topmost

Topmost: A Topic Modeling System Tookit


Keywords
toolkit, topic, model, neural, library, neural-topic-modeling, neural-topic-models, nlp, nlp-library, nlp-machine-learning, package, topic-modeling, topic-modeling-analysis, topic-models
License
Apache-2.0
Install
pip install topmost==0.0.4

Documentation

topmost-logo TopMost

Github Stars Downloads PyPi Documentation Status License Contributors arXiv

TopMost provides complete lifecycles of topic modeling, including datasets, preprocessing, models, training, and evaluations. It covers the most popular topic modeling scenarios, like basic, dynamic, hierarchical, and cross-lingual topic modeling.

Check our survey paper on neural topic models, accepted to Artificial Intelligence Review: A Survey on Neural Topic Models: Methods, Applications, and Challenges.

If you want to use TopMost, please cite as
@article{wu2023topmost,
    title={Towards the TopMost: A Topic Modeling System Toolkit},
    author={Wu, Xiaobao and Pan, Fengjun and Luu, Anh Tuan},
    journal={arXiv preprint arXiv:2309.06908},
    year={2023}
}

@article{wu2023survey,
    title={A Survey on Neural Topic Models: Methods, Applications, and Challenges},
    author={Wu, Xiaobao and Nguyen, Thong and Luu, Anh Tuan},
    journal={Artificial Intelligence Review},
    url={https://doi.org/10.1007/s10462-023-10661-7},
    year={2024},
    publisher={Springer}
}

TopMost offers the following topic modeling scenarios with models, evaluation metrics, and datasets:

Scenario Model Evaluation Metric Datasets
Basic Topic Modeling
TC
TD
Clustering
Classification
20NG
IMDB
NeurIPS
ACL
NYT
Wikitext-103
Hierarchical
Topic Modeling
TC over levels
TD over levels
Clustering over levels
Classification over levels
20NG
IMDB
NeurIPS
ACL
NYT
Wikitext-103
Dynamic
Topic Modeling
TC over time slices
TD over time slices
Clustering
Classification
NeurIPS
ACL
NYT
Cross-lingual
Topic Modeling
TC (CNPMI)
TD over languages
Classification (Intra and Cross-lingual)

ECNews
Amazon
Review Rakuten

Install topmost with pip as

$ pip install topmost

We try FASTopic to get the top words of discovered topics, topic_top_words and the topic distributions of documents, doc_topic_dist. The preprocessing steps are configurable. See our documentations.

import topmost
from topmost.data import RawDataset
from topmost.preprocessing import Preprocessing
from sklearn.datasets import fetch_20newsgroups

docs = fetch_20newsgroups(subset='all',  remove=('headers', 'footers', 'quotes'))['data']
preprocessing = Preprocessing(vocab_size=10000, stopwords='English')

device = 'cuda' # or 'cpu'
dataset = RawDataset(docs, preprocessing, device=device)

trainer = topmost.trainers.FASTopicTrainer(dataset, verbose=True)
top_words, doc_topic_dist = trainer.train()

new_docs = [
    "This is a document about space, including words like space, satellite, launch, orbit.",
    "This is a document about Microsoft Windows, including words like windows, files, dos."
]

new_theta = trainer.test(new_docs)
print(new_theta.argmax(1))
import topmost
from topmost.data import download_dataset

download_dataset('20NG', cache_path='./datasets')
device = "cuda" # or "cpu"

# load a preprocessed dataset
dataset = topmost.data.BasicDataset("./datasets/20NG", device=device, read_labels=True)
# create a model
model = topmost.models.ProdLDA(dataset.vocab_size)
model = model.to(device)

# create a trainer
trainer = topmost.trainers.BasicTrainer(model, dataset)

# train the model
top_words, train_theta = trainer.train()
# evaluate topic diversity
TD = topmost.evaluations.compute_topic_diversity(top_words)

# get doc-topic distributions of testing samples
test_theta = trainer.test(dataset.test_data)
# evaluate clustering
clustering_results = topmost.evaluations.evaluate_clustering(test_theta, dataset.test_labels)
# evaluate classification
classification_results = topmost.evaluations.evaluate_classification(train_theta, test_theta, dataset.train_labels, dataset.test_labels)
import torch
from topmost.preprocessing import Preprocessing

new_docs = [
    "This is a new document about space, including words like space, satellite, launch, orbit.",
    "This is a new document about Microsoft Windows, including words like windows, files, dos."
]

preprocessing = Preprocessing()
new_parsed_docs, new_bow = preprocessing.parse(new_docs, vocab=dataset.vocab)
new_theta = trainer.test(torch.as_tensor(new_bow, device=device).float())

To install TopMost, run this command in the terminal:

$ pip install topmost

This is the preferred method to install TopMost, as it will always install the most recent stable release.

The sources for TopMost can be downloaded from the Github repository.

$ pip install git+https://github.com/bobxwu/TopMost.git

We provide tutorials for different usages:

Name Link
Quickstart Open In GitHub
How to preprocess datasets Open In GitHub
How to train and evaluate a basic topic model Open In GitHub
How to train and evaluate a hierarchical topic model Open In GitHub
How to train and evaluate a dynamic topic model Open In GitHub
How to train and evaluate a cross-lingual topic model Open In GitHub

This library includes some datasets for demonstration. If you are a dataset owner who wants to exclude your dataset from this library, please contact Xiaobao Wu.

xiaobao-figure Xiaobao Wu
fengjun-figure Fengjun Pan

Contributors

  • Icon by Flat-icons-com.
  • If you want to add any models to this package, we welcome your pull requests.
  • If you encounter any problem, please either directly contact Xiaobao Wu or leave an issue in the GitHub repo.