# 🇪🇹 Amharic NLP Toolkit
Amharic NLP Toolkit is a lightweight and easy-to-use Natural Language Processing (NLP) toolkit for Amharic.
It provides tools for Amharic text preprocessing, tokenization, normalization, stopword removal, stemming, and sentiment analysis.
Ideal for Amharic text processing, machine learning, deep learning,amharic large language model, AI projects, and other Ethiopian language applications
---
## ✨ Features
🔠 Amharic Text Tokenization – Split Amharic sentences into words or subwords
🧹 Text Normalization & Cleaning – Remove noise, fix unicode, handle punctuation
🛑 Stopword Removal – Filter out common Amharic stopwords
🌱 Stemming & Lemmatization – Reduce words to base form for NLP
😊 Sentiment Analysis – Simple positive/negative classification for Amharic text
📚 Supports Amharic NLP for Machine Learning, Deep Learning
---
## 📦 Installation
# Option 1: Install from GitHub (latest development version)
git clone https://github.com/yonasab12/amharicNLP.git
cd amharicNLP
pip install .
# Option 2: Install from PyPI (stable release)
pip install amharicNLP
Raw data
{
"_id": null,
"home_page": null,
"name": "amharicNLP",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "Amharic, NLP, Amharic NLP, Amharic preprocessing, Amharic tokenizer, Amharic stopwords, Amharic sentiment analysis, Amharic text processing, Ethiopian NLP, tokenizer, normalizer, sentiment analysis, amharicnlp, amharicprocessing, amharicnltk, tokinization, amharicstopword",
"author": null,
"author_email": "Yonas Abebe <abebeyonas88@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/29/dd/5cb9af43e28dc199e0ad173f8e4e25c189811a9da171b8979d9056cd1eb4/amharicnlp-0.8.0.tar.gz",
"platform": null,
"description": "# \ud83c\uddea\ud83c\uddf9 Amharic NLP Toolkit\n\nAmharic NLP Toolkit is a lightweight and easy-to-use Natural Language Processing (NLP) toolkit for Amharic.\nIt provides tools for Amharic text preprocessing, tokenization, normalization, stopword removal, stemming, and sentiment analysis.\nIdeal for Amharic text processing, machine learning, deep learning,amharic large language model, AI projects, and other Ethiopian language applications\n\n\n---\n\n## \u2728 Features\n\ud83d\udd20 Amharic Text Tokenization \u2013 Split Amharic sentences into words or subwords\n\n\ud83e\uddf9 Text Normalization & Cleaning \u2013 Remove noise, fix unicode, handle punctuation\n\n\ud83d\uded1 Stopword Removal \u2013 Filter out common Amharic stopwords\n\n\ud83c\udf31 Stemming & Lemmatization \u2013 Reduce words to base form for NLP\n\n\ud83d\ude0a Sentiment Analysis \u2013 Simple positive/negative classification for Amharic text\n \n\n\ud83d\udcda Supports Amharic NLP for Machine Learning, Deep Learning\n\n---\n\n## \ud83d\udce6 Installation\n\n# Option 1: Install from GitHub (latest development version)\ngit clone https://github.com/yonasab12/amharicNLP.git\ncd amharicNLP\npip install .\n\n# Option 2: Install from PyPI (stable release)\npip install amharicNLP\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "amharicNLP is a Python package for Amharic Natural Language Processing (NLP) and text preprocessing. ",
"version": "0.8.0",
"project_urls": {
"Homepage": "https://github.com/yonasab12/amharicNLP",
"Repository": "https://github.com/yonasab12/amharicNLP"
},
"split_keywords": [
"amharic",
" nlp",
" amharic nlp",
" amharic preprocessing",
" amharic tokenizer",
" amharic stopwords",
" amharic sentiment analysis",
" amharic text processing",
" ethiopian nlp",
" tokenizer",
" normalizer",
" sentiment analysis",
" amharicnlp",
" amharicprocessing",
" amharicnltk",
" tokinization",
" amharicstopword"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "29a28c3ec46809b1ffd68602f7d3296bc448ab16aa6e6e4439e42b46e48d11fb",
"md5": "809f7b3efac1cebe2cb3ba5aef41c61d",
"sha256": "51b54eb1339a7c18d6e90a599feb2b53e71998c43ce84f1d2b949d5d9051c9b6"
},
"downloads": -1,
"filename": "amharicnlp-0.8.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "809f7b3efac1cebe2cb3ba5aef41c61d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8",
"size": 118593,
"upload_time": "2025-08-23T10:34:56",
"upload_time_iso_8601": "2025-08-23T10:34:56.678607Z",
"url": "https://files.pythonhosted.org/packages/29/a2/8c3ec46809b1ffd68602f7d3296bc448ab16aa6e6e4439e42b46e48d11fb/amharicnlp-0.8.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "29dd5cb9af43e28dc199e0ad173f8e4e25c189811a9da171b8979d9056cd1eb4",
"md5": "9775f654261811e62130e0a036b7fe7c",
"sha256": "f9536a757a8c7499d0a492f2ae94dc2c3df247b41c7a5a23f663e283b101ad75"
},
"downloads": -1,
"filename": "amharicnlp-0.8.0.tar.gz",
"has_sig": false,
"md5_digest": "9775f654261811e62130e0a036b7fe7c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 113590,
"upload_time": "2025-08-23T10:34:58",
"upload_time_iso_8601": "2025-08-23T10:34:58.470816Z",
"url": "https://files.pythonhosted.org/packages/29/dd/5cb9af43e28dc199e0ad173f8e4e25c189811a9da171b8979d9056cd1eb4/amharicnlp-0.8.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-08-23 10:34:58",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "yonasab12",
"github_project": "amharicNLP",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "re",
"specs": []
},
{
"name": "pytest",
"specs": []
},
{
"name": "pytest-cov",
"specs": []
}
],
"lcname": "amharicnlp"
}
JSON
