# Welcome to AntakIA !
Hi!
AntakIA is THE tool to explain an ML model or replace it with a collection of basic explainable models.
AntakIA can be used for many purposes: it may help you understand the truths your ML model has learned, or it can assist you in converting an ML model into multiple simple rule-based algorithms.
It achieves this by dividing a given ML model into smaller regions. Hence its name: Antakia is an ancient city famous for its mosaics (and IA is AI in French).
Here is a quick overview on AntakIA:
See full video on [Youtube](https://youtu.be/wQFC_20OIOM).
## Install
AntakIA is available on [PyPI](https://pypi.org/project/antakia/) :
```
pip install antakia
```
## Running example notebooks
Once you've installed `antakia`, you can download some of our notebook examples from our repo [here](https://github.com/AI-vidence/antakia/tree/main/examples).
Then, launch a Jupyter server from the notebook file (`.ipynb`) location :
```
jupyter notebook # or jupyter lab
```
You'll find a complete tutorial for our California housing example here : https://doc.antakia.ai
> [!IMPORTANT]
If you're using a virtual env, it's handy to be able to chose it from Jupyter's kernel list. Do the following :
```
python -m ipykernel install --user --name your_venv_name --display-name "My great virtual env"
```
## Online demo
You can give `antakia` a try online : https://demo.antakia.ai
Log as `demo` with password `antakia`.
Note it runs on a simple server and may be busy.
## Run with Docker
> [!IMPORTANT]
Be sure to have a Docker engine running on your computer (ie. launch Docker Desktop)
```
docker build -t antakia .
docker run -p 8888:8888 antakia
```
In your Terminal, click on the `http://127.0.0.1:8888/lab?token=WHATEVER_YOUR_TOKEN_IS URL` link.
## Logs
`antakia` is our open-source project. We plan to learn a lot from it to build our SaaS product, and earn our living. By default, `antakia` sends anonymous usage logs to our server. With this data, we cannot discover who you are, what you do, or what data you work on. It only tells us how people use the software. However, if you don't want us to receive this data, just create a `.env` file at the root of your project folder with the following line `SEND_ANONYMOUS_LOGS=false`
Raw data
{
"_id": null,
"home_page": null,
"name": "antakia",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.12,>=3.10",
"maintainer_email": null,
"keywords": "XAI, explainability, AI, ML, machine learning, artificial intelligence",
"author": "Pierre HULOT",
"author_email": "pierre@ai-vidence.com",
"download_url": "https://files.pythonhosted.org/packages/d1/ba/6e48829d7e8f7d7b7764b427e1b24f94e15e0255cbbbd298db9b8e3da409/antakia-0.4.6.tar.gz",
"platform": null,
"description": "# Welcome to AntakIA !\nHi!\n\nAntakIA is THE tool to explain an ML model or replace it with a collection of basic explainable models.\n\nAntakIA can be used for many purposes: it may help you understand the truths your ML model has learned, or it can assist you in converting an ML model into multiple simple rule-based algorithms.\n\nIt achieves this by dividing a given ML model into smaller regions. Hence its name: Antakia is an ancient city famous for its mosaics (and IA is AI in French).\n\nHere is a quick overview on AntakIA:\n\n\nSee full video on [Youtube](https://youtu.be/wQFC_20OIOM).\n\n## Install\n\nAntakIA is available on [PyPI](https://pypi.org/project/antakia/) :\n\n```\npip install antakia\n```\n\n## Running example notebooks\n\nOnce you've installed `antakia`, you can download some of our notebook examples from our repo [here](https://github.com/AI-vidence/antakia/tree/main/examples).\n\nThen, launch a Jupyter server from the notebook file (`.ipynb`) location :\n\n```\njupyter notebook # or jupyter lab\n```\n\nYou'll find a complete tutorial for our California housing example here : https://doc.antakia.ai\n\n> [!IMPORTANT] \nIf you're using a virtual env, it's handy to be able to chose it from Jupyter's kernel list. Do the following :\n\n```\npython -m ipykernel install --user --name your_venv_name --display-name \"My great virtual env\"\n```\n\n## Online demo\n\nYou can give `antakia` a try online : https://demo.antakia.ai \n\nLog as `demo` with password `antakia`.\nNote it runs on a simple server and may be busy.\n\n\n## Run with Docker\n\n> [!IMPORTANT] \nBe sure to have a Docker engine running on your computer (ie. launch Docker Desktop)\n\n```\ndocker build -t antakia .\ndocker run -p 8888:8888 antakia\n```\n\nIn your Terminal, click on the `http://127.0.0.1:8888/lab?token=WHATEVER_YOUR_TOKEN_IS URL` link.\n\n## Logs\n\n`antakia` is our open-source project. We plan to learn a lot from it to build our SaaS product, and earn our living. By default, `antakia` sends anonymous usage logs to our server. With this data, we cannot discover who you are, what you do, or what data you work on. It only tells us how people use the software. However, if you don't want us to receive this data, just create a `.env` file at the root of your project folder with the following line `SEND_ANONYMOUS_LOGS=false`\n",
"bugtrack_url": null,
"license": null,
"summary": "AI made Xplainable",
"version": "0.4.6",
"project_urls": null,
"split_keywords": [
"xai",
" explainability",
" ai",
" ml",
" machine learning",
" artificial intelligence"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f7c288968b4f6b0d84636000400cc0f7c0686c62543cfa38de021a9025073db6",
"md5": "5c832355a167469b2099321528fb886f",
"sha256": "5e1e7df4b67b7ae4671f7aae179956b63a6b84b09634a708bba47592e379875d"
},
"downloads": -1,
"filename": "antakia-0.4.6-py3-none-any.whl",
"has_sig": false,
"md5_digest": "5c832355a167469b2099321528fb886f",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.12,>=3.10",
"size": 23495841,
"upload_time": "2024-05-13T17:21:27",
"upload_time_iso_8601": "2024-05-13T17:21:27.204319Z",
"url": "https://files.pythonhosted.org/packages/f7/c2/88968b4f6b0d84636000400cc0f7c0686c62543cfa38de021a9025073db6/antakia-0.4.6-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "d1ba6e48829d7e8f7d7b7764b427e1b24f94e15e0255cbbbd298db9b8e3da409",
"md5": "c30301160da6a523cbcbe668e28e5003",
"sha256": "59152f8ef4b77c1bf8c9acc06f4ad6b0ac69f1144db9b5e6cffd6c8c4a114382"
},
"downloads": -1,
"filename": "antakia-0.4.6.tar.gz",
"has_sig": false,
"md5_digest": "c30301160da6a523cbcbe668e28e5003",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.12,>=3.10",
"size": 22881564,
"upload_time": "2024-05-13T17:21:50",
"upload_time_iso_8601": "2024-05-13T17:21:50.415008Z",
"url": "https://files.pythonhosted.org/packages/d1/ba/6e48829d7e8f7d7b7764b427e1b24f94e15e0255cbbbd298db9b8e3da409/antakia-0.4.6.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-13 17:21:50",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "antakia"
}
JSON