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
width	int	The width of the figure.	650
height	int	The height of the figure.	650

Usage:

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,
                     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
        width: The width of the figure.
        height: The height of the figure.

    Usage:

    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]
    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 = topic_model.c_tf_idf.toarray()[indices]
    embeddings = MinMaxScaler().fit_transform(embeddings)
    embeddings = UMAP(n_neighbors=2, n_components=2, metric='hellinger').fit_transform(embeddings)

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