Method merge_topics

bertopic/_bertopic.py:2101–2175

Arguments: docs: The documents you used when calling either `fit` or `fit_transform` topics_to_merge: Either a list of topics or a list of list of topics to merge. For example: [1, 2, 3] will merge topics 1, 2 and 3

(
        self,
        docs: List[str],
        topics_to_merge: List[Union[Iterable[int], int]],
        images: List[str] | None = None,
    )

        return topic_labels

    def merge_topics(
        self,
        docs: List[str],
        topics_to_merge: List[Union[Iterable[int], int]],
        images: List[str] | None = None,
    ) -> None:
        """Arguments:
            docs: The documents you used when calling either `fit` or `fit_transform`
            topics_to_merge: Either a list of topics or a list of list of topics
                             to merge. For example:
                                [1, 2, 3] will merge topics 1, 2 and 3
                                [[1, 2], [3, 4]] will merge topics 1 and 2, and
                                separately merge topics 3 and 4.
            images: A list of paths to the images used when calling either
                    `fit` or `fit_transform`.

        Examples:
        If you want to merge topics 1, 2, and 3:

        ```python
        topics_to_merge = [1, 2, 3]
        topic_model.merge_topics(docs, topics_to_merge)
        ```

        or if you want to merge topics 1 and 2, and separately
        merge topics 3 and 4:

        ```python
        topics_to_merge = [[1, 2],
                            [3, 4]]
        topic_model.merge_topics(docs, topics_to_merge)
        ```
        """
        check_is_fitted(self)
        check_documents_type(docs)
        documents = pd.DataFrame(
            {
                "Document": docs,
                "Topic": self.topics_,
                "Image": images,
                "ID": range(len(docs)),
            }
        )

        mapping = {topic: topic for topic in set(self.topics_)}
        if isinstance(topics_to_merge[0], int):
            for topic in sorted(topics_to_merge):
                mapping[topic] = topics_to_merge[0]
        elif isinstance(topics_to_merge[0], Iterable):
            for topic_group in sorted(topics_to_merge):
                for topic in topic_group:
                    mapping[topic] = topic_group[0]
        else:
            raise ValueError("Make sure that `topics_to_merge` is eithera list of topics or a list of list of topics.")

        # Track mappings and sizes of topics for merging topic embeddings
        mappings = defaultdict(list)
        for key, val in sorted(mapping.items()):