<p align="center">
<img width="805" height="310" alt="image" src="https://github.com/user-attachments/assets/6f0ff77f-c83e-45eb-bdf6-b6f2fcbd31ed" />
</p>
MTSA is a research toolkit designed to aggregate machine learning models for anomaly detection, with a strong focus on enhancing reproducibility and explainability in model implementation. It offers a structured environment for developing, testing, and comparing various anomaly detection approaches, prioritizing replicability and ease of use. The toolkit is continuously updated to include both classical and state-of-the-art algorithms for anomaly detection in multivariate time series.
## 🔧 Installation
To get started, clone the repository and install the required dependencies:
```bash
git clone https://github.com/your-username/MTSA.git
cd MTSA
pip install -r requirements.txt
```
## 🚀 Usage
MTSA allows you to run anomaly detection models on acoustic data collected from complex systems like industrial machines.
A complete example is available in the following Jupyter notebook:
👉 [examples/MTSA.ipynb](examples/MTSA.ipynb)
> **Note:** If you encounter issues while running on Google Colab, try upgrading the Colab package:
```bash
pip install --upgrade google-colab
```
## 🧠 Implemented Machine Learning Approaches
MTSA currently integrates the following anomaly detection models:
- **Hitachi**
A robust autoencoder model specifically designed for industrial anomaly detection tasks.
- **RANSynCoders**
Ensemble of autoencoders with FFT, leveraging bootstrapping to perform robust anomaly inference.
- **GANF**
A model that combines graph structures, recurrent neural networks (RNNs), and normalizing flows to perform anomaly inference.
- **Isolation Forest**
A tree-based ensemble method that isolates anomalies.
- **OSVM (One-Class SVM)**
A support vector-based approach for detecting outliers by modeling the distribution of normal data.
And more!
## 🌐 Learn More
For full documentation, examples, and additional resources, visit our [official website](https://iotdataatelier.github.io/mtsa-docs/).
Raw data
{
"_id": null,
"home_page": "https://github.com/diegompin/mtsa",
"name": "mtsa",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "mtsa, setuptools",
"author": "Diego Pinheiro",
"author_email": "diegompin@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/5c/8a/2d70a6b7ee317673677fc49f75178ad82757f43f54cfffa873c003017891/mtsa-0.2.4.tar.gz",
"platform": null,
"description": "<p align=\"center\">\n<img width=\"805\" height=\"310\" alt=\"image\" src=\"https://github.com/user-attachments/assets/6f0ff77f-c83e-45eb-bdf6-b6f2fcbd31ed\" />\n</p>\n\nMTSA is a research toolkit designed to aggregate machine learning models for anomaly detection, with a strong focus on enhancing reproducibility and explainability in model implementation. It offers a structured environment for developing, testing, and comparing various anomaly detection approaches, prioritizing replicability and ease of use. The toolkit is continuously updated to include both classical and state-of-the-art algorithms for anomaly detection in multivariate time series.\n\n## \ud83d\udd27 Installation\n\nTo get started, clone the repository and install the required dependencies:\n\n```bash\ngit clone https://github.com/your-username/MTSA.git\ncd MTSA\npip install -r requirements.txt\n```\n\n## \ud83d\ude80 Usage\n\nMTSA allows you to run anomaly detection models on acoustic data collected from complex systems like industrial machines.\n\nA complete example is available in the following Jupyter notebook: \n\ud83d\udc49 [examples/MTSA.ipynb](examples/MTSA.ipynb)\n\n> **Note:** If you encounter issues while running on Google Colab, try upgrading the Colab package:\n\n```bash\npip install --upgrade google-colab\n```\n\n## \ud83e\udde0 Implemented Machine Learning Approaches\n\nMTSA currently integrates the following anomaly detection models:\n\n- **Hitachi** \n A robust autoencoder model specifically designed for industrial anomaly detection tasks.\n\n- **RANSynCoders** \n Ensemble of autoencoders with FFT, leveraging bootstrapping to perform robust anomaly inference.\n \n- **GANF** \n A model that combines graph structures, recurrent neural networks (RNNs), and normalizing flows to perform anomaly inference.\n\n- **Isolation Forest** \n A tree-based ensemble method that isolates anomalies.\n\n- **OSVM (One-Class SVM)** \n A support vector-based approach for detecting outliers by modeling the distribution of normal data.\n\nAnd more!\n\n\n## \ud83c\udf10 Learn More\n\nFor full documentation, examples, and additional resources, visit our [official website](https://iotdataatelier.github.io/mtsa-docs/).\n\n",
"bugtrack_url": null,
"license": "BSD 3-Clause License",
"summary": "Multiple Time Series Analysis",
"version": "0.2.4",
"project_urls": {
"Homepage": "https://github.com/diegompin/mtsa"
},
"split_keywords": [
"mtsa",
" setuptools"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "25de69aa8c59830917bf21af0a29c14e7d4de2a90380dddbe0b5dcdae276ceb5",
"md5": "73cf67e3c867f5ee4e1599c4918b06dd",
"sha256": "74edeaa571d2571dc5b1bc5229326731b1639613d47a872a1420f055c42c16e2"
},
"downloads": -1,
"filename": "mtsa-0.2.4-py3-none-any.whl",
"has_sig": false,
"md5_digest": "73cf67e3c867f5ee4e1599c4918b06dd",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 73832,
"upload_time": "2025-09-10T13:37:43",
"upload_time_iso_8601": "2025-09-10T13:37:43.123200Z",
"url": "https://files.pythonhosted.org/packages/25/de/69aa8c59830917bf21af0a29c14e7d4de2a90380dddbe0b5dcdae276ceb5/mtsa-0.2.4-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "5c8a2d70a6b7ee317673677fc49f75178ad82757f43f54cfffa873c003017891",
"md5": "11ba3bc281704463b8f0ec9eba904a4d",
"sha256": "31d3c1aa0ed89d8bb1b64300f9e355c65595d69e2335fc7a355b54b1f0d1196d"
},
"downloads": -1,
"filename": "mtsa-0.2.4.tar.gz",
"has_sig": false,
"md5_digest": "11ba3bc281704463b8f0ec9eba904a4d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 99067805,
"upload_time": "2025-09-10T13:37:47",
"upload_time_iso_8601": "2025-09-10T13:37:47.273333Z",
"url": "https://files.pythonhosted.org/packages/5c/8a/2d70a6b7ee317673677fc49f75178ad82757f43f54cfffa873c003017891/mtsa-0.2.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-09-10 13:37:47",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "diegompin",
"github_project": "mtsa",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [
{
"name": "apache-beam",
"specs": []
},
{
"name": "pandas",
"specs": []
},
{
"name": "matplotlib",
"specs": []
},
{
"name": "librosa",
"specs": []
},
{
"name": "ipykernel",
"specs": []
},
{
"name": "scikit-learn",
"specs": []
},
{
"name": "seaborn",
"specs": []
},
{
"name": "keras",
"specs": []
},
{
"name": "graphviz",
"specs": []
},
{
"name": "torch",
"specs": []
},
{
"name": "spectrum",
"specs": []
},
{
"name": "tqdm",
"specs": []
},
{
"name": "tensorflow",
"specs": []
},
{
"name": "setuptools-scm",
"specs": []
}
],
"lcname": "mtsa"
}
JSON
