Method fit

bertopic/_bertopic.py:350–393

Fit the models on a collection of documents and generate topics. Arguments: documents: A list of documents to fit on embeddings: Pre-trained document embeddings. These can be used instead of the sentence-transformer model images: A

(
        self,
        documents: List[str],
        embeddings: np.ndarray = None,
        images: List[str] | None = None,
        y: Union[List[int], np.ndarray] = None,
    )

        return topic_labels

    def fit(
        self,
        documents: List[str],
        embeddings: np.ndarray = None,
        images: List[str] | None = None,
        y: Union[List[int], np.ndarray] = None,
    ):
        """Fit the models on a collection of documents and generate topics.

        Arguments:
            documents: A list of documents to fit on
            embeddings: Pre-trained document embeddings. These can be used
                        instead of the sentence-transformer model
            images: A list of paths to the images to fit on or the images themselves
            y: The target class for (semi)-supervised modeling. Use -1 if no class for a
               specific instance is specified.

        Examples:
        ```python
        from bertopic import BERTopic
        from sklearn.datasets import fetch_20newsgroups

        docs = fetch_20newsgroups(subset='all')['data']
        topic_model = BERTopic().fit(docs)
        ```

        If you want to use your own embeddings, use it as follows:

        ```python
        from bertopic import BERTopic
        from sklearn.datasets import fetch_20newsgroups
        from sentence_transformers import SentenceTransformer

        # Create embeddings
        docs = fetch_20newsgroups(subset='all')['data']
        sentence_model = SentenceTransformer("all-MiniLM-L6-v2")
        embeddings = sentence_model.encode(docs, show_progress_bar=True)

        # Create topic model
        topic_model = BERTopic().fit(docs, embeddings)
        ```
        """
        self.fit_transform(documents=documents, embeddings=embeddings, y=y, images=images)
        return self

    def fit_transform(
        self,