fastopic 0.0.4

FASTopic

FASTopic

FASTopic is a fast, adaptive, stable, and transferable topic model, different from the previous conventional (LDA), VAE-based (ProLDA, ETM), or clustering-based (Top2Vec, BERTopic) methods. It leverages optimal transport between the document, topic, and word embeddings from pretrained Transformers to model topics and topic distributions of documents.

Check our paper: FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm

• FASTopic
  • Tutorials
  • Installation
  • Quick Start
  • Usage
    • Try FASTopic on your dataset
    • Topic info
    • Topic hierarchy
    • Topic weights
    • Topic activity over time
  • APIs
    • Common
    • Visualization
  • Q&A
  • Contact
  • Citation

Tutorials

Method	API
A complete tutorial on FASTopic.
FASTopic with other languages.

Installation

Install FASTopic with pip:

    pip install fastopic

Otherwise, install FASTopic from the source:

    pip install git+https://github.com/bobxwu/FASTopic.git

Quick Start

Discover topics from 20newsgroups with the topic number as 50.

    from fastopic import FASTopic
    from sklearn.datasets import fetch_20newsgroups
    from topmost.preprocessing import Preprocessing

    docs = fetch_20newsgroups(subset='all',  remove=('headers', 'footers', 'quotes'))['data']

    preprocessing = Preprocessing(vocab_size=10000, stopwords='English')

    model = FASTopic(50, preprocessing)
    topic_top_words, doc_topic_dist = model.fit_transform(docs)

topic_top_words is a list containing the top words of discovered topics. doc_topic_dist is the topic distributions of documents (doc-topic distributions), a numpy array with shape $N \times K$ (number of documents $N$ and number of topics $K$).

Usage

Try FASTopic on your dataset

    from fastopic import FASTopic
    from topmost.preprocessing import Preprocessing

    # Prepare your dataset.
    docs = [
        'doc 1',
        'doc 2', # ...
    ]

    # Preprocess the dataset. This step tokenizes docs, removes stopwords, and sets max vocabulary size, etc.
    # Pass your tokenizer as:
    #   preprocessing = Preprocessing(vocab_size=your_vocab_size, tokenizer=your_tokenizer, stopwords=your_stopwords_set)
    preprocessing = Preprocessing(stopwords='English')

    model = FASTopic(50, preprocessing)
    topic_top_words, doc_topic_dist = model.fit_transform(docs)

Topic info

We can get the top words and their probabilities of a topic.

    model.get_topic(topic_idx=36)

    (('impeachment', 0.008047104),
    ('mueller', 0.0075936727),
    ('trump', 0.0066773472),
    ('committee', 0.0057785935),
    ('inquiry', 0.005647915))

We can visualize these topic info.

    fig = model.visualize_topic(top_n=5)
    fig.show()

Topic hierarchy

We use the learned topic embeddings and scipy.cluster.hierarchy to build a hierarchy of discovered topics.

    fig = model.visualize_topic_hierarchy()
    fig.show()

Topic weights

We plot the weights of topics in the given dataset.

    fig = model.visualize_topic_weights(top_n=20, height=500)
    fig.show()

Topic activity over time

Topic activity refers to the weight of a topic at a time slice. We additionally input the time slices of documents, time_slices to compute and plot topic activity over time.

    act = model.topic_activity_over_time(time_slices)
    fig = model.visualize_topic_activity(top_n=6, topic_activity=act, time_slices=time_slices)
    fig.show()

APIs

We summarize the frequently used APIs of FASTopic here. It's easier for you to look up.

Common

Method	API
Fit the model	.fit(docs)
Fit the model and predict documents	.fit_transform(docs)
Predict new documents	.transform(new_docs)
Get topic-word distribution matrix	.get_beta()
Get top words of all topics	.get_top_words()
Get topic weights over the input dataset	.get_topic_weights()
Get topic activity over time	.topic_activity_over_time(time_slices)
Save model	.save("./model.zip")
Load model	.load("./model.zip")

Visualization

Method	API
Visualize topics	.visualize_topic(top_n=5) or .visualize_topic(topic_idx=[1, 2, 3])
Visualize topic weights	.visualize_topic_weights(top_n=5) or .visualize_topic_weights(topic_idx=[1, 2, 3])
Visualize topic hierarchy	.visualize_topic_hierarchy()
Visualize topic activity	.visualize_topic_activity(top_n=5, topic_activity=topic_activity, time_slices=time_slices)

Q&A

1. Meet the out of memory error. My GPU memory is not enough due to large datasets. What should I do?

   You can try to set save_memory=True and batch_size in FASTopic. batch_size should not be too small, otherwise it may damage performance.

       model = FASTopic(50, save_memory=True, batch_size=2000)
   

   Or you can run FASTopic on the CPU as

       model = FASTopic(50, device='cpu')
   

2. Can I try FASTopic with the languages other than English?

   Yes! You can pass a multilingual document embedding model, like paraphrase-multilingual-MiniLM-L12-v2, and the tokenizer and the stop words for your language, like pipelines of spaCy.

   Please refer to the tutorial in Colab.

Contact

• We welcome your contributions to this project. Please feel free to submit pull requests.
• If you encounter any issues, please either directly contact Xiaobao Wu ([e-mail]) or leave an issue in the GitHub repo.

Citation

If you want to use FASTopic, please cite our paper as

@article{wu2024fastopic,
    title={FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm},
    author={Wu, Xiaobao and Nguyen, Thong and Zhang, Delvin Ce and Wang, William Yang and Luu, Anh Tuan},
    journal={arXiv preprint arXiv:2405.17978},
    year={2024}
}