OCTIS
auto-sklearn
Our great sponsors
| OCTIS | auto-sklearn | |
|---|---|---|
| 7 | 3 | |
| 681 | 7,403 | |
| 1.9% | 0.8% | |
| 6.0 | 1.8 | |
| 4 months ago | 4 months ago | |
| Python | Python | |
| MIT License | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
OCTIS
-
Interpretation of topic modeling results between LDA and BERTopic
OCTIS
-
(NLP) Best practices for topic modeling and generating interesting topics?
My team and I have recently released a python library called OCTIS (https://github.com/mind-Lab/octis) that allows you to automatically optimize the hyperparameters of a topic model according to a given evaluation metric (not log-likelihood). I guess, in your case, you might be interested in topic coherence. So you will get good quality topics with a low effort on the choice of the hyperparameters. Also, we included some state-of-the-art topic models, e.g. contextualized topic models (https://github.com/MilaNLProc/contextualized-topic-models).
-
I am working on a topic modelling paper and I need your help
I recently released a topic modeling library that also includes different evaluation measures. If you are interested, I leave here the link: https://github.com/mind-Lab/octis
-
Latest trends in topic modelling?
Silvia Terragni (a coauthor on the above) also brought a topic modelling library OCTIS which was exhibited as a demo paper and aims to be the huggingface transformers of topic modelling - it includes wrappers around the above model as well as and LDA and some baselines as well as some tools and frameworks for comparing them.
-
OCTIS a python framework to compare and optimize Topic Models
Link to the code Paper
- OCTIS, our new python framework to optimize and compare topic models has been accepted at EACL2021!
- [p] OCTIS: Optimizing and Comparing Topic models Is Simple. Our new python framework to compare and optimize topic models using Bayesian Optimization
auto-sklearn
-
Why not AutoML every tabular data?
Efficiency Ignoring the feature engineering aspects aside, a typical data scientist workflow involves trying out the different models. Some of the AutoML modules like H2O AutoML, AutoSklearn does this for you, and allow you to interpret your models. All these save so much time experimenting with the standard models.
- [R] Regularization is all you Need: Simple Neural Nets can Excel on Tabular Data
-
What free AutoML library do you recommend?
If you want a more stable AutoML library, i’ll suggest auto-sklearn which optimises performance of sklearn learning algorithms.
What are some alternatives?
BERTopic - Leveraging BERT and c-TF-IDF to create easily interpretable topics.
autogluon - Fast and Accurate ML in 3 Lines of Code
contextualized-topic-models - A python package to run contextualized topic modeling. CTMs combine contextualized embeddings (e.g., BERT) with topic models to get coherent topics. Published at EACL and ACL 2021.
Auto-PyTorch - Automatic architecture search and hyperparameter optimization for PyTorch
image-similarity-measures - :chart_with_upwards_trend: Implementation of eight evaluation metrics to access the similarity between two images. The eight metrics are as follows: RMSE, PSNR, SSIM, ISSM, FSIM, SRE, SAM, and UIQ.
tune-sklearn - A drop-in replacement for Scikit-Learn’s GridSearchCV / RandomizedSearchCV -- but with cutting edge hyperparameter tuning techniques.
SMAC3 - SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
syne-tune - Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
TopMost - A Topic Modeling System Toolkit
nni - An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.
pymarl2 - Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)