<img src="./zeno.png" width="250px"/>
[](https://badge.fury.io/py/zenoml)


[](https://lbesson.mit-license.org/) [](https://gitter.im/zeno-ml-eval/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)
Zeno is a general-purpose framework for evaluating machine learning models.
It combines a **Python API** with an **interactive UI** to allow users to discover, explore, and analyze the performance of their models across diverse use cases.
Zeno can be used for any data type or task with [modular views](https://zenoml.com/docs/views/) for everything from object detection to audio transcription.
## Quickstart
Install the Zeno Python package from PyPI:
```bash
pip install zenoml
```
### Command Line
To get started, run the following command to initialize a Zeno project. It will walk you through creating the `zeno.toml` configuration file:
```bash
zeno init
```
Then run `zeno zeno.toml`.
### Jupyter Notebook
You can also run Zeno directly from Jupyter notebooks or lab. The `zeno` command takes a dictionary of configuration options as input. See [the docs](https://zenoml.com/docs/configuration) for a full list of options. In this example we pass the minimum options for exploring a non-tabular dataset:
```python
import pandas as pd
from zeno import zeno
df = pd.read_csv("/path/to/metadata/file.csv")
zeno({
"metadata": df, # Pandas DataFrame with a row for each instance
"view": "audio-transcription", # The type of view for this data/task
"data_path": "/path/to/raw/data/", # The folder with raw data (images, audio, etc.)
"data_column": "id" # The column in the metadata file that contains the relative paths of files in data_path
})
```
## Learn More
Check out examples and additional documentation:
- [Introduction](https://zenoml.com/docs/intro) - Learn more about Zeno.
- [Quickstart](http://zenoml.com/docs/quickstart) - Setup Zeno with your own data and models.
- [Documentation & API](http://zenoml.com/docs/intro) - Full documentation and API reference.
Raw data
{
"_id": null,
"home_page": "https://zenoml.com",
"name": "zenoml",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8.1,<=3.11",
"maintainer_email": "",
"keywords": "ml,testing,evaluation,machine learning,ai",
"author": "\u00c1ngel Alexander Cabrera",
"author_email": "alex.cabrera@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/40/b0/038ddd9416a95c8a4526e00c6faee6e224d861d24321e3428a30ae6196be/zenoml-0.3.2.tar.gz",
"platform": null,
"description": "<img src=\"./zeno.png\" width=\"250px\"/>\n\n[](https://badge.fury.io/py/zenoml)\n\n\n[](https://lbesson.mit-license.org/) [](https://gitter.im/zeno-ml-eval/community?utm_source=badge&utm_medium=badge&utm_campaign=pr-badge&utm_content=badge)\n\nZeno is a general-purpose framework for evaluating machine learning models.\nIt combines a **Python API** with an **interactive UI** to allow users to discover, explore, and analyze the performance of their models across diverse use cases.\nZeno can be used for any data type or task with [modular views](https://zenoml.com/docs/views/) for everything from object detection to audio transcription.\n\n## Quickstart\n\nInstall the Zeno Python package from PyPI:\n\n```bash\npip install zenoml\n```\n\n### Command Line\n\nTo get started, run the following command to initialize a Zeno project. It will walk you through creating the `zeno.toml` configuration file:\n\n```bash\nzeno init\n```\n\nThen run `zeno zeno.toml`.\n\n### Jupyter Notebook\n\nYou can also run Zeno directly from Jupyter notebooks or lab. The `zeno` command takes a dictionary of configuration options as input. See [the docs](https://zenoml.com/docs/configuration) for a full list of options. In this example we pass the minimum options for exploring a non-tabular dataset:\n\n```python\nimport pandas as pd\nfrom zeno import zeno\n\ndf = pd.read_csv(\"/path/to/metadata/file.csv\")\n\nzeno({\n \"metadata\": df, # Pandas DataFrame with a row for each instance\n \"view\": \"audio-transcription\", # The type of view for this data/task\n \"data_path\": \"/path/to/raw/data/\", # The folder with raw data (images, audio, etc.)\n \"data_column\": \"id\" # The column in the metadata file that contains the relative paths of files in data_path\n})\n\n```\n\n## Learn More\n\nCheck out examples and additional documentation:\n\n- [Introduction](https://zenoml.com/docs/intro) - Learn more about Zeno.\n- [Quickstart](http://zenoml.com/docs/quickstart) - Setup Zeno with your own data and models.\n- [Documentation & API](http://zenoml.com/docs/intro) - Full documentation and API reference.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Interactive Evaluation Framework for Machine Learning",
"version": "0.3.2",
"split_keywords": [
"ml",
"testing",
"evaluation",
"machine learning",
"ai"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "0ca3df02fc1f80644699918edeccd20fcfd6c568f375c1ad8a20e843c136f0a4",
"md5": "6fbc4aa89cd64aa2c2936a239f76659c",
"sha256": "1a5fcbe6eb050f305070ac73732c634e1b1a6a8ac0b1b7dde0be3918f4c0f9d2"
},
"downloads": -1,
"filename": "zenoml-0.3.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "6fbc4aa89cd64aa2c2936a239f76659c",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8.1,<=3.11",
"size": 867062,
"upload_time": "2023-01-31T13:26:39",
"upload_time_iso_8601": "2023-01-31T13:26:39.964212Z",
"url": "https://files.pythonhosted.org/packages/0c/a3/df02fc1f80644699918edeccd20fcfd6c568f375c1ad8a20e843c136f0a4/zenoml-0.3.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "40b0038ddd9416a95c8a4526e00c6faee6e224d861d24321e3428a30ae6196be",
"md5": "c0326646656afeefdd8682bdedff77e8",
"sha256": "d1111f69d6048f6bc7fdf76e9d351854bcd2d82de6bb3bf265a4b988f9ef4da3"
},
"downloads": -1,
"filename": "zenoml-0.3.2.tar.gz",
"has_sig": false,
"md5_digest": "c0326646656afeefdd8682bdedff77e8",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.1,<=3.11",
"size": 860707,
"upload_time": "2023-01-31T13:26:41",
"upload_time_iso_8601": "2023-01-31T13:26:41.402472Z",
"url": "https://files.pythonhosted.org/packages/40/b0/038ddd9416a95c8a4526e00c6faee6e224d861d24321e3428a30ae6196be/zenoml-0.3.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-01-31 13:26:41",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "zenoml"
}