Class swarmauri_standard.similarities.OverlapCoefficientSimilarity.OverlapCoefficientSimilarity

swarmauri_standard.similarities.OverlapCoefficientSimilarity.OverlapCoefficientSimilarity

Bases: SimilarityBase

Overlap Coefficient Similarity implementation.

The Overlap Coefficient measures the overlap between two sets. It is defined as the size of the intersection divided by the size of the smaller set. This makes it sensitive to complete inclusion, where one set is a subset of the other.

Attributes

type : Literal["OverlapCoefficientSimilarity"] The type identifier for this similarity measure

type class-attribute instance-attribute

type = 'OverlapCoefficientSimilarity'

model_config class-attribute instance-attribute

model_config = ConfigDict(
    extra="allow", arbitrary_types_allowed=True
)

id class-attribute instance-attribute

id = Field(default_factory=generate_id)

members class-attribute instance-attribute

members = None

owners class-attribute instance-attribute

owners = None

host class-attribute instance-attribute

host = None

default_logger class-attribute

default_logger = None

logger class-attribute instance-attribute

logger = None

name class-attribute instance-attribute

name = None

resource class-attribute instance-attribute

resource = SIMILARITY.value

version class-attribute instance-attribute

version = '0.1.0'

similarity

similarity(x, y)

Calculate the Overlap Coefficient similarity between two sets.

The Overlap Coefficient is defined as |X ∩ Y| / min(|X|, |Y|).

Parameters

x : ComparableType First set or collection y : ComparableType Second set or collection

Returns

float Overlap Coefficient similarity between x and y

Raises

ValueError If either set is empty TypeError If inputs cannot be converted to sets

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def similarity(self, x: ComparableType, y: ComparableType) -> float:
    """
    Calculate the Overlap Coefficient similarity between two sets.

    The Overlap Coefficient is defined as |X ∩ Y| / min(|X|, |Y|).

    Parameters
    ----------
    x : ComparableType
        First set or collection
    y : ComparableType
        Second set or collection

    Returns
    -------
    float
        Overlap Coefficient similarity between x and y

    Raises
    ------
    ValueError
        If either set is empty
    TypeError
        If inputs cannot be converted to sets
    """
    try:
        set_x = self._convert_to_set(x)
        set_y = self._convert_to_set(y)

        # Check if sets are non-empty
        if not set_x or not set_y:
            logger.error("Sets must be non-empty for Overlap Coefficient")
            raise ValueError("Sets must be non-empty for Overlap Coefficient")

        # Calculate intersection
        intersection_size = len(set_x.intersection(set_y))

        # Calculate minimum size
        min_size = min(len(set_x), len(set_y))

        # Calculate overlap coefficient
        return intersection_size / min_size
    except Exception as e:
        logger.error(f"Error calculating Overlap Coefficient similarity: {str(e)}")
        raise

similarities

similarities(x, ys)

Calculate Overlap Coefficient similarities between one set and multiple other sets.

Parameters

x : ComparableType Reference set or collection ys : Sequence[ComparableType] Sequence of sets or collections to compare against the reference

Returns

List[float] List of Overlap Coefficient similarity scores between x and each element in ys

Raises

ValueError If any set is empty TypeError If any input cannot be converted to a set

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def similarities(
    self, x: ComparableType, ys: Sequence[ComparableType]
) -> List[float]:
    """
    Calculate Overlap Coefficient similarities between one set and multiple other sets.

    Parameters
    ----------
    x : ComparableType
        Reference set or collection
    ys : Sequence[ComparableType]
        Sequence of sets or collections to compare against the reference

    Returns
    -------
    List[float]
        List of Overlap Coefficient similarity scores between x and each element in ys

    Raises
    ------
    ValueError
        If any set is empty
    TypeError
        If any input cannot be converted to a set
    """
    try:
        # Convert x to set once for efficiency
        set_x = self._convert_to_set(x)

        if not set_x:
            logger.error("Reference set must be non-empty for Overlap Coefficient")
            raise ValueError(
                "Reference set must be non-empty for Overlap Coefficient"
            )

        len_x = len(set_x)
        results = []

        for y in ys:
            set_y = self._convert_to_set(y)

            if not set_y:
                logger.error(
                    "Comparison set must be non-empty for Overlap Coefficient"
                )
                raise ValueError(
                    "Comparison set must be non-empty for Overlap Coefficient"
                )

            # Calculate intersection
            intersection_size = len(set_x.intersection(set_y))

            # Calculate minimum size
            min_size = min(len_x, len(set_y))

            # Calculate overlap coefficient
            results.append(intersection_size / min_size)

        return results
    except Exception as e:
        logger.error(
            f"Error calculating multiple Overlap Coefficient similarities: {str(e)}"
        )
        raise

dissimilarity

dissimilarity(x, y)

Calculate the Overlap Coefficient dissimilarity between two sets.

Defined as 1 - similarity(x, y).

Parameters

x : ComparableType First set or collection y : ComparableType Second set or collection

Returns

float Overlap Coefficient dissimilarity between x and y

Raises

ValueError If either set is empty TypeError If inputs cannot be converted to sets

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def dissimilarity(self, x: ComparableType, y: ComparableType) -> float:
    """
    Calculate the Overlap Coefficient dissimilarity between two sets.

    Defined as 1 - similarity(x, y).

    Parameters
    ----------
    x : ComparableType
        First set or collection
    y : ComparableType
        Second set or collection

    Returns
    -------
    float
        Overlap Coefficient dissimilarity between x and y

    Raises
    ------
    ValueError
        If either set is empty
    TypeError
        If inputs cannot be converted to sets
    """
    return 1.0 - self.similarity(x, y)

check_bounded

check_bounded()

Check if the Overlap Coefficient similarity measure is bounded.

The Overlap Coefficient is bounded in the range [0, 1].

Returns

bool True, as the Overlap Coefficient is bounded

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def check_bounded(self) -> bool:
    """
    Check if the Overlap Coefficient similarity measure is bounded.

    The Overlap Coefficient is bounded in the range [0, 1].

    Returns
    -------
    bool
        True, as the Overlap Coefficient is bounded
    """
    return True

check_reflexivity

check_reflexivity(x)

Check if the Overlap Coefficient similarity measure is reflexive: s(x,x) = 1.

Parameters

x : ComparableType Object to check reflexivity with

Returns

bool True, as the Overlap Coefficient is reflexive

Raises

ValueError If the set is empty TypeError If the input cannot be converted to a set

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def check_reflexivity(self, x: ComparableType) -> bool:
    """
    Check if the Overlap Coefficient similarity measure is reflexive: s(x,x) = 1.

    Parameters
    ----------
    x : ComparableType
        Object to check reflexivity with

    Returns
    -------
    bool
        True, as the Overlap Coefficient is reflexive

    Raises
    ------
    ValueError
        If the set is empty
    TypeError
        If the input cannot be converted to a set
    """
    try:
        set_x = self._convert_to_set(x)

        if not set_x:
            logger.error("Set must be non-empty for Overlap Coefficient")
            raise ValueError("Set must be non-empty for Overlap Coefficient")

        # For any non-empty set, the overlap with itself is the set itself,
        # and the minimum size is the size of the set, so the result is 1.0
        return True
    except Exception as e:
        logger.error(f"Error checking reflexivity: {str(e)}")
        raise

check_symmetry

check_symmetry(x, y)

Check if the Overlap Coefficient similarity measure is symmetric: s(x,y) = s(y,x).

Parameters

x : ComparableType First set or collection y : ComparableType Second set or collection

Returns

bool True, as the Overlap Coefficient is symmetric

Raises

ValueError If either set is empty TypeError If inputs cannot be converted to sets

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def check_symmetry(self, x: ComparableType, y: ComparableType) -> bool:
    """
    Check if the Overlap Coefficient similarity measure is symmetric: s(x,y) = s(y,x).

    Parameters
    ----------
    x : ComparableType
        First set or collection
    y : ComparableType
        Second set or collection

    Returns
    -------
    bool
        True, as the Overlap Coefficient is symmetric

    Raises
    ------
    ValueError
        If either set is empty
    TypeError
        If inputs cannot be converted to sets
    """
    # The Overlap Coefficient is symmetric by definition:
    # |X ∩ Y| / min(|X|, |Y|) = |Y ∩ X| / min(|Y|, |X|)
    return True

check_identity_of_discernibles

check_identity_of_discernibles(x, y)

Check if the Overlap Coefficient satisfies the identity of discernibles: s(x,y) = 1 ⟺ x = y.

Note: The Overlap Coefficient does not strictly satisfy this property. It returns 1 when one set is a subset of the other, not only when they are identical.

Parameters

x : ComparableType First set or collection y : ComparableType Second set or collection

Returns

bool False if x ≠ y but s(x,y) = 1, True otherwise

Raises

ValueError If either set is empty TypeError If inputs cannot be converted to sets

Source code in swarmauri_standard/similarities/OverlapCoefficientSimilarity.py

def check_identity_of_discernibles(
    self, x: ComparableType, y: ComparableType
) -> bool:
    """
    Check if the Overlap Coefficient satisfies the identity of discernibles: s(x,y) = 1 ⟺ x = y.

    Note: The Overlap Coefficient does not strictly satisfy this property.
    It returns 1 when one set is a subset of the other, not only when they are identical.

    Parameters
    ----------
    x : ComparableType
        First set or collection
    y : ComparableType
        Second set or collection

    Returns
    -------
    bool
        False if x ≠ y but s(x,y) = 1, True otherwise

    Raises
    ------
    ValueError
        If either set is empty
    TypeError
        If inputs cannot be converted to sets
    """
    try:
        set_x = self._convert_to_set(x)
        set_y = self._convert_to_set(y)

        if not set_x or not set_y:
            logger.error("Sets must be non-empty for Overlap Coefficient")
            raise ValueError("Sets must be non-empty for Overlap Coefficient")

        similarity_value = self.similarity(set_x, set_y)

        # If similarity is 1, check if sets are identical
        if abs(similarity_value - 1.0) < 1e-10:
            # The Overlap Coefficient can be 1 even if the sets are not identical
            # It will be 1 if one set is a subset of the other
            return set_x == set_y

        # If similarity is not 1, identity of discernibles is satisfied
        return True
    except Exception as e:
        logger.error(f"Error checking identity of discernibles: {str(e)}")
        raise

register_model classmethod

register_model()

Decorator to register a base model in the unified registry.

RETURNS	DESCRIPTION
Callable	A decorator function that registers the model class. TYPE: Callable[[Type[BaseModel]], Type[BaseModel]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_model(cls) -> Callable[[Type[BaseModel]], Type[BaseModel]]:
    """
    Decorator to register a base model in the unified registry.

    Returns:
        Callable: A decorator function that registers the model class.
    """

    def decorator(model_cls: Type[BaseModel]):
        """Register ``model_cls`` as a base model."""
        model_name = model_cls.__name__
        if model_name in cls._registry:
            glogger.warning(
                "Model '%s' is already registered; skipping duplicate.", model_name
            )
            return model_cls

        cls._registry[model_name] = {"model_cls": model_cls, "subtypes": {}}
        glogger.debug("Registered base model '%s'.", model_name)
        DynamicBase._recreate_models()
        return model_cls

    return decorator

register_type classmethod

register_type(resource_type=None, type_name=None)

Decorator to register a subtype under one or more base models in the unified registry.

PARAMETER	DESCRIPTION
resource_type	The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase) are used. TYPE: Optional[Union[Type[T], List[Type[T]]]] DEFAULT: None
type_name	An optional custom type name for the subtype. TYPE: Optional[str] DEFAULT: None

RETURNS	DESCRIPTION
Callable	A decorator function that registers the subtype. TYPE: Callable[[Type[DynamicBase]], Type[DynamicBase]]

Source code in swarmauri_base/DynamicBase.py

@classmethod
def register_type(
    cls,
    resource_type: Optional[Union[Type[T], List[Type[T]]]] = None,
    type_name: Optional[str] = None,
) -> Callable[[Type["DynamicBase"]], Type["DynamicBase"]]:
    """
    Decorator to register a subtype under one or more base models in the unified registry.

    Parameters:
        resource_type (Optional[Union[Type[T], List[Type[T]]]]):
            The base model(s) under which to register the subtype. If None, all direct base classes (except DynamicBase)
            are used.
        type_name (Optional[str]): An optional custom type name for the subtype.

    Returns:
        Callable: A decorator function that registers the subtype.
    """

    def decorator(subclass: Type["DynamicBase"]):
        """Register ``subclass`` as a subtype."""
        if resource_type is None:
            resource_types = [
                base for base in subclass.__bases__ if base is not cls
            ]
        elif not isinstance(resource_type, list):
            resource_types = [resource_type]
        else:
            resource_types = resource_type

        for rt in resource_types:
            if not issubclass(subclass, rt):
                raise TypeError(
                    f"'{subclass.__name__}' must be a subclass of '{rt.__name__}'."
                )
            final_type_name = type_name or getattr(
                subclass, "_type", subclass.__name__
            )
            base_model_name = rt.__name__

            if base_model_name not in cls._registry:
                cls._registry[base_model_name] = {"model_cls": rt, "subtypes": {}}
                glogger.debug(
                    "Created new registry entry for base model '%s'.",
                    base_model_name,
                )

            subtypes_dict = cls._registry[base_model_name]["subtypes"]
            if final_type_name in subtypes_dict:
                glogger.warning(
                    "Type '%s' already exists under '%s'; skipping duplicate.",
                    final_type_name,
                    base_model_name,
                )
                continue

            subtypes_dict[final_type_name] = subclass
            glogger.debug(
                "Registered '%s' as '%s' under '%s'.",
                subclass.__name__,
                final_type_name,
                base_model_name,
            )

        DynamicBase._recreate_models()
        return subclass

    return decorator

model_validate_toml classmethod

model_validate_toml(toml_data)

Validate a model from a TOML string.

Source code in swarmauri_base/TomlMixin.py

@classmethod
def model_validate_toml(cls, toml_data: str):
    """Validate a model from a TOML string."""
    try:
        # Parse TOML into a Python dictionary
        toml_content = tomllib.loads(toml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(toml_content))
    except tomllib.TOMLDecodeError as e:
        raise ValueError(f"Invalid TOML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_toml

model_dump_toml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a TOML representation of the model.

Source code in swarmauri_base/TomlMixin.py

def model_dump_toml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a TOML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into TOML
    return toml.dumps(filtered_data)

model_validate_yaml classmethod

model_validate_yaml(yaml_data)

Validate a model from a YAML string.

Source code in swarmauri_base/YamlMixin.py

@classmethod
def model_validate_yaml(cls, yaml_data: str):
    """Validate a model from a YAML string."""
    try:
        # Parse YAML into a Python dictionary
        yaml_content = yaml.safe_load(yaml_data)

        # Convert the dictionary to JSON and validate using Pydantic
        return cls.model_validate_json(json.dumps(yaml_content))
    except yaml.YAMLError as e:
        raise ValueError(f"Invalid YAML data: {e}")
    except ValidationError as e:
        raise ValueError(f"Validation failed: {e}")

model_dump_yaml

model_dump_yaml(
    fields_to_exclude=None, api_key_placeholder=None
)

Return a YAML representation of the model.

Source code in swarmauri_base/YamlMixin.py

def model_dump_yaml(self, fields_to_exclude=None, api_key_placeholder=None):
    """Return a YAML representation of the model."""
    if fields_to_exclude is None:
        fields_to_exclude = []

    # Load the JSON string into a Python dictionary
    json_data = json.loads(self.model_dump_json())

    # Function to recursively remove specific keys and handle api_key placeholders
    def process_fields(data, fields_to_exclude):
        """Recursively filter fields and apply placeholders."""
        if isinstance(data, dict):
            return {
                key: (
                    api_key_placeholder
                    if key == "api_key" and api_key_placeholder is not None
                    else process_fields(value, fields_to_exclude)
                )
                for key, value in data.items()
                if key not in fields_to_exclude
            }
        elif isinstance(data, list):
            return [process_fields(item, fields_to_exclude) for item in data]
        else:
            return data

    # Filter the JSON data
    filtered_data = process_fields(json_data, fields_to_exclude)

    # Convert the filtered data into YAML using safe mode
    return yaml.safe_dump(filtered_data, default_flow_style=False)

model_post_init

model_post_init(logger=None)

Assign a logger instance after model initialization.

Source code in swarmauri_base/LoggerMixin.py

def model_post_init(self, logger: Optional[FullUnion[LoggerBase]] = None) -> None:
    """Assign a logger instance after model initialization."""

    # Directly assign the provided FullUnion[LoggerBase] or fallback to the
    # class-level default.
    self.logger = self.logger or logger or self.default_logger

dissimilarities

dissimilarities(x, ys)

Calculate dissimilarities between one object and multiple other objects.

Parameters

x : ComparableType Reference object ys : Sequence[ComparableType] Sequence of objects to compare against the reference

Returns

List[float] List of dissimilarity scores between x and each element in ys

Raises

NotImplementedError This method must be implemented by subclasses ValueError If any objects are incomparable or have incompatible dimensions TypeError If any input types are not supported

Source code in swarmauri_base/similarities/SimilarityBase.py

def dissimilarities(
    self, x: ComparableType, ys: Sequence[ComparableType]
) -> List[float]:
    """
    Calculate dissimilarities between one object and multiple other objects.

    Parameters
    ----------
    x : ComparableType
        Reference object
    ys : Sequence[ComparableType]
        Sequence of objects to compare against the reference

    Returns
    -------
    List[float]
        List of dissimilarity scores between x and each element in ys

    Raises
    ------
    NotImplementedError
        This method must be implemented by subclasses
    ValueError
        If any objects are incomparable or have incompatible dimensions
    TypeError
        If any input types are not supported
    """
    # Default implementation can be overridden for efficiency
    try:
        return [self.dissimilarity(x, y) for y in ys]
    except Exception as e:
        logger.error(f"Error calculating dissimilarities: {str(e)}")
        raise