Topics

Visualize topics, their sizes, and their corresponding words.

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

Parameters:

Name	Type	Description	Default
topic_model		A fitted BERTopic instance.	required
topics	List[int]	A selection of topics to visualize	None
top_n_topics	int	Only select the top n most frequent topics	None
use_ctfidf	bool	Whether to use c-TF-IDF representations instead of the embeddings from the embedding model.	False
custom_labels	Union[bool, str]	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".	False
title	str	Title of the plot.	'<b>Intertopic Distance Map</b>'
width	int	The width of the figure.	650
height	int	The height of the figure.	650

Examples:

To visualize the topics simply run:

topic_model.visualize_topics()

Or if you want to save the resulting figure:

fig = topic_model.visualize_topics()
fig.write_html("path/to/file.html")

Source code in bertopic\plotting\_topics.py

def visualize_topics(
    topic_model,
    topics: List[int] = None,
    top_n_topics: int = 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]
        words = ["_".join([label[0] for label in labels[:4]]) for labels in words]
        words = [label if len(label) < 30 else label[:27] + "..." for label in words]
    elif custom_labels and topic_model.custom_labels_ is not None:
        words = [topic_model.custom_labels_[topic + topic_model._outliers] for topic in topic_list]
    else:
        words = [" | ".join([word[0] for word in topic_model.get_topic(topic)[:5]]) for topic in topic_list]

    # Embed c-TF-IDF into 2D
    all_topics = sorted(list(topic_model.get_topics().keys()))
    indices = np.array([all_topics.index(topic) for topic in topics])

    embeddings, c_tfidf_used = select_topic_representation(
        topic_model.c_tf_idf_,
        topic_model.topic_embeddings_,
        use_ctfidf=use_ctfidf,
        output_ndarray=True,
    )
    embeddings = embeddings[indices]

    if c_tfidf_used:
        embeddings = MinMaxScaler().fit_transform(embeddings)
        embeddings = UMAP(n_neighbors=2, n_components=2, metric="hellinger", random_state=42).fit_transform(embeddings)
    else:
        embeddings = UMAP(n_neighbors=2, n_components=2, metric="cosine", random_state=42).fit_transform(embeddings)

    # Visualize with plotly
    df = pd.DataFrame(
        {
            "x": embeddings[:, 0],
            "y": embeddings[:, 1],
            "Topic": topic_list,
            "Words": words,
            "Size": frequencies,
        }
    )
    return _plotly_topic_visualization(df, topic_list, title, width, height)