Class swarmauri_standard.measurements.MissingnessMeasurement.MissingnessMeasurement

swarmauri_standard.measurements.MissingnessMeasurement.MissingnessMeasurement

Bases: MeasurementCalculateMixin, MeasurementBase

A metric that evaluates the percentage of missing values in a dataset.

Missingness is calculated as the ratio of missing values to total values, expressed as a percentage. This metric helps identify data quality issues and incompleteness in datasets.

ATTRIBUTE	DESCRIPTION
type	Type identifier for the metric TYPE: Literal['MissingnessMeasurement']
unit	Unit of measurement (percentage) TYPE: str
value	Stores the calculated missingness score TYPE: float
measurements	List of measurements to analyze TYPE: List[Optional[float]]

type class-attribute instance-attribute

type = 'MissingnessMeasurement'

unit class-attribute instance-attribute

unit = '%'

measurements class-attribute instance-attribute

measurements = []

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 = Field(default=MEASUREMENT.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

value class-attribute instance-attribute

value = None

calculate_missingness

calculate_missingness(data)

Calculates the missingness score for different data types.

PARAMETER	DESCRIPTION
data	Input data which can be a pandas DataFrame, List, or Dictionary TYPE: Union[DataFrame, List, Dict]

RETURNS	DESCRIPTION
float	Missingness score as a percentage (0-100) TYPE: float

RAISES	DESCRIPTION
ValueError	If an unsupported data type is provided

Source code in swarmauri_standard/measurements/MissingnessMeasurement.py

def calculate_missingness(self, data: Union[pd.DataFrame, List, Dict]) -> float:
    """
    Calculates the missingness score for different data types.

    Args:
        data: Input data which can be a pandas DataFrame, List, or Dictionary

    Returns:
        float: Missingness score as a percentage (0-100)

    Raises:
        ValueError: If an unsupported data type is provided
    """
    if isinstance(data, pd.DataFrame):
        total_values = data.size
        missing_values = data.isna().sum().sum()
    elif isinstance(data, list):
        total_values = len(data)
        missing_values = sum(1 for x in data if x is None)
    elif isinstance(data, dict):
        total_values = len(data)
        missing_values = sum(1 for v in data.values() if v is None)
    else:
        raise ValueError(
            "Unsupported data type. Please provide DataFrame, List, or Dict."
        )

    if total_values == 0:
        return 0.0

    return (missing_values / total_values) * 100

get_column_missingness

get_column_missingness(df)

Calculate missingness scores for individual columns in a DataFrame.

PARAMETER	DESCRIPTION
df	Input DataFrame TYPE: DataFrame

RETURNS	DESCRIPTION
Dict[str, float]	Dict[str, float]: Dictionary mapping column names to their missingness scores

RAISES	DESCRIPTION
ValueError	If input is not a pandas DataFrame

Source code in swarmauri_standard/measurements/MissingnessMeasurement.py

def get_column_missingness(self, df: pd.DataFrame) -> Dict[str, float]:
    """
    Calculate missingness scores for individual columns in a DataFrame.

    Args:
        df: Input DataFrame

    Returns:
        Dict[str, float]: Dictionary mapping column names to their missingness scores

    Raises:
        ValueError: If input is not a pandas DataFrame
    """
    if not isinstance(df, pd.DataFrame):
        raise ValueError("Input must be a pandas DataFrame")

    return {
        column: (df[column].isna().sum() / len(df) * 100) for column in df.columns
    }

calculate

calculate()

Calculate method required by MeasurementCalculateMixin. Uses the measurements list to calculate missingness.

RETURNS	DESCRIPTION
float	Missingness score as a percentage (0-100) TYPE: float

Source code in swarmauri_standard/measurements/MissingnessMeasurement.py

def calculate(self) -> float:
    """
    Calculate method required by MeasurementCalculateMixin.
    Uses the measurements list to calculate missingness.

    Returns:
        float: Missingness score as a percentage (0-100)
    """
    if not self.measurements:
        return 0.0

    total_values = len(self.measurements)
    missing_values = sum(1 for x in self.measurements if x is None)

    missingness = (missing_values / total_values) * 100
    self.update(missingness)
    return missingness

add_measurement

add_measurement(measurement)

Adds a measurement to the internal list of measurements.

PARAMETER	DESCRIPTION
measurement	A numerical value or None to be added to the list of measurements. TYPE: Optional[float]

Source code in swarmauri_standard/measurements/MissingnessMeasurement.py

def add_measurement(self, measurement: Optional[float]) -> None:
    """
    Adds a measurement to the internal list of measurements.

    Args:
        measurement (Optional[float]): A numerical value or None to be added to the list of measurements.
    """
    self.measurements.append(measurement)

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

update

update(value)

Update the measurement value based on new information. This should be used internally by the calculate method or other logic.

Source code in swarmauri_base/measurements/MeasurementCalculateMixin.py

def update(self, value) -> None:
    """
    Update the measurement value based on new information.
    This should be used internally by the `calculate` method or other logic.
    """
    self.value = value