluations = 25000
algorithm = NSGAII(
    problem=problem,
    population_size=100,
    offspring_population_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

# Run the algorithm
algorithm.run()
solutions = algorithm.get_result()

# Visualize the Pareto front approximation
front = get_non_dominated_solutions(solutions)
plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='NSGAII-ZDT1')
```

### Response Example
(Execution of the script will generate a plot visualizing the Pareto front approximation. No direct API response is applicable here.)
```

--------------------------------

### SMPSO/RP Example Usage

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/psos/smpso_preference.html

Example demonstrating how to use the SMPSO/RP algorithm with ZDT4 problem and visualization.

```APIDOC
## SMPSO/RP Example

This example demonstrates the usage of the SMPSO/RP algorithm for solving the ZDT4 problem and visualizing the Pareto front approximation.

### Setup
```python
from jmetal.algorithm.multiobjective.smpso import SMPSORP
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT4
from jmetal.util.archive import CrowdingDistanceArchiveWithReferencePoint
from jmetal.util.termination_criterion import StoppingByEvaluations
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

problem = ZDT4()
swarm_size = 100
reference_point = [[0.1, 0.8],[0.6, 0.1]]
archives_with_reference_points = []

for point in reference_point:
    archives_with_reference_points.append(
        CrowdingDistanceArchiveWithReferencePoint(int(swarm_size / len(reference_point)), point)
    )

max_evaluations = 50000
algorithm = SMPSORP(
    problem=problem,
    swarm_size=swarm_size,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    reference_points=reference_point,
    leaders=archives_with_reference_points,
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)
```

### Execution
```python
algorithm.run()
solutions = algorithm.get_result()
```

### Visualization
```python
front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'], reference_point=reference_point)
plot_front.plot(front, label='SMPSORP-ZDT4')
```
```

--------------------------------

### IBEA Algorithm Example

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/ibea.html

Example of how to use the IBEA algorithm with ZDT1 problem, SBXCrossover, PolynomialMutation, and plotting the results.

```APIDOC
## Example Usage of IBEA

### Description
This example demonstrates how to instantiate and run the IBEA algorithm for a multi-objective optimization problem (ZDT1), and then visualize the obtained Pareto front approximation.

### Code
```python
from jmetal.algorithm.multiobjective.ibea import IBEA
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT1
from jmetal.util.termination_criterion import StoppingByEvaluations
from jmetal.lab.visualization.plotting import Plot

# 1. Define the problem
problem = ZDT1()

# 2. Set termination criterion
max_evaluations = 25000
termination_criterion = StoppingByEvaluations(max_evaluations)

# 3. Instantiate the IBEA algorithm
algorithm = IBEA(
    problem=problem,
    kappa=1.,
    population_size=100,
    offspring_population_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    termination_criterion=termination_criterion
)

# 4. Run the algorithm
algorithm.run()
front = algorithm.get_result()

# 5. Visualize the results
plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='IBEA-ZDT1')
```

### Explanation
- The code first imports necessary classes from `jmetalpy`.
- It defines the `ZDT1` problem.
- A `StoppingByEvaluations` termination criterion is set.
- The `IBEA` algorithm is instantiated with specified parameters, including population size, mutation, and crossover operators.
- The `run()` method executes the optimization process.
- `get_result()` retrieves the approximated Pareto front.
- Finally, a `Plot` object is used to visualize the obtained front.
```

--------------------------------

### SPEA2 Usage Example

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/spea2.html

Example demonstrating how to use the SPEA2 algorithm with ZDT1 problem.

```APIDOC
## Example Usage of SPEA2

### Description
This example shows how to initialize and run the SPEA2 algorithm to solve the ZDT1 multi-objective optimization problem.

### Code
```python
from jmetal.algorithm.multiobjective.spea2 import SPEA2
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT1
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT1()

max_evaluations = 20000

algorithm = SPEA2(
    problem=problem,
    population_size=40,
    offspring_population_size=40,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
solutions = algorithm.get_result()

# To visualize the Pareto front approximation:
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='SPEA2-ZDT1')
```
```

--------------------------------

### GDE3 Algorithm Example

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/gde3.html

Example demonstrating how to use the GDE3 algorithm with the ZDT1 problem and visualize the results.

```APIDOC
## Example Usage of GDE3

This example shows how to instantiate and run the GDE3 algorithm for the ZDT1 problem and then visualize the obtained Pareto front approximation.

### Initialization
```python
from jmetal.algorithm.multiobjective.gde3 import GDE3
from jmetal.problem import ZDT1
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT1()
max_evaluations = 25000

algorithm = GDE3(
    problem=problem,
    population_size=100,
    cr=0.5,
    f=0.5,
    termination_criterion=StoppingByEvaluations(max_evaluations)
)
```

### Running the Algorithm
```python
algorithm.run()
solutions = algorithm.get_result()
```

### Visualization
```python
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='GDE3-ZDT1')
```
```

--------------------------------

### CLI Output Formats

Source: https://jmetal.github.io/jMetalPy/tutorials/quality_indicators_cli.html

Examples of the default text output and the JSON output format.

```text
Result (epsilon): 0.1
Result (igd): 0.1414213562373095
Result (igdplus): 0.1
Result (hv): 0.84
Result (nhv): -0.037037037037037
```

```json
{
  "epsilon": 0.1,
  "igd": 0.1414213562373095,
  "igdplus": 0.1,
  "hv": 0.84,
  "nhv": -0.037037037037037
}
```

--------------------------------

### Install jMetalPy via pip

Source: https://jmetal.github.io/jMetalPy/getting-started.html

Standard installation command for the jMetalPy package.

```bash
$ pip install jmetalpy  # or "jmetalpy[distributed]"
```

--------------------------------

### Preference Point-Based NSGA-II Example

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/nsgaii_preference.html

Example demonstrating how to use the preference point-based NSGA-II algorithm with ZDT2 problem and visualization.

```APIDOC
## Preference Point-Based NSGA-II Example

### Description
This example shows how to configure and run the NSGAII algorithm with a reference point for preference-based multi-objective optimization, followed by visualizing the obtained Pareto front approximation.

### Method
```python
from jmetal.algorithm.multiobjective.nsgaii import NSGAII
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT2
from jmetal.util.comparator import GDominanceComparator
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT2()

max_evaluations = 25000
reference_point = [0.2, 0.5]

algorithm = NSGAII(
    problem=problem,
    population_size=100,
    offspring_population_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    dominance_comparator=GDominanceComparator(reference_point),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
solutions = algorithm.get_result()

from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'], reference_point=reference_point)
plot_front.plot(front, label='gNSGAII-ZDT1')
```

### Visualization
```python
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'], reference_point=reference_point)
plot_front.plot(front, label='gNSGAII-ZDT1')
```
```

--------------------------------

### Run NSGA-II algorithm

Source: https://jmetal.github.io/jMetalPy/getting-started.html

A basic example demonstrating how to configure and execute the NSGA-II algorithm on the ZDT1 problem.

```python
from jmetal.algorithm.multiobjective.nsgaii import NSGAII
from jmetal.operator import SBXCrossover, PolynomialMutation
from jmetal.operator.selection import BinaryTournamentSelection
from jmetal.problem import ZDT1
from jmetal.util.termination_criterion import StoppingByEvaluations

# Define the problem
problem = ZDT1()

# Configure the algorithm
algorithm = NSGAII(
    problem=problem,
    population_size=100,
    offspring_population_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    selection=BinaryTournamentSelection(),
    termination_criterion=StoppingByEvaluations(max_evaluations=25000)
)

# Run the algorithm
algorithm.run()
solutions = algorithm.get_result()

# Print results
print(f"Found {len(solutions)} solutions")
```

--------------------------------

### Integrate DistanceBasedArchive with Algorithms

Source: https://jmetal.github.io/jMetalPy/advanced-topics/distance-based-archive.html

Conceptual example of initializing an algorithm with a custom archive.

```python
from jmetal.algorithm.multiobjective.nsgaii import NSGAII
from jmetal.util.archive import DistanceBasedArchive
from jmetal.problem import ZDT1

# Create algorithm with custom archive
problem = ZDT1()
archive = DistanceBasedArchive(maximum_size=100)

# Note: This is conceptual - actual integration depends on algorithm design
# Some algorithms may need modification to accept custom archives
```

--------------------------------

### Compute Quality Indicators

Source: https://jmetal.github.io/jMetalPy/tutorials/quality_indicators_cli.html

Examples of computing specific indicators or all indicators with custom configurations.

```bash
python -m jmetal.util.quality_indicator_cli front.csv reference.csv igd
```

```bash
python -m jmetal.util.quality_indicator_cli front.csv reference.csv all --ref-point 2.0,2.0
```

```bash
python -m jmetal.util.quality_indicator_cli front.csv reference.csv all --normalize --format json
```

```bash
python -m jmetal.util.quality_indicator_cli front.csv reference.csv epsilon
```

--------------------------------

### DistributedNSGAII Initialization and Execution

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/nsgaii.html

Setup and execution logic for DistributedNSGAII, utilizing Dask for parallel evaluation.

```python
class DistributedNSGAII(Algorithm[S, R]):
    def __init__(
        self,
        problem: Problem,
        population_size: int,
        mutation: Mutation,
        crossover: Crossover,
        number_of_cores: int,
        client,
        selection: Selection = BinaryTournamentSelection(
            MultiComparator([FastNonDominatedRanking.get_comparator(), CrowdingDistanceDensityEstimator.get_comparator()])
        ),
        termination_criterion: TerminationCriterion = store.default_termination_criteria,
        dominance_comparator: DominanceComparator = DominanceComparator(),
    ):
        super(DistributedNSGAII, self).__init__()
        self.problem = problem
        self.population_size = population_size
        self.mutation_operator = mutation
        self.crossover_operator = crossover
        self.selection_operator = selection
        self.dominance_comparator = dominance_comparator

        self.termination_criterion = termination_criterion
        self.observable.register(termination_criterion)

        self.number_of_cores = number_of_cores
        self.client = client



[docs]
    def create_initial_solutions(self) -> List[S]:
        return [self.problem.create_solution() for _ in range(self.number_of_cores)]



[docs]
    def evaluate(self, solutions: List[S]) -> List[S]:
        return self.client.map(self.problem.evaluate, solutions)



[docs]
    def stopping_condition_is_met(self) -> bool:
        return self.termination_criterion.is_met



[docs]
    def observable_data(self) -> dict:
        ctime = time.time() - self.start_computing_time

        return {
            "PROBLEM": self.problem,
            "EVALUATIONS": self.evaluations,
            "SOLUTIONS": self.result(),
            "COMPUTING_TIME": ctime,
        }



[docs]
    def init_progress(self) -> None:
        self.evaluations = self.number_of_cores

        observable_data = self.observable_data()
        self.observable.notify_all(**observable_data)



[docs]
    def step(self) -> None:
        pass



[docs]
    def update_progress(self):
        observable_data = self.observable_data()
        self.observable.notify_all(**observable_data)



[docs]
    def run(self):
        """Execute the algorithm."""
        self.start_computing_time = time.time()

        create_solution = dask.delayed(self.problem.create_solution)
        evaluate_solution = dask.delayed(self.problem.evaluate)

        task_pool = as_completed([], with_results=True)

        for _ in range(self.number_of_cores):
            new_solution = create_solution()
            new_evaluated_solution = evaluate_solution(new_solution)
            future = self.client.compute(new_evaluated_solution)

            task_pool.add(future)

        batches = task_pool.batches()

        auxiliar_population = []
        while len(auxiliar_population) < self.population_size:
            batch = next(batches)
            for _, received_solution in batch:
                auxiliar_population.append(received_solution)

                if len(auxiliar_population) < self.population_size:
                    break

            # submit as many new tasks as we collected
            for _ in batch:
```

--------------------------------

### MOEA/D Algorithm Usage

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/moead.html

Example demonstrating how to use the MOEA/D algorithm for multi-objective optimization.

```APIDOC
## MOEA/D Algorithm Usage Example

### Description
This example shows how to instantiate and run the MOEA/D algorithm with a specific problem, operators, and termination criterion.

### Method
```python
from jmetal.algorithm.multiobjective.moead import MOEAD
from jmetal.operator.mutation import PolynomialMutation
from jmetal.operator.crossover import DifferentialEvolutionCrossover
from jmetal.problem import LZ09_F2
from jmetal.util.aggregative_function import Tschebycheff
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = LZ09_F2()

max_evaluations = 150000

algorithm = MOEAD(
    problem=problem,
    population_size=300,
    crossover=DifferentialEvolutionCrossover(CR=1.0, F=0.5, K=0.5),
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    aggregative_function=Tschebycheff(dimension=problem.number_of_objectives),
    neighbor_size=20,
    neighbourhood_selection_probability=0.9,
    max_number_of_replaced_solutions=2,
    weight_files_path='resources/MOEAD_weights',
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
solutions = algorithm.get_result()
```

### Visualization Example

### Description
This example shows how to visualize the Pareto front approximation obtained from the MOEA/D algorithm.

### Method
```python
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='MOEAD-LZ09_F2')
```
```

--------------------------------

### Initialize Progress Method

Source: https://jmetal.github.io/jMetalPy/api/algorithm/singleobjective/local.search.html

Initializes the algorithm's progress tracking. This should be called before starting the algorithm's execution.

```python
init_progress() → None[source]¶
    
Initialize the algorithm. 
```

--------------------------------

### Initialize algorithm progress

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/omopso.html

Sets up initial evaluations, density estimation, and velocity/best solution states.

```python
    def init_progress(self) -> None:
        self.evaluations = self.swarm_size
        self.leaders.compute_density_estimator()

        self.initialize_velocity(self.solutions)
        self.initialize_particle_best(self.solutions)
        self.initialize_global_best(self.solutions)
```

--------------------------------

### Run MOEA/D Algorithm

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/moead.html

Example demonstrating how to instantiate and run the MOEA/D algorithm with specified problem, operators, and termination criterion. Ensure the 'resources/MOEAD_weights' directory exists.

```python
from jmetal.algorithm.multiobjective.moead import MOEAD
from jmetal.operator.mutation import PolynomialMutation
from jmetal.operator.crossover import DifferentialEvolutionCrossover
from jmetal.problem import LZ09_F2
from jmetal.util.aggregative_function import Tschebycheff
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = LZ09_F2()

max_evaluations = 150000

algorithm = MOEAD(
    problem=problem,
    population_size=300,
    crossover=DifferentialEvolutionCrossover(CR=1.0, F=0.5, K=0.5),
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    aggregative_function=Tschebycheff(dimension=problem.number_of_objectives),
    neighbor_size=20,
    neighbourhood_selection_probability=0.9,
    max_number_of_replaced_solutions=2,
    weight_files_path='resources/MOEAD_weights',
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
solutions = algorithm.get_result()

```

--------------------------------

### Initialize and run Dynamic GDE3

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/gde3_dynamic.html

Demonstrates how to configure and execute the Dynamic GDE3 algorithm with a dynamic problem, time-based updates, and observers for tracking progress.

```python
from jmetal.algorithm.multiobjective.gde3 import DynamicGDE3
from jmetal.problem.multiobjective.fda import FDA2
from jmetal.util.observable import TimeCounter
from jmetal.util.observer import PlotFrontToFileObserver, WriteFrontToFileObserver
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = FDA2()

time_counter = TimeCounter(delay=1)
time_counter.observable.register(problem)
time_counter.start()

algorithm = DynamicGDE3(
    problem=problem,
    population_size=100,
    cr=0.5,
    f=0.5,
    termination_criterion=StoppingByEvaluations(max=500)
)

algorithm.observable.register(observer=PlotFrontToFileObserver('front_plot'))
algorithm.observable.register(observer=WriteFrontToFileObserver('front_files'))

algorithm.run()
```

--------------------------------

### Configure and run SMPSO/RP

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/psos/smpso_preference.html

Initializes the SMPSO/RP algorithm with specific reference points and archives, then executes the optimization process.

```python
from jmetal.algorithm.multiobjective.smpso import SMPSORP
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT4
from jmetal.util.archive import CrowdingDistanceArchiveWithReferencePoint
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT4()

swarm_size = 100

reference_point = [[0.1, 0.8],[0.6, 0.1]]
archives_with_reference_points = []

for point in reference_point:
    archives_with_reference_points.append(
        CrowdingDistanceArchiveWithReferencePoint(int(swarm_size / len(reference_point)), point)
    )

max_evaluations = 50000
algorithm = SMPSORP(
    problem=problem,
    swarm_size=swarm_size,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    reference_points=reference_point,
    leaders=archives_with_reference_points,
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
solutions = algorithm.get_result()
```

--------------------------------

### Generate Sample Data Files

Source: https://jmetal.github.io/jMetalPy/tutorials/quality_indicators_cli.html

Use numpy to create sample solution and reference fronts for quality indicator computation. Save these fronts as CSV files.

```python
import numpy as np

# Create a sample solution front
front = np.array([[0.1, 0.9], [0.3, 0.7], [0.5, 0.5], [0.7, 0.3], [0.9, 0.1]])
np.savetxt('my_front.csv', front, delimiter=',')

# Create a reference front (e.g., true Pareto front)
reference = np.array([[0.0, 1.0], [0.2, 0.8], [0.4, 0.6], [0.6, 0.4], [0.8, 0.2], [1.0, 0.0]])
np.savetxt('reference_front.csv', reference, delimiter=',')

```

--------------------------------

### Run SMPSO Algorithm and Visualize Results

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/psos/smpso.html

This example demonstrates how to instantiate and run the SMPSO algorithm with the ZDT4 problem. It configures the algorithm with a specific swarm size, mutation operator, leader selection mechanism (CrowdingDistanceArchive), and termination criterion based on the maximum number of evaluations. After running, it retrieves the solutions and visualizes the Pareto front approximation.

```python
from jmetal.algorithm.multiobjective.smpso import SMPSO
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT4
from jmetal.util.archive import CrowdingDistanceArchive
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT4()

max_evaluations = 25000
algorithm = SMPSO(
    problem=problem,
    swarm_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    leaders=CrowdingDistanceArchive(100),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
solutions = algorithm.get_result()
```

```python
from jmetal.lab.visualization.plotting import Plot
from jmetal.util.solution import get_non_dominated_solutions

front = get_non_dominated_solutions(solutions)

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='SMPSO-ZDT4')
```

--------------------------------

### Initialize Experiment Execution

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/lab/experiment.html

Sets up an experiment to run a list of jobs. Specify the output directory for results and the maximum number of parallel workers.

```python
class Experiment:
    def __init__(self, output_dir: str, jobs: List[Job], m_workers: int = 6):
        """Run an experiment to execute a list of jobs.

        :param output_dir: Base directory where each job will save its results.
        :param jobs: List of Jobs (from :py:mod:`jmetal.util.laboratory)`) to be executed.
        :param m_workers: Maximum number of workers to execute the Jobs in parallel.
        """
        self.jobs = jobs
        self.m_workers = m_workers
        self.output_dir = output_dir
        self.job_data = []
```

--------------------------------

### Initialize LZ09_F2 Problem

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/multiobjective/lz09.html

Constructor for the LZ09_F2 benchmark problem.

```python
class LZ09_F2(LZ09):
    def __init__(self, number_of_variables=30):
        super(LZ09_F2, self).__init__(
```

--------------------------------

### Generic Type Constraint Example

Source: https://jmetal.github.io/jMetalPy/contributing.html

This example demonstrates a type warning when a type not allowed by the `TypeVar` constraint is used. The `TypeVar('S', int, float)` restricts `S` to only `int` or `float`.

```python
from typing import TypeVar

_TypeVar('S', int, float)

# IDE will display a warning here if 'str' is passed for S
```

--------------------------------

### Get algorithm name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/omopso.html

Returns the name of the algorithm.

```python
    def get_name(self) -> str:
        return "OMOPSO"
```

--------------------------------

### FDA2 Get Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/multiobjective/fda.html

Returns the name of the problem, which is 'FDA2'.

```python
def get_name(self):
        return "FDA2"
```

--------------------------------

### FDA1 Get Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/multiobjective/fda.html

Returns the name of the problem, which is 'FDA1'.

```python
def get_name(self):
        return "FDA1"
```

--------------------------------

### HYPE Algorithm Implementation

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/hype.html

Example of how to implement and run the HYPE algorithm for multi-objective optimization. Requires setting up a problem, reference point, and various genetic algorithm operators. Note the mandatory objective assignment for the reference point.

```python
from jmetal.algorithm.multiobjective.hype import HYPE
from jmetal.core.solution import FloatSolution
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT1
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT1()

reference_point = FloatSolution([0], [1], problem.number_of_objectives, )
reference_point.objectives = [1., 1.]  # Mandatory for HYPE

algorithm = HYPE(
    problem=problem,
    reference_point=reference_point,
    population_size=100,
    offspring_population_size=100,
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    termination_criterion=StoppingByEvaluations(2500)
)

algorithm.run()
solutions = algorithm.get_result()

```

--------------------------------

### NSGA-III Get Name Method

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/nsgaiii.html

Returns the name of the algorithm.

```APIDOC
## NSGA-III Get Name Method

### Description
Returns the name of the algorithm.

### Method
`get_name(self) -> str`

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
None

### Request Example
None

### Response
#### Success Response (200)
Returns the string "NSGAIII".

#### Response Example
None
```

--------------------------------

### Initialize SMPSO Algorithm

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/smpso.html

Constructor for the SMPSO algorithm. Requires the problem, swarm size, mutation operator, and a leaders archive. It sets up various parameters for the optimization process.

```python
def __init__(
        self,
        problem: FloatProblem,
        swarm_size: int,
        mutation: Mutation,
        leaders: Optional[BoundedArchive],
        dominance_comparator: Comparator = DominanceComparator(),
        termination_criterion: TerminationCriterion = store.default_termination_criteria,
        swarm_generator: Generator = store.default_generator,
        swarm_evaluator: Evaluator = store.default_evaluator,
    ):
        """This class implements the SMPSO algorithm as described in

        * SMPSO: A new PSO-based metaheuristic for multi-objective optimization
        * MCDM 2009. DOI: `<http://dx.doi.org/10.1109/MCDM.2009.4938830/>`_.

        The implementation of SMPSO provided in jMetalPy follows the algorithm template described in the algorithm
        templates section of the documentation.

        :param problem: The problem to solve.
        :param swarm_size: Size of the swarm.
        :param max_evaluations: Maximum number of evaluations/iterations.
        :param mutation: Mutation operator (see :py:mod:`jmetal.operator.mutation`).
        :param leaders: Archive for leaders.
        """
        super(SMPSO, self).__init__(problem=problem, swarm_size=swarm_size)
        self.swarm_generator = swarm_generator
        self.swarm_evaluator = swarm_evaluator
        self.termination_criterion = termination_criterion
        self.observable.register(termination_criterion)
        self.mutation_operator = mutation
        self.leaders = leaders

        self.c1_min = 1.5
        self.c1_max = 2.5
        self.c2_min = 1.5
        self.c2_max = 2.5
        self.r1_min = 0.0
        self.r1_max = 1.0
        self.r2_min = 0.0
        self.r2_max = 1.0
        self.min_weight = 0.1
        self.max_weight = 0.1
        self.change_velocity1 = -1
        self.change_velocity2 = -1

        self.dominance_comparator = dominance_comparator

        self.speed = numpy.zeros((self.swarm_size, self.problem.number_of_variables()), dtype=float)
        self.delta_max, self.delta_min = (
            numpy.empty(problem.number_of_variables()),
            numpy.empty(problem.number_of_variables()),
        )
```

--------------------------------

### MOEAD_DRA Get Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/moead.html

Returns the name of the MOEAD-DRA algorithm.

```python
    def get_name(self):
        return "MOEAD-DRA"
```

--------------------------------

### MOEAD Get Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/moead.html

Returns the name of the MOEAD algorithm.

```python
[docs]
    def get_name(self):
        return "MOEAD"
```

--------------------------------

### Create Many-Objective Solutions and Archive

Source: https://jmetal.github.io/jMetalPy/advanced-topics/distance-based-archive.html

Demonstrates creating a set of solutions with diverse trade-offs and managing them using a DistanceBasedArchive.

```python
import random
from jmetal.util.archive import DistanceBasedArchive
from jmetal.core.solution import FloatSolution

def create_many_objective_solutions(n_solutions=100, n_objectives=5):
    """Create diverse solutions in many-objective space"""
    solutions = []
    random.seed(42)  # For reproducibility

    for i in range(n_solutions):
        solution = FloatSolution([], [], n_objectives)
        # Create solutions with different trade-offs
        objectives = []
        for j in range(n_objectives):
            # Some solutions excel in specific objectives
            if i % n_objectives == j:
                objectives.append(random.uniform(0.0, 0.3))  # Good in this objective
            else:
                objectives.append(random.uniform(0.4, 1.0))  # Worse in others
        solution.objectives = objectives
        solutions.append(solution)

    return solutions

# Create archive for 5-objective problem
archive = DistanceBasedArchive(maximum_size=10)
solutions = create_many_objective_solutions(100, 5)

for solution in solutions:
    archive.add(solution)

print(f"Selected {archive.size()} solutions from {len(solutions)} candidates")
print("Selected solutions (5 objectives):")
for i in range(archive.size()):
    sol = archive.get(i)
    obj_str = [f"{obj:.3f}" for obj in sol.objectives]
    print(f"  Solution {i}: [{', '.join(obj_str)}]")
```

--------------------------------

### Get problem name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/core/problem.html

Returns the stored name of the problem.

```python
    def name(self) -> str:
        return self.problem_name
```

--------------------------------

### Get DTLZ6 Problem Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/multiobjective/dtlz.html

Returns the name of the DTLZ6 problem.

```python
def name(self):
        return "DTLZ6"
```

--------------------------------

### Initialize OMOPSO Algorithm

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/omopso.html

The OMOPSO class constructor requires a problem, swarm size, mutation operators, and an archive for leaders.

```python
class OMOPSO(ParticleSwarmOptimization):
    def __init__(
        self,
        problem: FloatProblem,
        swarm_size: int,
        uniform_mutation: UniformMutation,
        non_uniform_mutation: NonUniformMutation,
        leaders: Optional[BoundedArchive],
        epsilon: float,
        termination_criterion: TerminationCriterion,
        swarm_generator: Generator = store.default_generator,
        swarm_evaluator: Evaluator = store.default_evaluator,
    ):
        """This class implements the OMOPSO algorithm as described in

        todo Update this reference
        * SMPSO: A new PSO-based metaheuristic for multi-objective optimization

        The implementation of OMOPSO provided in jMetalPy follows the algorithm template described in the algorithm
        templates section of the documentation.

        :param problem: The problem to solve.
        :param swarm_size: Size of the swarm.
        :param leaders: Archive for leaders.
        """
        super(OMOPSO, self).__init__(problem=problem, swarm_size=swarm_size)
        self.swarm_generator = swarm_generator
        self.swarm_evaluator = swarm_evaluator

        self.termination_criterion = termination_criterion
        self.observable.register(termination_criterion)

        self.uniform_mutation = uniform_mutation
        self.non_uniform_mutation = non_uniform_mutation

        self.leaders = leaders

        self.epsilon = epsilon
        self.epsilon_archive = NonDominatedSolutionsArchive(EpsilonDominanceComparator(epsilon))

        self.c1_min = 1.5
        self.c1_max = 2.0
        self.c2_min = 1.5
        self.c2_max = 2.0
        self.r1_min = 0.0
        self.r1_max = 1.0
        self.r2_min = 0.0
        self.r2_max = 1.0
        self.weight_min = 0.1
        self.weight_max = 0.5
        self.change_velocity1 = -1
        self.change_velocity2 = -1

        self.dominance_comparator = DominanceComparator()

        self.speed = numpy.zeros((self.swarm_size, self.problem.number_of_variables()), dtype=float)
```

--------------------------------

### Get DTLZ5 Problem Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/multiobjective/dtlz.html

Returns the name of the DTLZ5 problem.

```python
def name(self):
        return "DTLZ5"
```

--------------------------------

### Get DTLZ4 Problem Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/multiobjective/dtlz.html

Returns the name of the DTLZ4 problem.

```python
def name(self):
        return "DTLZ4"
```

--------------------------------

### MOEAD Progress Initialization

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/moead.html

Sets up the initial state of the algorithm, including fitness function updates and permutation generation.

```python
def init_progress(self) -> None:
    self.evaluations = self.population_size
    for solution in self.solutions:
        self.fitness_function.update(solution.objectives)

    self.permutation = Permutation(self.population_size)

    observable_data = self.observable_data()
    self.observable.notify_all(**observable_data)
```

--------------------------------

### Get Problem Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/singleobjective/unconstrained.html

Returns the name of the problem, which is 'Subset Sum'.

```python
def name(self) -> str:
        return "Subset Sum"
```

--------------------------------

### Progress and Reference Point Methods

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/smpso.html

Methods to initialize progress, update state, and manage reference points.

```python
    def init_progress(self) -> None:
        self.evaluations = self.swarm_size

        for leader in self.leaders:
            leader.compute_density_estimator()

        self.initialize_velocity(self.solutions)
        self.initialize_particle_best(self.solutions)
        self.initialize_global_best(self.solutions)
```

```python
    def update_progress(self) -> None:
        self.evaluations += self.swarm_size

        for leader in self.leaders:
            leader.filter()
            leader.compute_density_estimator()

        observable_data = self.observable_data()
        observable_data["REFERENCE_POINT"] = self.get_reference_point()
        self.observable.notify_all(**observable_data)
```

```python
    def update_reference_point(self, new_reference_points: list):
        with self.lock:
            self.reference_points = new_reference_points

            for index, archive in enumerate(self.leaders):
                archive.update_reference_point(new_reference_points[index])
```

```python
    def get_reference_point(self):
        with self.lock:
            return self.reference_points
```

--------------------------------

### Get Knapsack Problem Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/problem/singleobjective/knapsack.html

Returns the name of the problem, which is 'Knapsack'.

```python
def name(self):
        return "Knapsack"

```

--------------------------------

### GET /result

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/smpso.html

Retrieves the final set of solutions found by the algorithm.

```APIDOC
## GET /result

### Description
Aggregates and returns all solutions stored in the algorithm's leaders.

### Method
GET

### Response
#### Success Response (200)
- **result** (List[FloatSolution]) - A list of solutions collected from all archives.
```

--------------------------------

### Get number of constraints

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/core/problem.html

Returns the count of constraints defined for the problem.

```python
    def number_of_constraints(self) -> int:
        return len(self.constraints)
```

--------------------------------

### Run MOCell Algorithm and Visualize Pareto Front

Source: https://jmetal.github.io/jMetalPy/api/algorithm/multiobjective/eas/mocell.html

This example demonstrates how to instantiate and run the MOCell algorithm for a multi-objective problem (ZDT4). It includes setting up the problem, population size, neighborhood, archive, mutation, crossover, and termination criterion. Finally, it visualizes the obtained Pareto front approximation using the Plot utility.

```python
from jmetal.algorithm.multiobjective.mocell import MOCell
from jmetal.operator.crossover import SBXCrossover
from jmetal.operator.mutation import PolynomialMutation
from jmetal.problem import ZDT4
from jmetal.util.archive import CrowdingDistanceArchive
from jmetal.util.neighborhood import C9
from jmetal.util.termination_criterion import StoppingByEvaluations

problem = ZDT4()

max_evaluations = 25000

algorithm = MOCell(
    problem=problem,
    population_size=100,
    neighborhood=C9(10, 10),
    archive=CrowdingDistanceArchive(100),
    mutation=PolynomialMutation(probability=1.0 / problem.number_of_variables, distribution_index=20),
    crossover=SBXCrossover(probability=1.0, distribution_index=20),
    termination_criterion=StoppingByEvaluations(max=max_evaluations)
)

algorithm.run()
front = algorithm.get_result()

```

```python
from jmetal.lab.visualization.plotting import Plot

plot_front = Plot(plot_title='Pareto front approximation', axis_labels=['x', 'y'])
plot_front.plot(front, label='MOCell-ZDT4')

```

--------------------------------

### Get GDE3 Algorithm Name

Source: https://jmetal.github.io/jMetalPy/_modules/jmetal/algorithm/multiobjective/gde3.html

Returns the name of the GDE3 algorithm.

```python
def get_name(self) -> str:
        return "GDE3"
```
Tokens:
Raw