Function visualize_heatmap

bertopic/plotting/_heatmap.py:11–136

Visualize a heatmap of the topic's similarity matrix. Based on the cosine similarity matrix between topic embeddings (either c-TF-IDF or the embeddings from the embedding model), a heatmap is created showing the similarity between topics. Arguments: topic_model: A fitted BERTop

(
    topic_model,
    topics: List[int] | None = None,
    top_n_topics: int | None = None,
    n_clusters: int | None = None,
    use_ctfidf: bool = False,
    custom_labels: Union[bool, str] = False,
    title: str = "<b>Similarity Matrix</b>",
    width: int = 800,
    height: int = 800,
)

def visualize_heatmap(
    topic_model,
    topics: List[int] | None = None,
    top_n_topics: int | None = None,
    n_clusters: int | None = None,
    use_ctfidf: bool = False,
    custom_labels: Union[bool, str] = False,
    title: str = "<b>Similarity Matrix</b>",
    width: int = 800,
    height: int = 800,
) -> go.Figure:
    """Visualize a heatmap of the topic&#x27;s similarity matrix.

    Based on the cosine similarity matrix between topic embeddings (either c-TF-IDF or the embeddings from the embedding
    model), a heatmap is created showing the similarity between topics.

    Arguments:
        topic_model: A fitted BERTopic instance.
        topics: A selection of topics to visualize.
        top_n_topics: Only select the top n most frequent topics.
        n_clusters: Create n clusters and order the similarity
                    matrix by those clusters.
        use_ctfidf: Whether to calculate distances between topics based on c-TF-IDF embeddings. If False, the embeddings
                    from the embedding model are used.
        custom_labels: If bool, whether to use custom topic labels that were defined using
                       `topic_model.set_topic_labels`.
                       If `str`, it uses labels from other aspects, e.g., "Aspect1".
        title: Title of the plot.
        width: The width of the figure.
        height: The height of the figure.

    Returns:
        fig: A plotly figure

    Examples:
    To visualize the similarity matrix of
    topics simply run:

    ```python
    topic_model.visualize_heatmap()
    ```

    Or if you want to save the resulting figure:

    ```python
    fig = topic_model.visualize_heatmap()
    fig.write_html("path/to/file.html")
    ```
    <iframe src="../../getting_started/visualization/heatmap.html"
    style="width:1000px; height: 720px; border: 0px;""></iframe>
    """
    embeddings = select_topic_representation(topic_model.c_tf_idf_, topic_model.topic_embeddings_, use_ctfidf)[0][
        topic_model._outliers :
    ]

    # Select topics based on top_n and topics args
    freq_df = topic_model.get_topic_freq()
    freq_df = freq_df.loc[freq_df.Topic != -1, :]