# chronowords
Detect semantic shifts over time in word embeddings. Train small PPMI-based language models, create topic models using NMF, and analyze semantic changes using Procrustes alignment.
## Features
- Memory-efficient word embedding training using Count-Min Sketch
- Topic modeling with Non-negative Matrix Factorization
- Temporal alignment of word embeddings using Procrustes analysis
- Cython-optimized PPMI matrix computation
## Installation
```bash
pip install chronowords
```
## Quick Start
```python
from chronowords.algebra import SVDAlgebra
from chronowords.topics import TopicModel
# Train word embeddings
model = SVDAlgebra(n_components=300)
model.train(your_corpus_iterator)
# Find similar words
similar = model.most_similar('computer')
for word in similar:
print(f"{word.word}: {word.similarity:.3f}")
# Create topic model
topic_model = TopicModel(n_topics=10)
topic_model.fit(ppmi_matrix, vocabulary)
```
## Documentation
Full documentation available at ReadTheDocs.
## Requirements
Python ≥ 3.10
NumPy
SciPy
scikit-learn
Cython
## Contributing
Pull requests welcome. For major changes, open an issue first.
## License
MIT
Raw data
{
"_id": null,
"home_page": "https://github.com/crow-intelligence/chronowords",
"name": "chronowords",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.13,>=3.10",
"maintainer_email": null,
"keywords": "nlp, embeddings, semantic-change, topic-modeling",
"author": "Orsolya Putz",
"author_email": "orsolya.putz@crowintelligence.org>,Zoltan Varju <zoltan.varju@crowintelligence.org",
"download_url": "https://files.pythonhosted.org/packages/bb/ba/e805cd1fba12ce2644a5414b1918f2ecf59d91cf6affd1c8b829e3c68e73/chronowords-0.1.1.tar.gz",
"platform": null,
"description": "# chronowords\n\nDetect semantic shifts over time in word embeddings. Train small PPMI-based language models, create topic models using NMF, and analyze semantic changes using Procrustes alignment.\n\n## Features\n\n- Memory-efficient word embedding training using Count-Min Sketch\n- Topic modeling with Non-negative Matrix Factorization\n- Temporal alignment of word embeddings using Procrustes analysis\n- Cython-optimized PPMI matrix computation\n\n## Installation\n\n```bash\npip install chronowords\n```\n\n## Quick Start\n```python\nfrom chronowords.algebra import SVDAlgebra\nfrom chronowords.topics import TopicModel\n\n# Train word embeddings\nmodel = SVDAlgebra(n_components=300)\nmodel.train(your_corpus_iterator)\n\n# Find similar words\nsimilar = model.most_similar('computer')\nfor word in similar:\n print(f\"{word.word}: {word.similarity:.3f}\")\n\n# Create topic model\ntopic_model = TopicModel(n_topics=10)\ntopic_model.fit(ppmi_matrix, vocabulary)\n```\n\n## Documentation\nFull documentation available at ReadTheDocs.\n\n## Requirements\n\nPython \u2265 3.10\nNumPy\nSciPy\nscikit-learn\nCython\n\n## Contributing\nPull requests welcome. For major changes, open an issue first.\n\n## License\nMIT\n",
"bugtrack_url": null,
"license": "MIT",
"summary": null,
"version": "0.1.1",
"project_urls": {
"Documentation": "https://chronowords.readthedocs.io",
"Homepage": "https://github.com/crow-intelligence/chronowords",
"Repository": "https://github.com/crow-intelligence/chronowords"
},
"split_keywords": [
"nlp",
" embeddings",
" semantic-change",
" topic-modeling"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "9962e461adf89e9f42786dc19432f91a56de3184362d9939cabb83ad3c947e2d",
"md5": "7cd18fa2aa6c42660b8922f8df3cdfbc",
"sha256": "b0c62531e282883981f5d1c3a88e8bc36247ad2d3f26b2b452a37507607c4ec7"
},
"downloads": -1,
"filename": "chronowords-0.1.1-cp312-cp312-manylinux_2_39_x86_64.whl",
"has_sig": false,
"md5_digest": "7cd18fa2aa6c42660b8922f8df3cdfbc",
"packagetype": "bdist_wheel",
"python_version": "cp312",
"requires_python": "<3.13,>=3.10",
"size": 16974,
"upload_time": "2025-02-12T14:01:43",
"upload_time_iso_8601": "2025-02-12T14:01:43.366859Z",
"url": "https://files.pythonhosted.org/packages/99/62/e461adf89e9f42786dc19432f91a56de3184362d9939cabb83ad3c947e2d/chronowords-0.1.1-cp312-cp312-manylinux_2_39_x86_64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "bbbae805cd1fba12ce2644a5414b1918f2ecf59d91cf6affd1c8b829e3c68e73",
"md5": "5051f030b258ebdf1758b6dc681f20c0",
"sha256": "b40b07b197b809cb7b3aca7066907a7b5a23019738c45e9c3522b321710f0b16"
},
"downloads": -1,
"filename": "chronowords-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "5051f030b258ebdf1758b6dc681f20c0",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.13,>=3.10",
"size": 15440,
"upload_time": "2025-02-12T14:01:45",
"upload_time_iso_8601": "2025-02-12T14:01:45.203316Z",
"url": "https://files.pythonhosted.org/packages/bb/ba/e805cd1fba12ce2644a5414b1918f2ecf59d91cf6affd1c8b829e3c68e73/chronowords-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-12 14:01:45",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "crow-intelligence",
"github_project": "chronowords",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "chronowords"
}
JSON
