Class swarmauri_standard.similarities.BhattacharyyaCoefficientSimilarity.BhattacharyyaCoefficientSimilarity

swarmauri_standard.similarities.BhattacharyyaCoefficientSimilarity.BhattacharyyaCoefficientSimilarity

Bases: SimilarityBase

Bhattacharyya Coefficient Similarity metric for measuring overlap between probability distributions.

This similarity measure calculates the Bhattacharyya coefficient, which quantifies the amount of overlap between two probability distributions. It's commonly used for comparing histograms or probability density functions.

The coefficient is defined as the sum of the square root of the product of corresponding probabilities from both distributions: BC(p,q) = ∑ √(p_i * q_i)

Attributes

type : Literal["BhattacharyyaCoefficientSimilarity"] Type identifier for this similarity measure

type class-attribute instance-attribute

type = 'BhattacharyyaCoefficientSimilarity'

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 Bhattacharyya coefficient between two probability distributions.

Parameters

x : ComparableType First probability distribution (list, array, or dict) y : ComparableType Second probability distribution (list, array, or dict)

Returns

float Bhattacharyya coefficient between x and y (range [0,1])

Raises

ValueError If the distributions have incompatible dimensions or are not normalized TypeError If the input types are not supported

Source code in swarmauri_standard/similarities/BhattacharyyaCoefficientSimilarity.py

def similarity(self, x: ComparableType, y: ComparableType) -> float:
    """
    Calculate the Bhattacharyya coefficient between two probability distributions.

    Parameters
    ----------
    x : ComparableType
        First probability distribution (list, array, or dict)
    y : ComparableType
        Second probability distribution (list, array, or dict)

    Returns
    -------
    float
        Bhattacharyya coefficient between x and y (range [0,1])

    Raises
    ------
    ValueError
        If the distributions have incompatible dimensions or are not normalized
    TypeError
        If the input types are not supported
    """
    try:
        # Convert inputs to numpy arrays if they are lists
        if isinstance(x, dict) and isinstance(y, dict):
            # For dictionary representations of distributions
            # Ensure both dictionaries have the same keys
            all_keys = set(x.keys()).union(set(y.keys()))
            p = np.array([x.get(k, 0.0) for k in all_keys])
            q = np.array([y.get(k, 0.0) for k in all_keys])
        else:
            # For list/array representations
            p = np.array(x, dtype=float)
            q = np.array(y, dtype=float)

        # Check if distributions have the same dimensions
        if p.shape != q.shape:
            raise ValueError(
                f"Distributions must have the same dimensions: {p.shape} != {q.shape}"
            )

        # Check for negative probabilities
        if np.any(p < 0) or np.any(q < 0):
            raise ValueError("Probability values must be non-negative")

        # Check if distributions are normalized (sum to 1)
        if not np.isclose(np.sum(p), 1.0, rtol=1e-5):
            raise ValueError(
                f"First distribution is not normalized: sum = {np.sum(p)}"
            )
        if not np.isclose(np.sum(q), 1.0, rtol=1e-5):
            raise ValueError(
                f"Second distribution is not normalized: sum = {np.sum(q)}"
            )

        # Calculate Bhattacharyya coefficient
        # BC(p,q) = ∑ √(p_i * q_i)
        bc = np.sum(np.sqrt(p * q))

        return float(bc)

    except (TypeError, ValueError) as e:
        logger.error(f"Error calculating Bhattacharyya coefficient: {str(e)}")
        raise

similarities

similarities(x, ys)

Calculate Bhattacharyya coefficients between one distribution and multiple others.

Parameters

x : ComparableType Reference probability distribution ys : Sequence[ComparableType] Sequence of probability distributions to compare against the reference

Returns

List[float] List of Bhattacharyya coefficients between x and each element in ys

Raises

ValueError If any distributions have incompatible dimensions or are not normalized TypeError If any input types are not supported

Source code in swarmauri_standard/similarities/BhattacharyyaCoefficientSimilarity.py

def similarities(
    self, x: ComparableType, ys: Sequence[ComparableType]
) -> List[float]:
    """
    Calculate Bhattacharyya coefficients between one distribution and multiple others.

    Parameters
    ----------
    x : ComparableType
        Reference probability distribution
    ys : Sequence[ComparableType]
        Sequence of probability distributions to compare against the reference

    Returns
    -------
    List[float]
        List of Bhattacharyya coefficients between x and each element in ys

    Raises
    ------
    ValueError
        If any distributions have incompatible dimensions or are not normalized
    TypeError
        If any input types are not supported
    """
    try:
        # Convert reference distribution to numpy array
        if isinstance(x, dict):
            # For dictionary representations, we'll handle this in the loop
            p_dict = x
            p_array = None
        else:
            p_dict = None
            p_array = np.array(x, dtype=float)

            # Check if reference distribution is normalized
            if not np.isclose(np.sum(p_array), 1.0, rtol=1e-5):
                raise ValueError(
                    f"Reference distribution is not normalized: sum = {np.sum(p_array)}"
                )

        results = []
        for i, y in enumerate(ys):
            try:
                if p_dict is not None and isinstance(y, dict):
                    # Dictionary case - handle in similarity method
                    sim = self.similarity(p_dict, y)
                elif p_array is not None:
                    # Array case - optimize by reusing the converted reference
                    q = np.array(y, dtype=float)

                    # Check if distribution is normalized
                    if not np.isclose(np.sum(q), 1.0, rtol=1e-5):
                        raise ValueError(
                            f"Distribution at index {i} is not normalized: sum = {np.sum(q)}"
                        )

                    # Check dimensions
                    if p_array.shape != q.shape:
                        raise ValueError(
                            f"Distribution at index {i} has incompatible dimensions: {p_array.shape} != {q.shape}"
                        )

                    # Calculate Bhattacharyya coefficient
                    sim = float(np.sum(np.sqrt(p_array * q)))
                else:
                    # Fall back to standard method
                    sim = self.similarity(x, y)

                results.append(sim)
            except Exception as e:
                logger.error(f"Error calculating similarity for item {i}: {str(e)}")
                raise

        return results

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

dissimilarity

dissimilarity(x, y)

Calculate the Bhattacharyya distance between two probability distributions.

The Bhattacharyya distance is defined as: -ln(BC(p,q)) For normalized probability distributions, this is equivalent to: 1 - BC(p,q)

Parameters

x : ComparableType First probability distribution y : ComparableType Second probability distribution

Returns

float Bhattacharyya-based dissimilarity between x and y (range [0,1])

Raises

ValueError If the distributions have incompatible dimensions or are not normalized TypeError If the input types are not supported

Source code in swarmauri_standard/similarities/BhattacharyyaCoefficientSimilarity.py

def dissimilarity(self, x: ComparableType, y: ComparableType) -> float:
    """
    Calculate the Bhattacharyya distance between two probability distributions.

    The Bhattacharyya distance is defined as: -ln(BC(p,q))
    For normalized probability distributions, this is equivalent to: 1 - BC(p,q)

    Parameters
    ----------
    x : ComparableType
        First probability distribution
    y : ComparableType
        Second probability distribution

    Returns
    -------
    float
        Bhattacharyya-based dissimilarity between x and y (range [0,1])

    Raises
    ------
    ValueError
        If the distributions have incompatible dimensions or are not normalized
    TypeError
        If the input types are not supported
    """
    try:
        # Get the Bhattacharyya coefficient
        bc = self.similarity(x, y)

        # Convert to a dissimilarity measure in [0,1]
        # For probability distributions, 1-BC is a valid dissimilarity measure
        return 1.0 - bc

    except Exception as e:
        logger.error(f"Error calculating Bhattacharyya dissimilarity: {str(e)}")
        raise

check_bounded

check_bounded()

Check if the similarity measure is bounded.

The Bhattacharyya coefficient is always bounded between 0 and 1.

Returns

bool True, as the Bhattacharyya coefficient is bounded

Source code in swarmauri_standard/similarities/BhattacharyyaCoefficientSimilarity.py

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

    The Bhattacharyya coefficient is always bounded between 0 and 1.

    Returns
    -------
    bool
        True, as the Bhattacharyya coefficient is bounded
    """
    return True

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

check_reflexivity

check_reflexivity(x)

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

Parameters

x : ComparableType Object to check reflexivity with

Returns

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

Raises

TypeError If the input type is not supported

Source code in swarmauri_base/similarities/SimilarityBase.py

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

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

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

    Raises
    ------
    TypeError
        If the input type is not supported
    """
    try:
        # A similarity measure is reflexive if s(x,x) = 1
        similarity_value = self.similarity(x, x)
        # Use approximate equality to handle floating-point precision issues
        return abs(similarity_value - 1.0) < 1e-10
    except Exception as e:
        logger.error(f"Error checking reflexivity: {str(e)}")
        raise

check_symmetry

check_symmetry(x, y)

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

Parameters

x : ComparableType First object to compare y : ComparableType Second object to compare

Returns

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

Raises

ValueError If the objects are incomparable or have incompatible dimensions TypeError If the input types are not supported

Source code in swarmauri_base/similarities/SimilarityBase.py

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

    Parameters
    ----------
    x : ComparableType
        First object to compare
    y : ComparableType
        Second object to compare

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

    Raises
    ------
    ValueError
        If the objects are incomparable or have incompatible dimensions
    TypeError
        If the input types are not supported
    """
    try:
        # A similarity measure is symmetric if s(x,y) = s(y,x)
        similarity_xy = self.similarity(x, y)
        similarity_yx = self.similarity(y, x)
        # Use approximate equality to handle floating-point precision issues
        return abs(similarity_xy - similarity_yx) < 1e-10
    except Exception as e:
        logger.error(f"Error checking symmetry: {str(e)}")
        raise

check_identity_of_discernibles

check_identity_of_discernibles(x, y)

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

Parameters

x : ComparableType First object to compare y : ComparableType Second object to compare

Returns

bool True if the identity of discernibles property holds, False otherwise

Raises

ValueError If the objects are incomparable or have incompatible dimensions TypeError If the input types are not supported

Source code in swarmauri_base/similarities/SimilarityBase.py

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

    Parameters
    ----------
    x : ComparableType
        First object to compare
    y : ComparableType
        Second object to compare

    Returns
    -------
    bool
        True if the identity of discernibles property holds, False otherwise

    Raises
    ------
    ValueError
        If the objects are incomparable or have incompatible dimensions
    TypeError
        If the input types are not supported
    """
    try:
        similarity_value = self.similarity(x, y)
        # If x and y are identical (by value, not necessarily by reference)
        if str(x) == str(y):  # Simple string comparison as a basic equality check
            # Then the similarity should be 1
            return abs(similarity_value - 1.0) < 1e-10
        else:
            # If x and y are different, the similarity should be less than 1
            return similarity_value < 1.0 - 1e-10
    except Exception as e:
        logger.error(f"Error checking identity of discernibles: {str(e)}")
        raise