# MANTA (Multi-lingual Advanced NMF-based Topic Analysis)
[](https://badge.fury.io/py/manta-topic-modelling)
[](https://badge.fury.io/py/manta-topic-modelling)
[](https://www.python.org/downloads/)
[](https://opensource.org/licenses/MIT)
A comprehensive topic modeling system using Non-negative Matrix Factorization (NMF) that supports both English and Turkish text processing. Features advanced tokenization techniques, multiple NMF algorithms, and rich visualization capabilities.
## Quick Start
### Installing locally for Development
To build and run the app locally for development:
First clone the repository:
```bash
git clone https://github.com/emirkyz/manta.git
```
After cloning, navigate to the project directory and create a virtual environment:
```bash
cd manta
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
```
Next, install the required dependencies. If you have `pip` installed, you can run:
```bash
pip install -e .
```
or if you have `uv` installed, you can use:
```bash
uv pip install -e .
```
### Installation from PyPI
```bash
pip install manta-topic-modelling
```
After that you can import and use the app.
### Command Line Usage
```bash
# Turkish text analysis
manta-topic-modelling analyze data.csv --column text --language TR --topics 5
# English text analysis with lemmatization and visualizations
manta-topic-modelling analyze data.csv --column content --language EN --topics 10 --lemmatize --wordclouds --excel
# Custom tokenizer for Turkish text
manta-topic-modelling analyze reviews.csv --column review_text --language TR --topics 8 --tokenizer bpe --wordclouds
# Disable emoji processing for faster processing
manta-topic-modelling analyze data.csv --column text --language EN --topics 5 --emoji-map False
```
### Python API Usage
```python
from manta import run_topic_analysis
# Simple topic modeling
results = run_topic_analysis(
filepath="data.csv",
column="review_text",
language="EN",
topics=5,
lemmatize=True
)
# Turkish text analysis
results = run_topic_analysis(
filepath="turkish_reviews.csv",
column="yorum_metni",
language="TR",
topics=8,
tokenizer_type="bpe",
generate_wordclouds=True
)
```
## Package Structure
```
manta/
├── _functions/
│ ├── common_language/ # Shared functionality across languages
│ │ ├── emoji_processor.py # Emoji handling utilities
│ │ └── topic_analyzer.py # Cross-language topic analysis
│ ├── english/ # English text processing modules
│ │ ├── english_entry.py # English text processing entry point
│ │ ├── english_preprocessor.py # Text cleaning and preprocessing
│ │ ├── english_vocabulary.py # Vocabulary creation
│ │ ├── english_text_encoder.py # Text-to-numerical conversion
│ │ ├── english_topic_analyzer.py # Topic extraction utilities
│ │ ├── english_topic_output.py # Topic visualization and output
│ │ └── english_nmf_core.py # NMF implementation for English
│ ├── nmf/ # NMF algorithm implementations
│ │ ├── nmf_orchestrator.py # Main NMF interface
│ │ ├── nmf_initialization.py # Matrix initialization strategies
│ │ ├── nmf_basic.py # Standard NMF algorithm
│ │ ├── nmf_projective_basic.py # Basic projective NMF
│ │ └── nmf_projective_enhanced.py # Enhanced projective NMF
│ ├── tfidf/ # TF-IDF calculation modules
│ │ ├── tfidf_english_calculator.py # English TF-IDF implementation
│ │ ├── tfidf_turkish_calculator.py # Turkish TF-IDF implementation
│ │ ├── tfidf_tf_functions.py # Term frequency functions
│ │ ├── tfidf_idf_functions.py # Inverse document frequency functions
│ │ └── tfidf_bm25_turkish.py # BM25 implementation for Turkish
│ └── turkish/ # Turkish text processing modules
│ ├── turkish_entry.py # Turkish text processing entry point
│ ├── turkish_preprocessor.py # Turkish text cleaning
│ ├── turkish_tokenizer_factory.py # Tokenizer creation and training
│ ├── turkish_text_encoder.py # Text-to-numerical conversion
│ └── turkish_tfidf_generator.py # TF-IDF matrix generation
├── utils/ # Helper utilities
│ ├── coherence_score.py # Topic coherence evaluation
│ ├── combine_number_suffix.py # Number and suffix combination utilities
│ ├── distance_two_words.py # Word distance calculation
│ ├── export_excel.py # Excel export functionality
│ ├── gen_cloud.py # Word cloud generation
│ ├── hierarchy_nmf.py # Hierarchical NMF utilities
│ ├── image_to_base.py # Image to base64 conversion
│ ├── save_doc_score_pair.py # Document-score pair saving utilities
│ ├── save_topics_db.py # Topic database saving
│ ├── save_word_score_pair.py # Word-score pair saving utilities
│ ├── topic_dist.py # Topic distribution plotting
│ ├── umass_test.py # UMass coherence testing
│ ├── visualizer.py # General visualization utilities
│ ├── word_cooccurrence.py # Word co-occurrence analysis
│ └── other/ # Additional utility functions
├── cli.py # Command-line interface
├── standalone_nmf.py # Core NMF implementation
└── __init__.py # Package initialization and public API
```
## Installation
### From PyPI (Recommended)
```bash
pip install manta-topic-modelling
```
### From Source (Development)
1. Clone the repository:
```bash
git clone https://github.com/emirkyz/manta.git
cd manta
```
2. Create a virtual environment:
```bash
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
```
3. Install dependencies:
```bash
pip install -r requirements.txt
```
## Usage
### Command Line Interface
The package provides the `manta-topic-modelling` command with an `analyze` subcommand:
```bash
# Basic usage
manta-topic-modelling analyze data.csv --column text --language TR --topics 5
# Advanced usage with all options
manta-topic-modelling analyze reviews.csv \
--column review_text \
--language EN \
--topics 10 \
--words-per-topic 20 \
--nmf-method opnmf \
--lemmatize \
--wordclouds \
--excel \
--topic-distribution \
--output-name my_analysis
```
#### Command Line Options
**Required Arguments:**
- `filepath`: Path to input CSV or Excel file
- `--column, -c`: Name of column containing text data
- `--language, -l`: Language ("TR" for Turkish, "EN" for English)
**Optional Arguments:**
- `--topics, -t`: Number of topics to extract (default: 5)
- `--output-name, -o`: Custom name for output files (default: auto-generated)
- `--tokenizer`: Tokenizer type for Turkish ("bpe" or "wordpiece", default: "bpe")
- `--nmf-method`: NMF algorithm ("nmf" or "opnmf", default: "nmf")
- `--words-per-topic`: Number of top words per topic (default: 15)
- `--lemmatize`: Apply lemmatization for English text
- `--emoji-map`: Enable emoji processing and mapping (default: True). Use --emoji-map False to disable
- `--wordclouds`: Generate word cloud visualizations
- `--excel`: Export results to Excel format
- `--topic-distribution`: Generate topic distribution plots
- `--separator`: CSV separator character (default: "|")
- `--filter-app`: Filter data by specific app name
### Python API
```python
from manta import run_topic_analysis
# Basic English text analysis
results = run_topic_analysis(
filepath="data.csv",
column="review_text",
language="EN",
topics=5,
lemmatize=True,
generate_wordclouds=True,
export_excel=True
)
# Advanced Turkish text analysis
results = run_topic_analysis(
filepath="turkish_reviews.csv",
column="yorum_metni",
language="TR",
topics=10,
words_per_topic=15,
tokenizer_type="bpe",
nmf_method="nmf",
generate_wordclouds=True,
export_excel=True,
topic_distribution=True
)
```
#### API Parameters
**Required:**
- `filepath` (str): Path to input CSV or Excel file
- `column` (str): Name of column containing text data
**Optional:**
- `language` (str): "TR" for Turkish, "EN" for English (default: "EN")
- `topics` (int): Number of topics to extract (default: 5)
- `words_per_topic` (int): Top words to show per topic (default: 15)
- `nmf_method` (str): "nmf" or "opnmf" algorithm variant (default: "nmf")
- `tokenizer_type` (str): "bpe" or "wordpiece" for Turkish (default: "bpe")
- `lemmatize` (bool): Apply lemmatization for English (default: True)
- `generate_wordclouds` (bool): Create word cloud visualizations (default: True)
- `export_excel` (bool): Export results to Excel (default: True)
- `topic_distribution` (bool): Generate distribution plots (default: True)
- `emoji_map` (bool): Enable emoji processing and mapping (default: True)
- `output_name` (str): Custom output directory name (default: auto-generated)
- `separator` (str): CSV separator character (default: ",")
- `filter_app` (bool): Enable app filtering (default: False)
- `filter_app_name` (str): App name for filtering (default: "")
## Outputs
The analysis generates several outputs in an `Output/` directory (created at runtime), organized in a subdirectory named after your analysis:
- **Topic-Word Excel File**: `.xlsx` file containing top words for each topic and their scores
- **Word Clouds**: PNG images of word clouds for each topic (if `generate_wordclouds=True`)
- **Topic Distribution Plot**: Plot showing distribution of documents across topics (if `topic_distribution=True`)
- **Coherence Scores**: JSON file with coherence scores for the topics
- **Top Documents**: JSON file listing most representative documents for each topic
## Features
- **Multi-language Support**: Optimized processing for both Turkish and English texts
- **Advanced Tokenization**: BPE and WordPiece tokenizers for Turkish, traditional tokenization for English
- **Multiple NMF Algorithms**: Standard NMF and Orthogonal Projective NMF (OPNMF)
- **Rich Visualizations**: Word clouds and topic distribution plots
- **Flexible Export**: Excel and JSON export formats
- **Coherence Evaluation**: Built-in topic coherence scoring
- **Text Preprocessing**: Language-specific text cleaning and preprocessing
## Requirements
- Python 3.9+
- Dependencies are automatically installed with the package
## License
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
## Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
## Support
For issues and questions, please open an issue on the [GitHub repository](https://github.com/emirkyz/manta/issues?q=is%3Aissue)
Raw data
{
"_id": null,
"home_page": null,
"name": "manta-topic-modelling",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.11",
"maintainer_email": null,
"keywords": "nlp, topic-modeling, nmf, text-analysis, turkish, english",
"author": null,
"author_email": "Emir Karayagiz <emirkyzmain@gmail.com>",
"download_url": "https://files.pythonhosted.org/packages/05/6b/f3cc97caa8021b6d37ab3516059a5de8ddc0a6e9dd097778b90979fd8a1d/manta_topic_modelling-0.5.2.tar.gz",
"platform": null,
"description": "# MANTA (Multi-lingual Advanced NMF-based Topic Analysis)\n\n[](https://badge.fury.io/py/manta-topic-modelling)\n[](https://badge.fury.io/py/manta-topic-modelling)\n[](https://www.python.org/downloads/)\n[](https://opensource.org/licenses/MIT)\n\nA comprehensive topic modeling system using Non-negative Matrix Factorization (NMF) that supports both English and Turkish text processing. Features advanced tokenization techniques, multiple NMF algorithms, and rich visualization capabilities.\n\n## Quick Start\n### Installing locally for Development\nTo build and run the app locally for development:\nFirst clone the repository:\n```bash\ngit clone https://github.com/emirkyz/manta.git\n```\nAfter cloning, navigate to the project directory and create a virtual environment:\n\n```bash\ncd manta\npython -m venv .venv\nsource .venv/bin/activate # On Windows: .venv\\Scripts\\activate\n```\nNext, install the required dependencies. If you have `pip` installed, you can run:\n```bash\npip install -e .\n```\nor if you have `uv` installed, you can use:\n```bash\nuv pip install -e .\n```\n### Installation from PyPI\n```bash\npip install manta-topic-modelling\n```\n\nAfter that you can import and use the app.\n\n### Command Line Usage\n```bash\n# Turkish text analysis\nmanta-topic-modelling analyze data.csv --column text --language TR --topics 5\n\n# English text analysis with lemmatization and visualizations\nmanta-topic-modelling analyze data.csv --column content --language EN --topics 10 --lemmatize --wordclouds --excel\n\n# Custom tokenizer for Turkish text\nmanta-topic-modelling analyze reviews.csv --column review_text --language TR --topics 8 --tokenizer bpe --wordclouds\n\n# Disable emoji processing for faster processing\nmanta-topic-modelling analyze data.csv --column text --language EN --topics 5 --emoji-map False\n```\n\n### Python API Usage\n```python\nfrom manta import run_topic_analysis\n\n# Simple topic modeling\nresults = run_topic_analysis(\n filepath=\"data.csv\",\n column=\"review_text\",\n language=\"EN\",\n topics=5,\n lemmatize=True\n)\n\n# Turkish text analysis\nresults = run_topic_analysis(\n filepath=\"turkish_reviews.csv\", \n column=\"yorum_metni\",\n language=\"TR\",\n topics=8,\n tokenizer_type=\"bpe\",\n generate_wordclouds=True\n)\n```\n\n## Package Structure\n\n```\nmanta/\n\u251c\u2500\u2500 _functions/\n\u2502 \u251c\u2500\u2500 common_language/ # Shared functionality across languages\n\u2502 \u2502 \u251c\u2500\u2500 emoji_processor.py # Emoji handling utilities\n\u2502 \u2502 \u2514\u2500\u2500 topic_analyzer.py # Cross-language topic analysis\n\u2502 \u251c\u2500\u2500 english/ # English text processing modules\n\u2502 \u2502 \u251c\u2500\u2500 english_entry.py # English text processing entry point\n\u2502 \u2502 \u251c\u2500\u2500 english_preprocessor.py # Text cleaning and preprocessing\n\u2502 \u2502 \u251c\u2500\u2500 english_vocabulary.py # Vocabulary creation\n\u2502 \u2502 \u251c\u2500\u2500 english_text_encoder.py # Text-to-numerical conversion\n\u2502 \u2502 \u251c\u2500\u2500 english_topic_analyzer.py # Topic extraction utilities\n\u2502 \u2502 \u251c\u2500\u2500 english_topic_output.py # Topic visualization and output\n\u2502 \u2502 \u2514\u2500\u2500 english_nmf_core.py # NMF implementation for English\n\u2502 \u251c\u2500\u2500 nmf/ # NMF algorithm implementations\n\u2502 \u2502 \u251c\u2500\u2500 nmf_orchestrator.py # Main NMF interface\n\u2502 \u2502 \u251c\u2500\u2500 nmf_initialization.py # Matrix initialization strategies\n\u2502 \u2502 \u251c\u2500\u2500 nmf_basic.py # Standard NMF algorithm\n\u2502 \u2502 \u251c\u2500\u2500 nmf_projective_basic.py # Basic projective NMF\n\u2502 \u2502 \u2514\u2500\u2500 nmf_projective_enhanced.py # Enhanced projective NMF\n\u2502 \u251c\u2500\u2500 tfidf/ # TF-IDF calculation modules\n\u2502 \u2502 \u251c\u2500\u2500 tfidf_english_calculator.py # English TF-IDF implementation\n\u2502 \u2502 \u251c\u2500\u2500 tfidf_turkish_calculator.py # Turkish TF-IDF implementation\n\u2502 \u2502 \u251c\u2500\u2500 tfidf_tf_functions.py # Term frequency functions\n\u2502 \u2502 \u251c\u2500\u2500 tfidf_idf_functions.py # Inverse document frequency functions\n\u2502 \u2502 \u2514\u2500\u2500 tfidf_bm25_turkish.py # BM25 implementation for Turkish\n\u2502 \u2514\u2500\u2500 turkish/ # Turkish text processing modules\n\u2502 \u251c\u2500\u2500 turkish_entry.py # Turkish text processing entry point\n\u2502 \u251c\u2500\u2500 turkish_preprocessor.py # Turkish text cleaning\n\u2502 \u251c\u2500\u2500 turkish_tokenizer_factory.py # Tokenizer creation and training\n\u2502 \u251c\u2500\u2500 turkish_text_encoder.py # Text-to-numerical conversion\n\u2502 \u2514\u2500\u2500 turkish_tfidf_generator.py # TF-IDF matrix generation\n\u251c\u2500\u2500 utils/ # Helper utilities\n\u2502 \u251c\u2500\u2500 coherence_score.py # Topic coherence evaluation\n\u2502 \u251c\u2500\u2500 combine_number_suffix.py # Number and suffix combination utilities\n\u2502 \u251c\u2500\u2500 distance_two_words.py # Word distance calculation\n\u2502 \u251c\u2500\u2500 export_excel.py # Excel export functionality\n\u2502 \u251c\u2500\u2500 gen_cloud.py # Word cloud generation\n\u2502 \u251c\u2500\u2500 hierarchy_nmf.py # Hierarchical NMF utilities\n\u2502 \u251c\u2500\u2500 image_to_base.py # Image to base64 conversion\n\u2502 \u251c\u2500\u2500 save_doc_score_pair.py # Document-score pair saving utilities\n\u2502 \u251c\u2500\u2500 save_topics_db.py # Topic database saving\n\u2502 \u251c\u2500\u2500 save_word_score_pair.py # Word-score pair saving utilities\n\u2502 \u251c\u2500\u2500 topic_dist.py # Topic distribution plotting\n\u2502 \u251c\u2500\u2500 umass_test.py # UMass coherence testing\n\u2502 \u251c\u2500\u2500 visualizer.py # General visualization utilities\n\u2502 \u251c\u2500\u2500 word_cooccurrence.py # Word co-occurrence analysis\n\u2502 \u2514\u2500\u2500 other/ # Additional utility functions\n\u251c\u2500\u2500 cli.py # Command-line interface\n\u251c\u2500\u2500 standalone_nmf.py # Core NMF implementation\n\u2514\u2500\u2500 __init__.py # Package initialization and public API\n```\n\n## Installation\n\n### From PyPI (Recommended)\n```bash\npip install manta-topic-modelling\n```\n\n### From Source (Development)\n1. Clone the repository:\n```bash\ngit clone https://github.com/emirkyz/manta.git\ncd manta\n```\n\n2. Create a virtual environment:\n```bash\npython -m venv .venv\nsource .venv/bin/activate # On Windows: .venv\\Scripts\\activate\n```\n\n3. Install dependencies:\n```bash\npip install -r requirements.txt\n```\n\n## Usage\n\n### Command Line Interface\n\nThe package provides the `manta-topic-modelling` command with an `analyze` subcommand:\n\n```bash\n# Basic usage\nmanta-topic-modelling analyze data.csv --column text --language TR --topics 5\n\n# Advanced usage with all options\nmanta-topic-modelling analyze reviews.csv \\\n --column review_text \\\n --language EN \\\n --topics 10 \\\n --words-per-topic 20 \\\n --nmf-method opnmf \\\n --lemmatize \\\n --wordclouds \\\n --excel \\\n --topic-distribution \\\n --output-name my_analysis\n```\n\n#### Command Line Options\n\n**Required Arguments:**\n- `filepath`: Path to input CSV or Excel file\n- `--column, -c`: Name of column containing text data\n- `--language, -l`: Language (\"TR\" for Turkish, \"EN\" for English)\n\n**Optional Arguments:**\n- `--topics, -t`: Number of topics to extract (default: 5)\n- `--output-name, -o`: Custom name for output files (default: auto-generated)\n- `--tokenizer`: Tokenizer type for Turkish (\"bpe\" or \"wordpiece\", default: \"bpe\")\n- `--nmf-method`: NMF algorithm (\"nmf\" or \"opnmf\", default: \"nmf\")\n- `--words-per-topic`: Number of top words per topic (default: 15)\n- `--lemmatize`: Apply lemmatization for English text\n- `--emoji-map`: Enable emoji processing and mapping (default: True). Use --emoji-map False to disable\n- `--wordclouds`: Generate word cloud visualizations\n- `--excel`: Export results to Excel format\n- `--topic-distribution`: Generate topic distribution plots\n- `--separator`: CSV separator character (default: \"|\")\n- `--filter-app`: Filter data by specific app name\n\n### Python API\n\n```python\nfrom manta import run_topic_analysis\n\n# Basic English text analysis\nresults = run_topic_analysis(\n filepath=\"data.csv\",\n column=\"review_text\",\n language=\"EN\",\n topics=5,\n lemmatize=True,\n generate_wordclouds=True,\n export_excel=True\n)\n\n# Advanced Turkish text analysis\nresults = run_topic_analysis(\n filepath=\"turkish_reviews.csv\",\n column=\"yorum_metni\",\n language=\"TR\",\n topics=10,\n words_per_topic=15,\n tokenizer_type=\"bpe\",\n nmf_method=\"nmf\",\n generate_wordclouds=True,\n export_excel=True,\n topic_distribution=True\n)\n```\n\n#### API Parameters\n\n**Required:**\n- `filepath` (str): Path to input CSV or Excel file\n- `column` (str): Name of column containing text data\n\n**Optional:**\n- `language` (str): \"TR\" for Turkish, \"EN\" for English (default: \"EN\")\n- `topics` (int): Number of topics to extract (default: 5)\n- `words_per_topic` (int): Top words to show per topic (default: 15)\n- `nmf_method` (str): \"nmf\" or \"opnmf\" algorithm variant (default: \"nmf\")\n- `tokenizer_type` (str): \"bpe\" or \"wordpiece\" for Turkish (default: \"bpe\")\n- `lemmatize` (bool): Apply lemmatization for English (default: True)\n- `generate_wordclouds` (bool): Create word cloud visualizations (default: True)\n- `export_excel` (bool): Export results to Excel (default: True)\n- `topic_distribution` (bool): Generate distribution plots (default: True)\n- `emoji_map` (bool): Enable emoji processing and mapping (default: True)\n- `output_name` (str): Custom output directory name (default: auto-generated)\n- `separator` (str): CSV separator character (default: \",\")\n- `filter_app` (bool): Enable app filtering (default: False)\n- `filter_app_name` (str): App name for filtering (default: \"\")\n\n## Outputs\n\nThe analysis generates several outputs in an `Output/` directory (created at runtime), organized in a subdirectory named after your analysis:\n\n- **Topic-Word Excel File**: `.xlsx` file containing top words for each topic and their scores\n- **Word Clouds**: PNG images of word clouds for each topic (if `generate_wordclouds=True`)\n- **Topic Distribution Plot**: Plot showing distribution of documents across topics (if `topic_distribution=True`)\n- **Coherence Scores**: JSON file with coherence scores for the topics\n- **Top Documents**: JSON file listing most representative documents for each topic\n\n## Features\n\n- **Multi-language Support**: Optimized processing for both Turkish and English texts\n- **Advanced Tokenization**: BPE and WordPiece tokenizers for Turkish, traditional tokenization for English\n- **Multiple NMF Algorithms**: Standard NMF and Orthogonal Projective NMF (OPNMF)\n- **Rich Visualizations**: Word clouds and topic distribution plots\n- **Flexible Export**: Excel and JSON export formats\n- **Coherence Evaluation**: Built-in topic coherence scoring\n- **Text Preprocessing**: Language-specific text cleaning and preprocessing\n\n## Requirements\n\n- Python 3.9+\n- Dependencies are automatically installed with the package\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.\n\n## Contributing\n\nContributions are welcome! Please feel free to submit a Pull Request.\n\n## Support\n\nFor issues and questions, please open an issue on the [GitHub repository](https://github.com/emirkyz/manta/issues?q=is%3Aissue)\n",
"bugtrack_url": null,
"license": null,
"summary": "Multi-lingual Advanced NMF-based Topic Analysis - A comprehensive NMF topic modeling tool for Turkish and English texts",
"version": "0.5.2",
"project_urls": {
"Documentation": "https://github.com/emirkarayagiz/manta#readme",
"Homepage": "https://github.com/emirkyz/manta/tree/main/manta-pypi",
"Issues": "https://github.com/emirkyz/manta/issues?q=is%3Aissue",
"Repository": "https://github.com/emirkyz/manta/tree/main/manta-pypi"
},
"split_keywords": [
"nlp",
" topic-modeling",
" nmf",
" text-analysis",
" turkish",
" english"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "1982442b1705aba50520a34d627a722889e095b4a542db692ae550fb43f3ce0c",
"md5": "34c6a02ba359719a561544f9c321092a",
"sha256": "1bd2057cc0f6ae64cf38d06a0cb58097bb8cac0c2ca826a9c57516905bfbef1e"
},
"downloads": -1,
"filename": "manta_topic_modelling-0.5.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "34c6a02ba359719a561544f9c321092a",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.11",
"size": 88957,
"upload_time": "2025-07-18T11:40:28",
"upload_time_iso_8601": "2025-07-18T11:40:28.275617Z",
"url": "https://files.pythonhosted.org/packages/19/82/442b1705aba50520a34d627a722889e095b4a542db692ae550fb43f3ce0c/manta_topic_modelling-0.5.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "056bf3cc97caa8021b6d37ab3516059a5de8ddc0a6e9dd097778b90979fd8a1d",
"md5": "fccf2247878c6202caa141a9e7374323",
"sha256": "b8d0db5bfbce468f2a7ecadae449ec4311304677dc2c7455d9ea0ca50b0c5986"
},
"downloads": -1,
"filename": "manta_topic_modelling-0.5.2.tar.gz",
"has_sig": false,
"md5_digest": "fccf2247878c6202caa141a9e7374323",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.11",
"size": 70226,
"upload_time": "2025-07-18T11:40:29",
"upload_time_iso_8601": "2025-07-18T11:40:29.704731Z",
"url": "https://files.pythonhosted.org/packages/05/6b/f3cc97caa8021b6d37ab3516059a5de8ddc0a6e9dd097778b90979fd8a1d/manta_topic_modelling-0.5.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-18 11:40:29",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "emirkarayagiz",
"github_project": "manta#readme",
"github_not_found": true,
"lcname": "manta-topic-modelling"
}
JSON
