WordDocEmbedder

Bases: BaseEmbedder

Combine a document- and word-level embedder

Source code in bertopic\backend\_word_doc.py

class WordDocEmbedder(BaseEmbedder):
    """ Combine a document- and word-level embedder
    """
    def __init__(self,
                 embedding_model,
                 word_embedding_model):
        super().__init__()

        self.embedding_model = select_backend(embedding_model)
        self.word_embedding_model = select_backend(word_embedding_model)

    def embed_words(self,
                    words: List[str],
                    verbose: bool = False) -> np.ndarray:
        """ Embed a list of n words into an n-dimensional
        matrix of embeddings

        Arguments:
            words: A list of words to be embedded
            verbose: Controls the verbosity of the process

        Returns:
            Word embeddings with shape (n, m) with `n` words
            that each have an embeddings size of `m`

        """
        return self.word_embedding_model.embed(words, verbose)

    def embed_documents(self,
                        document: List[str],
                        verbose: bool = False) -> np.ndarray:
        """ Embed a list of n words into an n-dimensional
        matrix of embeddings

        Arguments:
            document: A list of documents to be embedded
            verbose: Controls the verbosity of the process

        Returns:
            Document embeddings with shape (n, m) with `n` documents
            that each have an embeddings size of `m`
        """
        return self.embedding_model.embed(document, verbose)

embed_documents(document, verbose=False)

Embed a list of n words into an n-dimensional matrix of embeddings

Parameters:

Name	Type	Description	Default
document	List[str]	A list of documents to be embedded	required
verbose	bool	Controls the verbosity of the process	False

Returns:

Type	Description
ndarray	Document embeddings with shape (n, m) with n documents
ndarray	that each have an embeddings size of m

Source code in bertopic\backend\_word_doc.py

def embed_documents(self,
                    document: List[str],
                    verbose: bool = False) -> np.ndarray:
    """ Embed a list of n words into an n-dimensional
    matrix of embeddings

    Arguments:
        document: A list of documents to be embedded
        verbose: Controls the verbosity of the process

    Returns:
        Document embeddings with shape (n, m) with `n` documents
        that each have an embeddings size of `m`
    """
    return self.embedding_model.embed(document, verbose)

embed_words(words, verbose=False)

Embed a list of n words into an n-dimensional matrix of embeddings

Parameters:

Name	Type	Description	Default
words	List[str]	A list of words to be embedded	required
verbose	bool	Controls the verbosity of the process	False

Returns:

Type	Description
ndarray	Word embeddings with shape (n, m) with n words
ndarray	that each have an embeddings size of m

Source code in bertopic\backend\_word_doc.py

def embed_words(self,
                words: List[str],
                verbose: bool = False) -> np.ndarray:
    """ Embed a list of n words into an n-dimensional
    matrix of embeddings

    Arguments:
        words: A list of words to be embedded
        verbose: Controls the verbosity of the process

    Returns:
        Word embeddings with shape (n, m) with `n` words
        that each have an embeddings size of `m`

    """
    return self.word_embedding_model.embed(words, verbose)