daisybell
~~~~~~~~~~
A scanner that will scan your AI models for problems. Currently it focuses on bias testing. It is currently alpha.
How to Use
~~~~~~~~~~
First install it:
::
pip install daisybell
Run it in this manner (currently supports models from HuggingFace's repository):
::
daisybell roberta-base
The scan can output files for further analysis:
::
daisybell roberta-base --output results/roberta-base
We will infer the task(s) of model by default but to provide specific tasks to test explicitly use the --task switch:
::
daisybell cross-encoder/nli-distilroberta-base --task zero-shot-classification
That's it for now. More will come.
Future Work
~~~~~~~~~~~~
* More bias tests. More metrics for bias testing based on the research in the field.
* Integration with other types of testing (eg. adversarial robustness)
* More kinds of models besides HuggingFace models. We are especially interested in MLFlow integration.
* Documentation.
Please contribute if you can. Help is always helpful.
License
~~~~~~~
Apache
Credit
~~~~~~
A project of IQT Labs.
Raw data
{
"_id": null,
"home_page": "https://github.com/IQTLabs/daisybell",
"name": "daisybell",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": "",
"keywords": "machine_learning artificial_intelligence",
"author": "JJ Ben-Joseph",
"author_email": "jbenjoseph@iqt.org",
"download_url": "https://files.pythonhosted.org/packages/62/14/3a35b4f881f053ac026274fb73402e28e6cdb70e3a44ecf6098ca2025d24/daisybell-0.4.3.tar.gz",
"platform": null,
"description": "daisybell\n~~~~~~~~~~\n\nA scanner that will scan your AI models for problems. Currently it focuses on bias testing. It is currently alpha.\n\n\nHow to Use\n~~~~~~~~~~\n\nFirst install it:\n\n::\n\n pip install daisybell\n\n\nRun it in this manner (currently supports models from HuggingFace's repository):\n\n::\n\n daisybell roberta-base\n\n\nThe scan can output files for further analysis:\n\n::\n\n daisybell roberta-base --output results/roberta-base\n\nWe will infer the task(s) of model by default but to provide specific tasks to test explicitly use the --task switch:\n\n::\n\n daisybell cross-encoder/nli-distilroberta-base --task zero-shot-classification\n\nThat's it for now. More will come.\n\n\nFuture Work\n~~~~~~~~~~~~\n\n* More bias tests. More metrics for bias testing based on the research in the field.\n* Integration with other types of testing (eg. adversarial robustness)\n* More kinds of models besides HuggingFace models. We are especially interested in MLFlow integration.\n* Documentation.\n\nPlease contribute if you can. Help is always helpful.\n\nLicense\n~~~~~~~\n\nApache\n\nCredit\n~~~~~~\n\nA project of IQT Labs.\n\n\n",
"bugtrack_url": null,
"license": "Apache",
"summary": "Scan AI models for problems",
"version": "0.4.3",
"split_keywords": [
"machine_learning",
"artificial_intelligence"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "66c44ab8bc14cbe616a8e407d2a982d7191ab18cfbc3ad3870f683073745aa92",
"md5": "6a9e9f2e28bcbf62bf7bb9fa6e00e0ff",
"sha256": "e7d7d56c6268040b1917655846db6afd53be3ed102feb0349611ad0f822fdb70"
},
"downloads": -1,
"filename": "daisybell-0.4.3-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "6a9e9f2e28bcbf62bf7bb9fa6e00e0ff",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": ">=3.8",
"size": 15235,
"upload_time": "2023-02-09T14:37:51",
"upload_time_iso_8601": "2023-02-09T14:37:51.576186Z",
"url": "https://files.pythonhosted.org/packages/66/c4/4ab8bc14cbe616a8e407d2a982d7191ab18cfbc3ad3870f683073745aa92/daisybell-0.4.3-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "62143a35b4f881f053ac026274fb73402e28e6cdb70e3a44ecf6098ca2025d24",
"md5": "cffaad15a1736f313896ea4d0716be4c",
"sha256": "52bfdcc63918e9f0e7a6834402bf8c28118e02591cd26ea8d5c2502e5deeb78e"
},
"downloads": -1,
"filename": "daisybell-0.4.3.tar.gz",
"has_sig": false,
"md5_digest": "cffaad15a1736f313896ea4d0716be4c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 14956,
"upload_time": "2023-02-09T14:37:53",
"upload_time_iso_8601": "2023-02-09T14:37:53.306824Z",
"url": "https://files.pythonhosted.org/packages/62/14/3a35b4f881f053ac026274fb73402e28e6cdb70e3a44ecf6098ca2025d24/daisybell-0.4.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-02-09 14:37:53",
"github": true,
"gitlab": false,
"bitbucket": false,
"github_user": "IQTLabs",
"github_project": "daisybell",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "daisybell"
}
JSON
