Method __init__

bertopic/_bertopic.py:145–315

BERTopic initialization. Arguments: language: The main language used in your documents. The default sentence-transformers model for "english" is `all-MiniLM-L6-v2`. For a full overview of supported languages see bertopic.backend.langua

(
        self,
        language: str = "english",
        top_n_words: int = 10,
        n_gram_range: Tuple[int, int] = (1, 1),
        min_topic_size: int = 10,
        nr_topics: Union[int, str] | None = None,
        low_memory: bool = False,
        calculate_probabilities: bool = False,
        seed_topic_list: List[List[str]] | None = None,
        zeroshot_topic_list: List[str] | None = None,
        zeroshot_min_similarity: float = 0.7,
        embedding_model=None,
        umap_model=None,
        hdbscan_model=None,
        vectorizer_model: CountVectorizer = None,
        ctfidf_model: TfidfTransformer = None,
        representation_model: BaseRepresentation = None,
        verbose: bool = False,
    )

    """

    def __init__(
        self,
        language: str = "english",
        top_n_words: int = 10,
        n_gram_range: Tuple[int, int] = (1, 1),
        min_topic_size: int = 10,
        nr_topics: Union[int, str] | None = None,
        low_memory: bool = False,
        calculate_probabilities: bool = False,
        seed_topic_list: List[List[str]] | None = None,
        zeroshot_topic_list: List[str] | None = None,
        zeroshot_min_similarity: float = 0.7,
        embedding_model=None,
        umap_model=None,
        hdbscan_model=None,
        vectorizer_model: CountVectorizer = None,
        ctfidf_model: TfidfTransformer = None,
        representation_model: BaseRepresentation = None,
        verbose: bool = False,
    ):
        """BERTopic initialization.

        Arguments:
            language: The main language used in your documents. The default sentence-transformers
                      model for "english" is `all-MiniLM-L6-v2`. For a full overview of
                      supported languages see bertopic.backend.languages. Select
                      "multilingual" to load in the `paraphrase-multilingual-MiniLM-L12-v2`
                      sentence-transformers model that supports 50+ languages.
                      NOTE: This is not used if `embedding_model` is used.
            top_n_words: The number of words per topic to extract. Setting this
                         too high can negatively impact topic embeddings as topics
                         are typically best represented by at most 10 words.
            n_gram_range: The n-gram range for the CountVectorizer.
                          Advised to keep high values between 1 and 3.
                          More would likely lead to memory issues.
                          NOTE: This param will not be used if you pass in your own
                          CountVectorizer.
            min_topic_size: The minimum size of the topic. Increasing this value will lead
                            to a lower number of clusters/topics and vice versa.
                            It is the same parameter as `min_cluster_size` in HDBSCAN.
                            NOTE: This param will not be used if you are using `hdbscan_model`.
            nr_topics: Specifying the number of topics will reduce the initial
                       number of topics to the value specified. This reduction can take
                       a while as each reduction in topics (-1) activates a c-TF-IDF
                       calculation. If this is set to None, no reduction is applied. Use
                       "auto" to automatically reduce topics using HDBSCAN.
                       NOTE: Controlling the number of topics is best done by adjusting
                       `min_topic_size` first before adjusting this parameter.
            low_memory: Sets UMAP low memory to True to make sure less memory is used.
                        NOTE: This is only used in UMAP. For example, if you use PCA instead of UMAP
                        this parameter will not be used.
            calculate_probabilities: Calculate the probabilities of all topics
                                     per document instead of the probability of the assigned
                                     topic per document. This could slow down the extraction
                                     of topics if you have many documents (> 100_000).
                                     NOTE: If false you cannot use the corresponding
                                     visualization method `visualize_probabilities`.
                                     NOTE: This is an approximation of topic probabilities