## EazyML Responsible-AI: XAI
  
`eazyml-xai` is a python package designed to make machine learning predictions more transparent and interpretable. It provides human-readable explanations for predictions.
### Features
- Gain insights into **local feature importance and global feature impacts**.
- Understand **why a specific prediction was made**.
- Evaluate predictions with **explainability scores**.
`eazyml-xai` is a key tool for building trust in AI systems by providing clear, actionable explanations.
## Installation
To use the explainable ai, ensure you have Python installed on your system.
### User installation
The easiest way to install EazyML Explainable AI is using pip:
```bash
pip install -U eazyml-xai
```
### Dependencies
This package requires:
- pandas,
- scikit-learn,
- werkzeug,
- Unidecode,
- pydot,
- numpy,
- pyyaml
## Usage
Here's an example of how you can use the APIs from this package.
```python
from eazyml_xai import ez_init, ez_explain
# initialize: setup book-keeping, access_key if required
_ = ez_init()
response = ez_explain(
train_data(`DataFrame/str`) = 'train_dataframe/train_data_path',
outcome(`str`) = 'target',
test_data(`DataFrame/str`) = 'test_dataframe/test_data_path',
model(`Bytes/object`) = 'Encripted model_info from ez_build_model response or the trained model'
options(`dict`) = {
"record_number"(`list of integer`): "Specify the record number of test data in the list on which you want to get the explanations"
"scaler"(`object`): "Trained scaler object"
"preprocessor"(`object`): "Trained preprocessor object"
}
)
explanations = response['explanations']
```
You can find more information in the [documentation](https://eazyml.readthedocs.io/en/latest/packages/eazyml_xai.html).
## Useful links, other packages from EazyML family
- [Documentation](https://docs.eazyml.com)
- [Homepage](https://eazyml.com)
- If you have questions or would like to discuss a use case, please contact us [here](https://eazyml.com/trust-in-ai)
- Here are the other packages from EazyML suite:
- [eazyml-automl](https://pypi.org/project/eazyml-automl/): eazyml-automl provides a suite of APIs for training, optimizing and validating machine learning models with built-in AutoML capabilities, hyperparameter tuning, and cross-validation.
- [eazyml-data-quality](https://pypi.org/project/eazyml-data-quality/): eazyml-data-quality provides APIs for comprehensive data quality assessment, including bias detection, outlier identification, and drift analysis for both data and models.
- [eazyml-counterfactual](https://pypi.org/project/eazyml-counterfactual/): eazyml-counterfactual provides APIs for optimal prescriptive analytics, counterfactual explanations, and actionable insights to optimize predictive outcomes to align with your objectives.
- [eazyml-insight](https://pypi.org/project/eazyml-insight/): eazyml-insight provides APIs to discover patterns, generate insights, and mine rules from your datasets.
- [eazyml-xai](https://pypi.org/project/eazyml-xai/): eazyml-xai provides APIs for explainable AI (XAI), offering human-readable explanations, feature importance, and predictive reasoning.
- [eazyml-xai-image](https://pypi.org/project/eazyml-xai-image/): eazyml-xai-image provides APIs for image explainable AI (XAI).
## License
This project is licensed under the [Proprietary License](https://github.com/EazyML/eazyml-docs/blob/master/LICENSE).
---
Maintained by [EazyML](https://eazyml.com)
© 2025 EazyML. All rights reserved.
Raw data
{
"_id": null,
"home_page": "https://eazyml.com/",
"name": "eazyml-xai",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.7",
"maintainer_email": null,
"keywords": "xai, explainable-ai, model-explainability, predictive-reasoning, feature-importance, predictive-reasoning, explainability-score, interpretable-ai, local-feature-importance, machine-learning",
"author": "EazyML",
"author_email": "admin@ipsoftlabs.com",
"download_url": "https://files.pythonhosted.org/packages/04/b1/75e020ebc28b8546ae7c5801b3e421e4a529be3715f1d25d773b06ffa8d9/eazyml_xai-0.0.65.tar.gz",
"platform": null,
"description": "## EazyML Responsible-AI: XAI\r\n  \r\n\r\n\r\n\r\n`eazyml-xai` is a python package designed to make machine learning predictions more transparent and interpretable. It provides human-readable explanations for predictions.\r\n\r\n### Features\r\n- Gain insights into **local feature importance and global feature impacts**.\r\n- Understand **why a specific prediction was made**.\r\n- Evaluate predictions with **explainability scores**. \r\n\r\n`eazyml-xai` is a key tool for building trust in AI systems by providing clear, actionable explanations.\r\n\r\n## Installation\r\nTo use the explainable ai, ensure you have Python installed on your system.\r\n### User installation\r\nThe easiest way to install EazyML Explainable AI is using pip:\r\n```bash\r\npip install -U eazyml-xai\r\n```\r\n### Dependencies\r\nThis package requires:\r\n- pandas,\r\n- scikit-learn,\r\n- werkzeug,\r\n- Unidecode,\r\n- pydot,\r\n- numpy,\r\n- pyyaml\r\n\r\n## Usage\r\nHere's an example of how you can use the APIs from this package.\r\n```python\r\nfrom eazyml_xai import ez_init, ez_explain\r\n\r\n# initialize: setup book-keeping, access_key if required \r\n_ = ez_init()\r\n\r\nresponse = ez_explain(\r\n train_data(`DataFrame/str`) = 'train_dataframe/train_data_path',\r\n outcome(`str`) = 'target',\r\n test_data(`DataFrame/str`) = 'test_dataframe/test_data_path',\r\n model(`Bytes/object`) = 'Encripted model_info from ez_build_model response or the trained model'\r\n options(`dict`) = {\r\n \"record_number\"(`list of integer`): \"Specify the record number of test data in the list on which you want to get the explanations\"\r\n \"scaler\"(`object`): \"Trained scaler object\"\r\n \"preprocessor\"(`object`): \"Trained preprocessor object\"\r\n }\r\n )\r\n\r\nexplanations = response['explanations']\r\n```\r\nYou can find more information in the [documentation](https://eazyml.readthedocs.io/en/latest/packages/eazyml_xai.html).\r\n\r\n\r\n## Useful links, other packages from EazyML family\r\n- [Documentation](https://docs.eazyml.com)\r\n- [Homepage](https://eazyml.com)\r\n- If you have questions or would like to discuss a use case, please contact us [here](https://eazyml.com/trust-in-ai)\r\n- Here are the other packages from EazyML suite:\r\n\r\n - [eazyml-automl](https://pypi.org/project/eazyml-automl/): eazyml-automl provides a suite of APIs for training, optimizing and validating machine learning models with built-in AutoML capabilities, hyperparameter tuning, and cross-validation.\r\n - [eazyml-data-quality](https://pypi.org/project/eazyml-data-quality/): eazyml-data-quality provides APIs for comprehensive data quality assessment, including bias detection, outlier identification, and drift analysis for both data and models.\r\n - [eazyml-counterfactual](https://pypi.org/project/eazyml-counterfactual/): eazyml-counterfactual provides APIs for optimal prescriptive analytics, counterfactual explanations, and actionable insights to optimize predictive outcomes to align with your objectives.\r\n - [eazyml-insight](https://pypi.org/project/eazyml-insight/): eazyml-insight provides APIs to discover patterns, generate insights, and mine rules from your datasets.\r\n - [eazyml-xai](https://pypi.org/project/eazyml-xai/): eazyml-xai provides APIs for explainable AI (XAI), offering human-readable explanations, feature importance, and predictive reasoning.\r\n - [eazyml-xai-image](https://pypi.org/project/eazyml-xai-image/): eazyml-xai-image provides APIs for image explainable AI (XAI).\r\n\r\n## License\r\nThis project is licensed under the [Proprietary License](https://github.com/EazyML/eazyml-docs/blob/master/LICENSE).\r\n\r\n---\r\n\r\nMaintained by [EazyML](https://eazyml.com) \r\n\u00c2\u00a9 2025 EazyML. All rights reserved.\r\n",
"bugtrack_url": null,
"license": null,
"summary": "eazyml-xai provides APIs for explainable AI (XAI), offering human-readable explanations, feature importance, and predictive reasoning.",
"version": "0.0.65",
"project_urls": {
"Contact Us": "https://eazyml.com/trust-in-ai",
"Documentation": "https://docs.eazyml.com/",
"Homepage": "https://eazyml.com/",
"eazyml-automl": "https://pypi.org/project/eazyml-automl/",
"eazyml-counterfactual": "https://pypi.org/project/eazyml-counterfactual/",
"eazyml-data-quality": "https://pypi.org/project/eazyml-data-quality/",
"eazyml-insight": "https://pypi.org/project/eazyml-insight/",
"eazyml-xai": "https://pypi.org/project/eazyml-xai/",
"eazyml-xai-image": "https://pypi.org/project/eazyml-xai-image/"
},
"split_keywords": [
"xai",
" explainable-ai",
" model-explainability",
" predictive-reasoning",
" feature-importance",
" predictive-reasoning",
" explainability-score",
" interpretable-ai",
" local-feature-importance",
" machine-learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f4e6e5a3612b393522d2e6030bb015ec8d84325489a8dfc949efa3f06d0a881b",
"md5": "c1dac488cba01a7a0e867d67543b47eb",
"sha256": "5df5ac707d532a45811105978cf3eb02e25d2ee46d89217405a6b259197c27d4"
},
"downloads": -1,
"filename": "eazyml_xai-0.0.65-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "c1dac488cba01a7a0e867d67543b47eb",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.7",
"size": 32731494,
"upload_time": "2025-02-27T15:51:24",
"upload_time_iso_8601": "2025-02-27T15:51:24.664299Z",
"url": "https://files.pythonhosted.org/packages/f4/e6/e5a3612b393522d2e6030bb015ec8d84325489a8dfc949efa3f06d0a881b/eazyml_xai-0.0.65-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "04b175e020ebc28b8546ae7c5801b3e421e4a529be3715f1d25d773b06ffa8d9",
"md5": "1c093814da6d1ab55205e582ef402911",
"sha256": "46e45f72f80db6a401e50457603822ad623c0f9f849720cae35f22d42bb645cd"
},
"downloads": -1,
"filename": "eazyml_xai-0.0.65.tar.gz",
"has_sig": false,
"md5_digest": "1c093814da6d1ab55205e582ef402911",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.7",
"size": 32156251,
"upload_time": "2025-02-27T15:51:36",
"upload_time_iso_8601": "2025-02-27T15:51:36.637944Z",
"url": "https://files.pythonhosted.org/packages/04/b1/75e020ebc28b8546ae7c5801b3e421e4a529be3715f1d25d773b06ffa8d9/eazyml_xai-0.0.65.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-02-27 15:51:36",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "eazyml-xai"
}
JSON