Class swarmauri_embedding_nmf.NmfEmbedding.NmfEmbedding

swarmauri_embedding_nmf.NmfEmbedding.NmfEmbedding

NmfEmbedding(**kwargs)

Bases: EmbeddingBase

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def __init__(self, **kwargs):
    super().__init__(**kwargs)
    # Initialize TF-IDF Vectorizer
    self._tfidf_vectorizer = TfidfVectorizer()
    # Initialize NMF with the desired number of components
    self._model = NMF(n_components=self.n_components)

n_components class-attribute instance-attribute

n_components = 10

feature_names class-attribute instance-attribute

feature_names = []

type class-attribute instance-attribute

type = 'NmfEmbedding'

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=EMBEDDING.value, frozen=True)

version class-attribute instance-attribute

version = '0.1.0'

fit

fit(data)

Fit the NMF model to data.

PARAMETER	DESCRIPTION
data	The text data to fit. TYPE: Union[str, Any]

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def fit(self, data):
    """
    Fit the NMF model to data.

    Args:
        data (Union[str, Any]): The text data to fit.
    """
    # Transform data into TF-IDF matrix
    tfidf_matrix = self._tfidf_vectorizer.fit_transform(data)
    # Fit the NMF model
    self._model.fit(tfidf_matrix)
    # Store feature names
    self.feature_names = self._tfidf_vectorizer.get_feature_names_out()

transform

transform(data)

Transform new data into NMF feature space.

PARAMETER	DESCRIPTION
data	Text data to transform. TYPE: Union[str, Any]

RETURNS	DESCRIPTION
	List[IVector]: A list of vectors representing the transformed data.

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def transform(self, data):
    """
    Transform new data into NMF feature space.

    Args:
        data (Union[str, Any]): Text data to transform.

    Returns:
        List[IVector]: A list of vectors representing the transformed data.
    """
    # Transform data into TF-IDF matrix
    tfidf_matrix = self._tfidf_vectorizer.transform(data)
    # Transform TF-IDF matrix into NMF space
    nmf_features = self._model.transform(tfidf_matrix)

    # Wrap NMF features in SimpleVector instances and return
    return [Vector(value=features.tolist()) for features in nmf_features]

fit_transform

fit_transform(data)

Fit the model to data and then transform it.

PARAMETER	DESCRIPTION
data	The text data to fit and transform. TYPE: Union[str, Any]

RETURNS	DESCRIPTION
	List[IVector]: A list of vectors representing the fitted and transformed data.

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def fit_transform(self, data):
    """
    Fit the model to data and then transform it.

    Args:
        data (Union[str, Any]): The text data to fit and transform.

    Returns:
        List[IVector]: A list of vectors representing the fitted and transformed data.
    """
    self.fit(data)
    return self.transform(data)

infer_vector

infer_vector(data)

Convenience method for transforming a single data point.

PARAMETER	DESCRIPTION
data	Single text data to transform. TYPE: Union[str, Any]

RETURNS	DESCRIPTION
IVector	A vector representing the transformed single data point.

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def infer_vector(self, data):
    """
    Convenience method for transforming a single data point.

    Args:
        data (Union[str, Any]): Single text data to transform.

    Returns:
        IVector: A vector representing the transformed single data point.
    """
    return self.transform([data])[0]

extract_features

extract_features()

Extract the feature names from the TF-IDF vectorizer.

RETURNS	DESCRIPTION
	The feature names.

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def extract_features(self):
    """
    Extract the feature names from the TF-IDF vectorizer.

    Returns:
        The feature names.
    """
    return self.feature_names.tolist()

save_model

save_model(path)

Saves the NMF model and TF-IDF vectorizer using joblib.

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def save_model(self, path: str) -> None:
    """
    Saves the NMF model and TF-IDF vectorizer using joblib.
    """
    # It might be necessary to save both tfidf_vectorizer and model
    # Consider using a directory for 'path' or appended identifiers for each model file
    joblib.dump(self._tfidf_vectorizer, f"{path}_tfidf.joblib")
    joblib.dump(self._model, f"{path}_nmf.joblib")

load_model

load_model(path)

Loads the NMF model and TF-IDF vectorizer from paths using joblib.

Source code in swarmauri_embedding_nmf/NmfEmbedding.py

def load_model(self, path: str) -> None:
    """
    Loads the NMF model and TF-IDF vectorizer from paths using joblib.
    """
    self._tfidf_vectorizer = joblib.load(f"{path}_tfidf.joblib")
    self._model = joblib.load(f"{path}_nmf.joblib")
    # Dependending on your implementation, you might need to refresh the feature_names
    self.feature_names = self._tfidf_vectorizer.get_feature_names_out()

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