Metadata-Version: 2.1
Name: cooka
Version: 0.1.2
Summary: A lightweight AutoML system.
Home-page: UNKNOWN
Author: DataCanvas Community
Author-email: yangjian@zetyun.com
License: Apache License 2.0
Platform: Linux
Platform: Mac OS X
Classifier: Operating System :: OS Independent
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: License :: OSI Approved :: Apache Software License
Requires-Python: >=3.6.*
Description-Content-Type: text/markdown
Requires-Dist: numpy
Requires-Dist: pandas
Requires-Dist: scikit-learn (>=0.22.1)
Requires-Dist: requests
Requires-Dist: SQLAlchemy (>=1.3.18)
Requires-Dist: tornado (==6.0.4)
Requires-Dist: jinja2
Requires-Dist: deeptables (==0.1.13)
Requires-Dist: hypergbm (==0.2.2)
Requires-Dist: traitlets

# Cooka
[![Python Versions](https://img.shields.io/pypi/pyversions/cooka.svg)](https://pypi.org/project/hypergbm)
[![Downloads](https://pepy.tech/badge/cooka)](https://pepy.tech/project/hypergbm)
[![PyPI Version](https://img.shields.io/pypi/v/cooka.svg)](https://pypi.org/project/hypergbm)

[Doc](https://cooka.readthedocs.io) | [简体中文](README_zh_CN.md)

Cooka is a lightweight and visualization toolkit to manage datasets and design model learning experiments through web UI.
It using [DeepTables](https://github.com/DataCanvasIO/DeepTables) and [HyperGBM](https://github.com/DataCanvasIO/HyperGBM) as experiment engine to complete feature engineering, neural architecture search and hyperparameter tuning automatically.

<img src="docs/static/datacanvas_automl_toolkit.png" alt="drawing" width="700" height="450"/>

## Features overview 
Through the web UI provided by cooka you can:

- Add and analyze datasets
- Design experiment
- View experiment process and result
- Using models
- Export experiment to jupyter notebook 

Screen shots：
<table style="border: none">
    <th><img src="docs/static/cooka_home_page.png" width="500"/></th>
    <th><img src="docs/static/cooka_train.gif" width="500"/></th>
</table>

The machine learning algorithms supported are ：
- XGBoost
- LightGBM
- Catboost

The neural networks supported are：
- WideDeep
- DeepFM
- xDeepFM
- AutoInt
- DCN
- FGCNN 
- FiBiNet
- PNN
- AFM
- [...](https://deeptables.readthedocs.io/en/latest/models.html)


The search algorithms supported are：
- Evolution
- MCTS(Monte Carlo Tree Search)
- [...](https://github.com/DataCanvasIO/HyperGBM)

The supported feature engineering provided by  [scikit-learn](https://scikit-learn.org) and [featuretools](https://github.com/alteryx/featuretools) are：

- Scaler
    - StandardScaler
    - MinMaxScaler
    - RobustScaler
    - MaxAbsScaler
    - Normalizer

- Encoder
    - LabelEncoder
    - OneHotEncoder
    - OrdinalEncoder

- Discretizer
    - KBinsDiscretizer
    - Binarizer

- Dimension Reduction
    - PCA

- Feature derivation
    - featuretools

- Missing value filling
    - SimpleImputer 

It can also extend the search space to support more feature engineering methods and modeling algorithms.

## Installation 

### Using pip

The python version should be >= 3.6, for CentOS , install the system package:

```shell script
pip install --upgrade pip
pip install cooka
```

Start the web server：
```shell script
cooka server
```

Then open `http://<your_ip:8000>` with your browser to use cooka.

By default, the cooka configuration file is at `~/.config/cooka/cooka.py`,  to generate a template:
```shell script
mkdir -p ~/.config/cooka/
cooka generate-config > ~/.config/cooka/cooka.py
```

### Using Docker

Launch a Cooka docker container:

```shell script
docker run -ti -p 8888:8888 -p 8000:8000 -p 9001:9001 -e COOKA_NOTEBOOK_PORTAL=http://<your_ip>:8888 datacanvas/cooka:latest
```

Open `http://<your_ip:8000>` with your browser to visit cooka.

## DataCanvas

![](docs/static/dc_logo_1.png)

Cooka is an open source project created by [DataCanvas](https://www.datacanvas.com/). 




