Method _extract_topics

bertopic/_bertopic.py:4177–4215

Extract topics from the clusters using a class-based TF-IDF. Arguments: documents: Dataframe with documents and their corresponding IDs embeddings: The document embeddings mappings: The mappings from topic to word verbose: Whether to log the p

(
        self,
        documents: pd.DataFrame,
        embeddings: np.ndarray = None,
        mappings=None,
        verbose: bool = False,
        fine_tune_representation: bool = True,
    )

        return y, embeddings

    def _extract_topics(
        self,
        documents: pd.DataFrame,
        embeddings: np.ndarray = None,
        mappings=None,
        verbose: bool = False,
        fine_tune_representation: bool = True,
    ):
        """Extract topics from the clusters using a class-based TF-IDF.

        Arguments:
            documents: Dataframe with documents and their corresponding IDs
            embeddings: The document embeddings
            mappings: The mappings from topic to word
            verbose: Whether to log the process of extracting topics
            fine_tune_representation: If True, the topic representation will be fine-tuned using representation models.
                                      If False, the topic representation will remain as the base c-TF-IDF representation.

        Returns:
            c_tf_idf: The resulting matrix giving a value (importance score) for each word per topic
        """
        if verbose:
            action = "Fine-tuning" if fine_tune_representation else "Extracting"
            method = "representation models" if fine_tune_representation else "c-TF-IDF for topic reduction"
            logger.info(f"Representation - {action} topics using {method}.")

        documents_per_topic = documents.groupby(["Topic"], as_index=False).agg({"Document": " ".join})
        self.c_tf_idf_, words = self._c_tf_idf(documents_per_topic)
        self.topic_representations_ = self._extract_words_per_topic(
            words,
            documents,
            fine_tune_representation=fine_tune_representation,
            calculate_aspects=fine_tune_representation,
            embeddings=embeddings,
        )
        self._create_topic_vectors(documents=documents, embeddings=embeddings, mappings=mappings)

        if verbose:
            logger.info("Representation - Completed \u2713")

    def _save_representative_docs(self, documents: pd.DataFrame):
        """Save the 3 most representative docs per topic.