### Install dependencies from requirements.txt

Source: https://geneticengine.readthedocs.io/en/latest/_sources/tutorial.md.txt

Installs the dependencies listed in requirements.txt as part of the tutorial setup.

```bash
python -m pip install -r requirements.txt
```

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

### Run all examples with uv

Source: https://geneticengine.readthedocs.io/en/latest/_sources/index.md.txt

Runs all examples using uv to manage Python dependencies. Requires uv installed.

```bash
./run_examples.sh

```

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

### Run examples with Codon enabled

Source: https://geneticengine.readthedocs.io/en/latest/_sources/index.md.txt

Runs all examples with Codon enabled. Requires Codon installed; the script uses codon run -release when feasible and falls back to uv run python for unsupported third-party packages.

```bash
CODON=1 ./run_examples.sh

```

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

### SimpleGP output example

Source: https://geneticengine.readthedocs.io/en/latest/_sources/tutorial.md.txt

Example output from the SimpleGP run, showing best fitness per generation and the best individual found.

```text
BEST at 0 / 5 is 0
BEST at 1 / 5 is 0
BEST at 2 / 5 is 0
BEST at 3 / 5 is 0
BEST at 4 / 5 is 0
0 Mean(arr=VectorialVar(index=2))
```

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

### Initialize GengyList

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/solutions/tree/index.html

Python built-in docstring example for GengyList, which extends list.Generic[T]. Initializes list.

```python
class GengyList(list, Generic[T]):
    """Built-in mutable sequence."""

```

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

### Grammar output example

Source: https://geneticengine.readthedocs.io/en/latest/_sources/tutorial.md.txt

Example output of the grammar extraction, showing the generated productions.

```text
Grammar<Starting=Scalar,Productions=[Scalar -> Value(value: float)|ScalarVar(index: [0...2])|Add(right: Scalar, left: Scalar)|Mean(arr: Vectorial);Vectorial -> VectorialVar(index: [2...4])|CumulativeSum(arr: Vectorial)]>.
```

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

### Example grammar with alternatives

Source: https://geneticengine.readthedocs.io/en/latest/grammars.html

Shows a simple grammar with two production rules. A can expand to 0 or B, and B can expand to 1 or 2. This illustrates how expansion depth is calculated.

```python
A       :== 0 | B
B       :== 1 | 2

```

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

### Minimal example: create arbitrary grammar and target individual

Source: https://geneticengine.readthedocs.io/en/latest/_sources/synthetic_problems.md.txt

Generates a random grammar with create_arbitrary_grammar, builds a Grammar object, and creates a random target individual (phenotype) using TreeBasedRepresentation and MaxDepthDecider.

```python
from geneticengine.grammar.grammar import extract_grammar
from geneticengine.grammar.synthetic_grammar import create_arbitrary_grammar
from geneticengine.random.sources import NativeRandomSource
from geneticengine.representations.tree.initializations import MaxDepthDecider
from geneticengine.representations.tree.treebased import TreeBasedRepresentation

# 1) Generate a random grammar
nodes, root = create_arbitrary_grammar(
    seed=0,
    non_terminals_count=3,
    recursive_non_terminals_count=2,
    productions_per_non_terminal=lambda rd: 2,
    non_terminals_per_production=lambda rd: 1,
)

# 2) Build a Grammar object
G = extract_grammar(nodes, root)

# 3) Create a random target individual (phenotype) from this grammar
r = NativeRandomSource(0)
rep = TreeBasedRepresentation(G, decider=MaxDepthDecider(r, G, G.get_min_tree_depth()))
G_target = rep.create_genotype(r, depth=8)
P_target = rep.genotype_to_phenotype(G_target)
print(P_target)
```

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

### Dependent metahandler example

Source: https://geneticengine.readthedocs.io/en/latest/_sources/metahandlers/index.md.txt

Shows how to use the Dependent metahandler to make a field depend on a previously generated field of the same class.

```python
@dataclass
class SimplePair:
    a: Annotated[int, IntRange(0, 3)]
    b: Annotated[int, Dependent("a", lambda a: IntRange(a, 4))]
```

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

### Grammar expansion example for depthing

Source: https://geneticengine.readthedocs.io/en/latest/_sources/grammars.md.txt

Example grammar used to illustrate grammar-expansion depthing. A tree with a single node 0 has depth 2 (A -> 0), while a tree with a single node 1 or 2 has depth 3 (A -> B -> 1 or 2).

```text
A       :== 0 | B
B       :== 1 | 2
```

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

### Structural subtyping example

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/solutions/index.html

Shows a class that structurally matches the Proto protocol and a function that accepts Proto. The call func(C()) passes static type checking.

```python
class C:
    def meth(self) -> int:
        return 0

def func(x: Proto) -> int:
    return x.meth()

func(C())  # Passes static type check

```

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

### py:method Grammar.get_weights

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/grammar/index.rst.txt

Gets grammar weights.

```APIDOC
### py:method Grammar.get_weights

### Description
Gets the current weights of the grammar.

### Method Signature
```python
get_weights()
```

### Returns
- **list[float]** - The grammar weights.

```

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

### Usage of Protocol in a function

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/solutions/tree/index.html

Example demonstrating how to use a Protocol class with structural subtyping. Includes a class C that satisfies the protocol and a function that accepts the protocol type.

```python
class C:
    def meth(self) -> int:
        return 0

def func(x: Proto) -> int:
    return x.meth()

func(C())  # Passes static type check


```

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

### Definition of TreeNode Protocol

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/solutions/tree/index.html

Shown in the documentation for the TreeNode class, this example illustrates how to define a Protocol class with a method. Copy the syntax for creating custom protocols.

```python
class Proto(Protocol):
    def meth(self) -> int:
        ...


```

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

### Define a custom genetic programming step with ParallelStep and SequenceStep

Source: https://geneticengine.readthedocs.io/en/latest/_sources/genetic_operators.md.txt

Shows how to combine elitism, novelty, selection, crossover, and mutation into a single step using ParallelStep and SequenceStep. The weights determine the proportion of each operation in the new generation. Note the example includes a trailing parenthesis that appears to be a typo in the source.

```python
default_generic_programming_step = ParallelStep([
        ElitismStep(),
        NoveltyStep()
        SequenceStep(
            TournamentSelection(tournament_size=5),
            GenericCrossoverStep(probability=0.01),
            GenericMutationStep(probability=0.9),
        )
    ], weights=[.05, .05, .90])
)
```

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

### PonyGE2Grammar.to_geneticengine()

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/grammar/ponyge2/index.rst.txt

Converts the parsed PonyGE2 grammar into the GeneticEngine node classes and starting symbol.

```APIDOC
## PonyGE2Grammar.to_geneticengine()

### Description
Returns the generated node classes and starting symbol from the parsed PonyGE2 grammar.

### Returns
- **tuple** - A tuple containing the generated node classes and the starting symbol.

### Example
```python
from geneticengine.grammar.ponyge2 import parse_ponyge2_grammar

grammar = parse_ponyge2_grammar("<start> ::= <expr>\n<expr> ::= x | y")
nodes, start = grammar.to_geneticengine()
```
```

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

### Generic Protocol class example

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/solutions/tree/index.html

Shows how to define a generic Protocol class using type parameter T. Part of the TreeNode documentation.

```python
class GenProto[T](Protocol):
    def meth(self) -> T:
        ...


```

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

### parse_ponyge2_grammar(source, *, ge_constants = None)

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/grammar/ponyge2/index.rst.txt

Parses PonyGE2 BNF text or a grammar file into a GeneticEngine grammar structure. The first rule is the starting symbol, and terminals are converted to fixed string fields or integer ranges.

```APIDOC
## parse_ponyge2_grammar(source, *, ge_constants = None)

### Description
Parses PonyGE2 BNF text or a grammar file. The first rule is the starting symbol. Ordinary terminals become fixed `VarRange` string fields. `GE_RANGE:n` becomes an integer field in `range(n)`; named ranges can be supplied through `ge_constants`.

### Parameters
- **source** (str) - Required - The PonyGE2 BNF grammar text or path to a grammar file.
- **ge_constants** (dict, optional) - Optional - Named ranges for `GE_RANGE` specifications.

### Returns
- **PonyGE2Grammar** - The generated GeneticEngine structure for the PonyGE2 grammar.

### Example
```python
from geneticengine.grammar.ponyge2 import parse_ponyge2_grammar

grammar = parse_ponyge2_grammar("<start> ::= <expr>\n<expr> ::= x | y")
```
```

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

### load_ponyge2_grammar

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/grammar/ponyge2/index.html

Parses a PonyGE2 grammar file into a PonyGE2Grammar object. The first rule is the starting symbol. Ordinary terminals become fixed VarRange string fields, and GE_RANGE:n becomes an integer field in range(n). Named ranges can be supplied through ge_constants.

```APIDOC
## load_ponyge2_grammar(path, *, ge_constants=None)

### Description
Parses a PonyGE2 grammar file. The first rule is the starting symbol. Ordinary terminals become fixed `VarRange` string fields. `GE_RANGE:n` becomes an integer field in `range(n)`; named ranges can be supplied through `ge_constants`.

### Parameters
- **path** (str | pathlib.Path) - Required - Path to the PonyGE2 grammar file.
- **ge_constants** (Mapping[str, int] | None) - Optional - Named ranges for `GE_RANGE` specifications.

### Returns
- **PonyGE2Grammar** - The generated GeneticEngine structure for the PonyGE2 grammar.

### Example
```python
from geneticengine.grammar.ponyge2 import load_ponyge2_grammar

grammar = load_ponyge2_grammar("grammar.bnf")
```
```

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

### Get number of enum members

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/grammar/metahandlers/lists/index.html

Returns the number of members in the enum. The output is 3 for the example Color enum.

```python
>>> len(Color)
3

```

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

### StandardInitializer.initialize

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/gp/operators/initializers/index.html

Initializes a population where all individuals are created with full trees (maximum depth in all branches).

```APIDOC
## StandardInitializer.initialize

### Description
All individuals are created with full trees (maximum depth in all branches).

### Method
initialize

### Signature
initialize(problem, representation, random, target_size, **kwargs)

### Parameters
- **problem** (geneticengine.problems.Problem) - Required - The problem to solve.
- **representation** (geneticengine.representations.api.Representation) - Required - The representation used for individuals.
- **random** (geneticengine.random.sources.RandomSource) - Required - The random source for stochastic operations.
- **target_size** (int) - Required - The target population size.
- **kwargs** - Optional - Additional keyword arguments.

### Return Type
Iterator[geneticengine.solutions.individual.PhenotypicIndividual]
```

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

### Initializers: StandardInitializer and InjectInitialPopulationWrapper

Source: https://geneticengine.readthedocs.io/en/latest/_sources/genetic_operators.md.txt

Population initializers for genetic algorithms. StandardInitializer creates an initial population, and InjectInitialPopulationWrapper allows injecting pre-existing programs into the initial population, with the remainder generated by a backup initializer.

```APIDOC
## StandardInitializer

### Description
Standard population initializer that works across all representations.

### Class
`geneticengine.algorithms.gp.operators.initializers.StandardInitializer`

## InjectInitialPopulationWrapper

### Description
Allows passing a list of programs to include in the initial population. The remainder is selected via a backup initializer.

### Class
`geneticengine.algorithms.gp.operators.initializers.InjectInitialPopulationWrapper`

### Usage
When creating the wrapper, provide the list of programs and a backup initializer.
```

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

### load_ponyge2_grammar(path, *, ge_constants = None)

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/grammar/ponyge2/index.rst.txt

Loads a PonyGE2 grammar from a file and parses it into a GeneticEngine grammar structure.

```APIDOC
## load_ponyge2_grammar(path, *, ge_constants = None)

### Description
Parses a PonyGE2 grammar file into a GeneticEngine grammar structure.

### Parameters
- **path** (str) - Required - Path to the PonyGE2 grammar file.
- **ge_constants** (dict, optional) - Optional - Named ranges for `GE_RANGE` specifications.

### Returns
- **PonyGE2Grammar** - The generated GeneticEngine structure for the PonyGE2 grammar.

### Example
```python
from geneticengine.grammar.ponyge2 import load_ponyge2_grammar

grammar = load_ponyge2_grammar("grammar.bnf")
```
```

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

### iterate_individuals

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/enumerative/index.html

Iterates over all possible individuals from a grammar starting from a given symbol.

```APIDOC
## iterate_individuals

### Description
Iterates over all possible individuals from a grammar starting from a given symbol.

### Parameters
- **grammar** (geneticengine.grammar.grammar.Grammar) - Required - The grammar to iterate.
- **starting_symbol** (type) - Required - The starting symbol type.

### Returns
Generator[geneticengine.solutions.individual.ConcreteIndividual, Any, Any]
```

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

### iterate_grammar

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/enumerative/index.html

Iterates over all possible representations from a grammar starting from a given symbol.

```APIDOC
## iterate_grammar

### Description
Iterates over all possible representations from a grammar starting from a given symbol.

### Parameters
- **grammar** (geneticengine.grammar.grammar.Grammar) - Required - The grammar to iterate.
- **starting_symbol** (type) - Required - The starting symbol type.
- **generator_for_recursive** (Optional[Any]) - Optional - Generator for recursive cases.
- **dependent_values** (Optional[dict[str, Any]]) - Optional - Dependent values.

### Returns
A generator of representations.
```

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

### HalfAndHalfInitializer.initialize

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/gp/operators/initializers/index.html

Initializes a population by combining two initializers, one for each half of the population.

```APIDOC
## HalfAndHalfInitializer.initialize

### Description
Combines two initializers, one for each half of the population.

### Method
initialize

### Signature
initialize(problem, representation, random, target_size, **kwargs)

### Parameters
- **problem** (geneticengine.problems.Problem) - Required - The problem to solve.
- **representation** (geneticengine.representations.api.Representation) - Required - The representation used for individuals.
- **random** (geneticengine.random.sources.RandomSource) - Required - The random source for stochastic operations.
- **target_size** (int) - Required - The target population size.
- **kwargs** - Optional - Additional keyword arguments.

### Return Type
Iterator[geneticengine.solutions.individual.PhenotypicIndividual]
```

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

### frange

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/enumerative/index.html

Generates a range of floating-point numbers from start to stop with a given step.

```APIDOC
## frange

### Description
Generates a range of floating-point numbers from start to stop with a given step.

### Parameters
- **start** (float) - Required - The starting value.
- **stop** (float) - Required - The stopping value (exclusive).
- **step** (float) - Required - The increment between values.

### Returns
A generator of floating-point numbers.
```

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

### Grammar-expansion depthing with expansion_depthing=True

Source: https://geneticengine.readthedocs.io/en/latest/_sources/grammars.md.txt

Creates a grammar using grammar-expansion depthing, as in PonyGE2. Depth increases each time a grammar production rule is expanded.

```python
grammar = extract_grammar([A, B], Root, expansion_depthing=True)
```

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

### time_for_initialization(budget)

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/algorithms/gp/adaptive/index.rst.txt

Determines if there is time for initialization based on the given budget. This function is part of the adaptive module.

```APIDOC
## Function: time_for_initialization(budget)

### Description
Checks whether there is time for initialization given the budget.

### Parameters
- **budget** (type not specified) - Required - The budget for initialization.

### Returns
- Boolean indicating if there is time for initialization.
```

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

### Population.__init__

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/gp/population/index.html

Constructor for the Population class. Initializes a population with an iterator of individuals, a progress tracker, and an optional generation number.

```APIDOC
## Population.__init__

### Description
Constructor for the Population class. Initializes a population with an iterator of individuals, a progress tracker, and an optional generation number.

### Method
`__init__(it, tracker, generation=-1)`

### Parameters
- **it** (Iterator[PhenotypicIndividual]) - Required - Iterator of individuals.
- **tracker** (ProgressTracker) - Required - Progress tracker for the algorithm.
- **generation** (int) - Optional - Generation number, defaults to -1.

### Returns
None
```

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

### Grammar

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/representations/stackgggp/index.html

The Grammar class represents a grammar with starting symbol, alternatives, and methods for validation, registration, and analysis.

```APIDOC
## Grammar

### Description
The Grammar class represents a grammar with a starting symbol, alternatives, and methods for validation, registration, and analysis.

### Constructor
`Grammar(starting_symbol, considered_subtypes=None, expansion_depthing=False)`

#### Parameters
- **starting_symbol** (type) - Required - The starting symbol of the grammar.
- **considered_subtypes** (list[type] | None) - Optional - List of considered subtypes.
- **expansion_depthing** (bool) - Optional - Whether expansion depthing is enabled.

### Attributes
- **starting_symbol** (type) - The starting symbol.
- **alternatives** (dict[type, list[type]]) - Mapping from nonterminal to list of alternatives.
- **distanceToTerminal** (dict[Any, int]) - Distance to terminal for each symbol.
- **all_nodes** (set[type]) - Set of all node types.
- **recursive_prods** (set[type]) - Set of recursive production types.
- **terminals** (set[type]) - Set of terminal types.
- **non_terminals** (set[type]) - Set of non-terminal types.
- **abstract_dist_to_t** (dict[type, dict[type, int]]) - Abstract distance to terminal.
- **considered_subtypes** (list) - Default: []
- **expansion_depthing** (bool) - Default: False

### Methods

#### validate()
Validates the grammar.

#### register_alternative(nonterminal, nodetype)
Registers a production A->B. Call multiple times with same A to register many possible alternatives.

##### Parameters
- **nonterminal** (type) - Required - The nonterminal symbol.
- **nodetype** (type) - Required - The node type.

#### register_type(ty)
Registers a type.

##### Parameters
- **ty** (type) - Required - The type to register.

#### __repr__()
Returns a string representation of the grammar.

#### get_all_symbols()
Returns all symbols in the current grammar, including terminals.

##### Return type
- tuple[set[type], set[type], set[type]]

#### collect_types(ty)
Collects types.

##### Parameters
- **ty** (type) - Required - The type to collect.

#### get_all_mentioned_symbols()
Returns all mentioned symbols.

##### Return type
- set[type]

#### get_distance_to_terminal(ty)
Returns the current distance to terminal of a given type.

##### Parameters
- **ty** (type) - Required - The type.

##### Return type
- int

#### get_min_tree_depth()
Returns the minimum depth a tree must have.

#### get_max_node_depth()
Returns the maximum minimum depth a node can have.

#### preprocess()
Computes distanceToTerminal via a fixpoint algorithm.

##### Return type
- None

#### get_weights()
Returns weights.

#### update_weights(learning_rate, extra_weights)
Updates weights.

#### is_reachable(t1, t2)
Checks if t2 is reachable from t1.

##### Parameters
- **t1** (Type) - Required - The source type.
- **t2** (Type) - Required - The target type.

##### Return type
- bool

#### reaches_leaf(t, visited=None)
Returns whether a given type reaches a leaf type, or None if it causes a loop. Loops should be ignored only if there is an alternative path.

##### Parameters
- **t** (Type) - Required - The type to check.
- **visited** (set | None) - Optional - Set of visited types.

##### Return type
- bool | None

#### usable_grammar()
Returns a subset of the grammar that is actually reachable.

##### Return type
- Grammar

#### get_grammar_properties_summary()
Returns a summary of grammar properties: a depth range (minimum depth and maximum depth), the number of Non-Terminal symbols, and production statistics including frequency of productions, number of recursive productions, per non-terminal alternatives, total productions, average productions per non-terminal, and average non-terminals per production.

##### Return type
- GrammarSummary
```

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

### StackBasedGGGPRepresentation

Source: https://geneticengine.readthedocs.io/en/latest/representations.html

Represents the Stack-based Grammatical Evolution representation. It uses a list of integers to guide the generation of trees in the phenotype.

```APIDOC
## StackBasedGGGPRepresentation

### Description
Represents the Stack-based Grammatical Evolution representation. It uses a list of integers to guide the generation of trees in the phenotype.

### Constructor
`StackBasedGGGPRepresentation(grammar, gene_length=1024, failures_limit=100)`

### Parameters
- **grammar** (geneticengine.grammar.grammar.Grammar) - Required - The grammar to use.
- **gene_length** (int) - Optional - The length of the gene. Default is 1024.
- **failures_limit** (int) - Optional - The limit of failures. Default is 100.

```

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

### GenericWrapper.get()

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/generic_utils/index.html

The get method of the GenericWrapper class returns the wrapped value of type C. It is a method that can be called on an instance of GenericWrapper.

```APIDOC
## GenericWrapper.get()

### Description
Returns the value of type C from the GenericWrapper instance.

### Method
get()

### Parameters
None

### Return Type
C

### Example
```python
wrapper = GenericWrapper(some_value)
result = wrapper.get()
```
```

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

### DynamicSGEDecider.choose_production_alternatives

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/representations/grammatical_evolution/dynamic_structured_ge/index.html

Chooses a production alternative for a given type.

```APIDOC
## DynamicSGEDecider.choose_production_alternatives

### Description
Chooses a production alternative for a given type.

### Method
`choose_production_alternatives(ty, alternatives, ctx)`

### Parameters
- **ty** (type) - Required - The type to choose for.
- **alternatives** (list[type]) - Required - The list of alternative types.
- **ctx** (geneticengine.solutions.tree.LocalSynthesisContext) - Required - The local synthesis context.

### Returns
- type - The chosen alternative type.
```

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

### random_node

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/representations/tree/treebased/index.html

Generates a random node in the tree representation using the given random source, grammar, starting symbol, and decider.

```APIDOC
## random_node(random, grammar, starting_symbol, decider)

### Description
Generates a random node in the tree representation using the given random source, grammar, starting symbol, and decider.

### Parameters
- **random** (geneticengine.random.sources.RandomSource) - Required - The random source used for generation.
- **grammar** (geneticengine.grammar.grammar.Grammar) - Required - The grammar defining valid tree structures.
- **starting_symbol** (type[Any]) - Required - The starting symbol for tree generation.
- **decider** (geneticengine.representations.tree.initializations.SynthesisDecider) - Required - The decider used for synthesis decisions.

### Returns
No explicit return type documented.

```

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

### Define an Enum with three members

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/grammar/metahandlers/lists/index.html

Defines an enumeration with three members. This is the example used in the documentation for the VariationType class, which is an enum.Enum subclass.

```python
>>> class Color(Enum):
...     RED = 1
...     BLUE = 2
...     GREEN = 3

```

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

### get_arguments(n)

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/grammar/utils/index.html

Returns list of (argname, argtype) for a production node.

```APIDOC
## get_arguments(n)

### Description
Returns list of (argname, argtype) for a production node.

### Parameters
- **n** (Any) - Required - production

### Returns
- list[tuple[str, type]]

```

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

### ParameterlessPopulationInitializer.initialize(problem, representation, random, target_size, **kwargs)

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/algorithms/gp/adaptive/index.rst.txt

Initializes a population without requiring explicit population size parameters. This method is part of the ParameterlessPopulationInitializer class.

```APIDOC
## Method: initialize(problem, representation, random, target_size, **kwargs)

### Description
Initializes a population for the given problem and representation.

### Parameters
- **problem** (type not specified) - Required - The problem to solve.
- **representation** (type not specified) - Required - The representation of individuals.
- **random** (type not specified) - Required - Random number generator.
- **target_size** (type not specified) - Required - The target population size.
- **kwargs** - Optional - Additional keyword arguments.

### Returns
- Initialized population.
```

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

### Extract grammar with extract_grammar

Source: https://geneticengine.readthedocs.io/en/latest/_sources/tutorial.md.txt

Extracts the grammar from the defined classes using extract_grammar, with Scalar as the starting type. Prints the grammar representation.

```python
g = extract_grammar([Value, ScalarVar, VectorialVar, Mean, CumulativeSum], Scalar)
print("Grammar: {}.".format(repr(g)))
```

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

### py:function extract_grammar

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/grammar/index.rst.txt

The extract_grammar function constructs a complete Grammar from a set of nodes and a starting symbol for use in search algorithms.

```APIDOC
## py:function extract_grammar

### Description
This function takes all productions of the grammar (nodes) and a starting symbol, and constructs a complete grammar that can be used for search algorithms such as Genetic Programming and Hill Climbing.

### Signature
```python
extract_grammar(considered_subtypes, starting_symbol, expansion_depthing=False)
```

### Parameters
- **nodes** (list) - Required - A list of objects representing tree nodes. Make sure that any node can be produced by the starting symbol.
- **starting_symbol** (object) - Required - The starting symbol of each tree. Ensures every generated tree by the returned grammar starts with this symbol. Make sure the starting symbol can produce any object of nodes.
- **considered_subtypes** (type) - Required - The considered subtypes parameter.
- **expansion_depthing** (bool) - Optional - Default is False.

### Returns
- **Grammar** - The constructed grammar.

```

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

### EvaluateStep.iterate

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/algorithms/gp/operators/evaluation/index.html

Documentation for the EvaluateStep class and its iterate method.

```APIDOC
## EvaluateStep.iterate

### Description
Evaluates the complete population.

### Method
iterate

### Parameters
- **problem** (geneticengine.problems.Problem) - Required - The problem to evaluate.
- **evaluator** (geneticengine.evaluation.Evaluator) - Required - The evaluator used to evaluate individuals.
- **representation** (geneticengine.representations.api.Representation) - Required - The representation of the individuals.
- **random** (geneticengine.random.sources.RandomSource) - Required - The random source.
- **population** (Iterator[geneticengine.solutions.individual.PhenotypicIndividual]) - Required - The population to evaluate.
- **target_size** (int) - Required - The target size of the population.
- **generation** (int) - Required - The current generation number.

### Returns
- Iterator[geneticengine.solutions.individual.PhenotypicIndividual] - The evaluated population.
```

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

### is_metahandler(ty)

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/grammar/utils/index.html

Returns if type is a metahandler. AnnotatedType[int, IntRange(3,10)] is an example of a Metahandler. Verification is done using the __metadata__, which is the first argument of Annotated.

```APIDOC
## is_metahandler(ty)

### Description
Returns if type is a metahandler. AnnotatedType[int, IntRange(3,10)] is an example of a Metahandler. Verification is done using the __metadata__, which is the first argument of Annotated.

### Parameters
- **ty** (type) - Required

### Returns
- bool

```

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

### GenericPopulationInitializer.initialize

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/representations/common/index.html

Initializes a population for any representation. This method is part of the GenericPopulationInitializer class and is used to generate an initial population of individuals for a given problem and representation.

```APIDOC
## GenericPopulationInitializer.initialize

### Description
Initializes a population for any representation. This method is part of the GenericPopulationInitializer class and is used to generate an initial population of individuals for a given problem and representation.

### Method
initialize

### Signature
initialize(problem, representation, random, target_size)

### Parameters
- **problem** (geneticengine.problems.Problem) - Required - The problem to solve.
- **representation** (geneticengine.representations.api.Representation) - Required - The representation to use.
- **random** (geneticengine.random.sources.RandomSource) - Required - The random source for generation.
- **target_size** (int) - Required - The desired population size.

### Return Type
Iterator[geneticengine.solutions.individual.PhenotypicIndividual]

### Description of Return
An iterator of PhenotypicIndividual objects representing the initial population.
```

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

### Run genetic search with SimpleGP

Source: https://geneticengine.readthedocs.io/en/latest/_sources/index.md.txt

Sets up and runs a genetic programming search using SimpleGP. Extracts the grammar from the defined classes, configures the algorithm with the fitness function and parameters, then prints the best fitness and best individual.

```python
grammar = extract_grammar([Literal, Plus], MyExpr)
alg = SimpleGP(
    grammar=grammar,
    fitness_function=fitness_function,
    minimize=True,
    population_size=200,
    max_evaluations=10000,
)
(b, bf) = alg.search()
print(bf, b)

```

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

### DynamicSGEDecider.choose_options

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/representations/grammatical_evolution/dynamic_structured_ge/index.html

Chooses an option from a list of alternatives.

```APIDOC
## DynamicSGEDecider.choose_options

### Description
Chooses an option from a list of alternatives.

### Method
`choose_options(alternatives, ctx)`

### Parameters
- **alternatives** (list[T]) - Required - The list of alternatives.
- **ctx** (geneticengine.solutions.tree.LocalSynthesisContext) - Required - The local synthesis context.

### Returns
- T - The chosen option.
```

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

### Define fitness function for expression evaluation

Source: https://geneticengine.readthedocs.io/en/latest/_sources/index.md.txt

Fitness function that evaluates an expression and returns the absolute difference from 42. Used by GeneticEngine to guide the search toward minimizing this value.

```python
def fitness_function(e:MyExpr) -> int
	return abs(42 - e.eval())

```

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

### geneticengine.solutions.individual

Source: https://geneticengine.readthedocs.io/en/latest/autoapi/geneticengine/solutions/individual/index.html

Documentation for the geneticengine.solutions.individual module, covering the Individual, ConcreteIndividual, PhenotypicIndividual classes and the IndividualNotEvaluatedException exception.

```APIDOC
## Class: Individual

### Description
Abstract base class for individuals in genetic algorithms. Provides a standard way to create an ABC using inheritance.

### Constructor
`Individual(_metadata=None)`

#### Parameters
- **metadata** (dict[str, Any] | None) - Optional metadata associated with the individual.

### Methods

#### get_phenotype()
- **Return type**: P
- **Description**: Abstract method to obtain the phenotype of the individual.

#### has_fitness(problem)
- **Parameters**:
  - **problem** (geneticengine.problems.Problem) - The problem for which fitness is checked.
- **Return type**: bool
- **Description**: Checks whether the individual has a fitness value for the given problem.

#### set_fitness(problem, fitness)
- **Parameters**:
  - **problem** (geneticengine.problems.Problem) - The problem for which fitness is set.
  - **fitness** (geneticengine.problems.Fitness) - The fitness value to set.
- **Description**: Sets the fitness value for the given problem.

#### get_fitness(problem=None)
- **Parameters**:
  - **problem** (geneticengine.problems.Problem | None) - The problem for which fitness is retrieved. If None, may return a default or raise an exception.
- **Return type**: geneticengine.problems.Fitness
- **Description**: Retrieves the fitness value for the given problem.

### Attributes
- **fitness_store**: weakref.WeakKeyDictionary[geneticengine.problems.Problem, geneticengine.problems.Fitness] - Stores fitness values per problem.
- **metadata**: dict[str, Any] - Metadata associated with the individual.

## Class: ConcreteIndividual

### Description
Concrete implementation of an individual that directly holds an instance of the phenotype.

### Constructor
`ConcreteIndividual(instance, metadata=None)`

#### Parameters
- **instance** (P) - The phenotype instance.
- **metadata** (dict[str, Any] | None) - Optional metadata.

### Methods

#### get_phenotype()
- **Return type**: P
- **Description**: Returns the phenotype instance.

### Attributes
- **instance**: P - The phenotype instance.

## Class: PhenotypicIndividual

### Description
Individual that derives its phenotype from a genotype using a representation.

### Constructor
`PhenotypicIndividual(genotype, representation, metadata=None)`

#### Parameters
- **genotype** (G) - The genotype.
- **representation** (geneticengine.representations.api.Representation[G, P]) - The representation used to convert genotype to phenotype.
- **metadata** (dict[str, Any] | None) - Optional metadata.

### Methods

#### get_phenotype()
- **Return type**: P
- **Description**: Computes and returns the phenotype from the genotype using the representation.

#### __str__()
- **Return type**: str
- **Description**: Returns a string representation of the individual.

### Attributes
- **genotype**: G - The genotype.
- **representation**: geneticengine.representations.api.Representation[G, P] - The representation.
- **phenotype**: P | None = None - Cached phenotype, initially None.

## Exception: IndividualNotEvaluatedException

### Description
Exception raised when an individual has not been evaluated (i.e., no fitness set). Inherits from Exception.

### Constructor
`IndividualNotEvaluatedException()`

#### Parameters
None.

## Module Attributes

- **G** - Type variable for genotype.
- **P** - Type variable for phenotype.
```

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

### Using with Genetic Programming: distance-based fitness

Source: https://geneticengine.readthedocs.io/en/latest/_sources/synthetic_problems.md.txt

Defines a fitness function using Levenshtein distance between stringified phenotypes and runs GeneticProgramming with an EvaluationBudget of 100. Assumes G and P_target are created as in the minimal example.

```python
from polyleven import levenshtein
from geneticengine.algorithms.gp.gp import GeneticProgramming
from geneticengine.evaluation.budget import EvaluationBudget
from geneticengine.problems import SingleObjectiveProblem

# Assume G and P_target are created as above

def fitness_function(p):
    return levenshtein(str(p), str(P_target))

problem = SingleObjectiveProblem(
    fitness_function=fitness_function,
    minimize=True,
    target=0,
)

r = NativeRandomSource(0)
alg = GeneticProgramming(
    problem=problem,
    budget=EvaluationBudget(100),
    representation=TreeBasedRepresentation(G, decider=MaxDepthDecider(r, G, G.get_min_tree_depth() + 10)),
    population_size=10,
    random=r,
)
ind = alg.search()[0]
print(ind, ind.get_fitness(problem))
```

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

### Run SimpleGP with grammar and fitness function

Source: https://geneticengine.readthedocs.io/en/latest/_sources/tutorial.md.txt

Runs the Genetic Engine with the extracted grammar and fitness function. Configures SimpleGP with tree-based representation, population size 10, and 50 evaluations.

```python
alg = SimpleGP(
    grammar=g,
    fitness_function=fitness_function,
    minimize=True,
    representation="treebased",
    population_size=10,
    max_evaluations=50)
(b, bf) = alg.search()
print(bf, b)
```

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

### mk_parser()

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/grammar/metahandlers/smt/parser/index.rst.txt

Creates and returns a parser for the SMT DSL using the defined grammar. This function is the primary entry point for parsing SMT expressions.

```APIDOC
## mk_parser()

### Description
Creates and returns a parser for the SMT DSL using the defined grammar. This function is the primary entry point for parsing SMT expressions.

### Function Signature
`mk_parser()`

### Returns
- **parser** (lark.Lark) - A configured Lark parser instance for the SMT DSL.

### Usage Example
```python
from geneticengine.grammar.metahandlers.smt.parser import mk_parser
parser = mk_parser()
# Use parser to parse SMT expressions
```
```

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

### Probabilistic grammar with @weight decorator

Source: https://geneticengine.readthedocs.io/en/latest/_sources/grammars.md.txt

Assigns probabilities to grammar productions using the @weight decorator. OptionA is selected with 10% probability and OptionB with 90%. The classes must extend the root class (here shown as R, but the example uses Root in the surrounding text).

```python
class Root(ABC):
    pass

@weight(0.1)
class OptionA(R):
    " This option will be selected with 10% of probability "
    pass


@weight(0.9)
class OptionB(R):
    " This option will be selected with 90% of probability "
    pass

```

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

### Simple integer class in Python

Source: https://geneticengine.readthedocs.io/en/latest/_sources/metahandlers/index.md.txt

Shows how to define a base type in Genetic Engine's STGP front-end, where only the base type needs to be specified.

```python
class I:
	value: int
```

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

### geneticengine.algorithms.gp.operators.initializers

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/algorithms/gp/operators/initializers/index.rst.txt

This module provides population initializers for genetic programming, including a combined initializer and a standard full-tree initializer.

```APIDOC
## HalfAndHalfInitializer

### Description
Combines two initializers, one for each half of the population.

### Constructor
- **initializer1** - The first initializer.
- **initializer2** - The second initializer.

### Attributes
- **initializer1** - The first initializer.
- **initializer2** - The second initializer.

### Methods
#### initialize(problem, representation, random, target_size, **kwargs)
Initializes a population by combining two initializers, each responsible for half of the population.

##### Parameters
- **problem** - The problem instance.
- **representation** - The representation used for individuals.
- **random** - The random number generator.
- **target_size** - The desired population size.
- **kwargs** - Additional keyword arguments.

##### Returns
- The initialized population.

## StandardInitializer

### Description
All individuals are created with full trees (maximum depth in all branches).

### Methods
#### initialize(problem, representation, random, target_size, **kwargs)
Initializes a population where all individuals are full trees.

##### Parameters
- **problem** - The problem instance.
- **representation** - The representation used for individuals.
- **random** - The random number generator.
- **target_size** - The desired population size.
- **kwargs** - Additional keyword arguments.

##### Returns
- The initialized population.
```

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

### GeneticProgramming(problem, budget, representation, random=None, tracker=None, population_size=100, population_initializer=None, step=None)

Source: https://geneticengine.readthedocs.io/en/latest/_sources/autoapi/geneticengine/algorithms/gp/gp/index.rst.txt

Represents the Genetic Programming algorithm. Defaults as given in A Field Guide to GP, p.17, by Poli and Mcphee. This class is a heuristic search algorithm that evolves solutions to a problem using genetic programming.

```APIDOC
## GeneticProgramming(problem, budget, representation, random=None, tracker=None, population_size=100, population_initializer=None, step=None)

### Description
Represents the Genetic Programming algorithm. Defaults as given in A Field Guide to GP, p.17, by Poli and Mcphee.

### Constructor Parameters
- **problem** (Problem) - Required - A SingleObjectiveProblem or a MultiObjectiveProblem problem.
- **budget** (SearchBudget) - Required - how long to search for
- **representation** (Representation) - Required - The individual representation used by the GP program.
- **random** (RandomSource) - Optional - A RNG instance
- **tracker** (ProgressTracker) - Optional - How to record the results of evaluations
- **population_size** (int) - Optional - The population size (default = 200).
- **population_initializer** (PopulationInitializer) - Optional - The method to generate new individuals.
- **step** (GeneticStep) - Optional - The main structure of evolution.

### Attributes
- **population_size** (int) - Default: 100
- **population_initializer** - No default provided
- **step** - No default provided

### Methods
#### perform_search()
Performs the search. No parameters or return value documented.

```

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

### Using metahandlers in a dataclass

Source: https://geneticengine.readthedocs.io/en/latest/_sources/metahandlers/index.md.txt

Shows how to use metahandlers to restrict fields with ranges and sizes. Includes IntRange, FloatRange, ListSizeBetween, VarRange, and StringSizeBetween.

```python
@dataclass
class Container(Parent):
	age : Annotated[int, IntRange[0, 200]]
	height : Annotated[float, FloatRange[0.10, 2.5]]
	children : Annotated[List[Container], ListSizeBetween[1,30]]
	var_name : Annotated[str, VarRange[["x", "y", "z"]]]
	dna : Annotated[str, StringSizeBetween(50, 80, ["a", "c", "t", "g"])]
```