Function visualize_topics

bertopic/plotting/_topics.py:18–120

Visualize topics, their sizes, and their corresponding words. This visualization is highly inspired by LDAvis, a great visualization technique typically reserved for LDA. Arguments: topic_model: A fitted BERTopic instance. topics: A selection of topics to visualize

(
    topic_model,
    topics: List[int] | None = None,
    top_n_topics: int | None = None,
    use_ctfidf: bool = False,
    custom_labels: Union[bool, str] = False,
    title: str = "<b>Intertopic Distance Map</b>",
    width: int = 650,
    height: int = 650,
)

def visualize_topics(
    topic_model,
    topics: List[int] | None = None,
    top_n_topics: int | None = None,
    use_ctfidf: bool = False,
    custom_labels: Union[bool, str] = False,
    title: str = "<b>Intertopic Distance Map</b>",
    width: int = 650,
    height: int = 650,
) -> go.Figure:
    """Visualize topics, their sizes, and their corresponding words.

    This visualization is highly inspired by LDAvis, a great visualization
    technique typically reserved for LDA.

    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
        use_ctfidf: Whether to use c-TF-IDF representations instead of the embeddings from the embedding model.
        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.

    Examples:
    To visualize the topics simply run:

    ```python
    topic_model.visualize_topics()
    ```

    Or if you want to save the resulting figure:

    ```python
    fig = topic_model.visualize_topics()
    fig.write_html("path/to/file.html")
    ```
    <iframe src="../../getting_started/visualization/viz.html"
    style="width:1000px; height: 680px; border: 0px;""></iframe>
    """
    # 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, :]
    if topics is not None:
        topics = list(topics)
    elif top_n_topics is not None:
        topics = sorted(freq_df.Topic.to_list()[:top_n_topics])
    else:
        topics = sorted(freq_df.Topic.to_list())

    # Extract topic words and their frequencies
    topic_list = sorted(topics)
    frequencies = [topic_model.topic_sizes_[topic] for topic in topic_list]
    if isinstance(custom_labels, str):
        words = [[[str(topic), None]] + topic_model.topic_aspects_[custom_labels][topic] for topic in topic_list]