Metadata-Version: 2.1
Name: lightwood
Version: 0.7.3
Summary: Lightwood's goal is to make it very simple for developers to use the power of artificial neural networks in their projects.
Home-page: https://github.com/mindsdb/lightwood
Author: MindsDB Inc
Author-email: jorge@mindsdb.com
License: MIT
Download-URL: https://pypi.org/project/lightwood
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Requires-Python: >=3.6
Description-Content-Type: text/markdown
Requires-Dist: NLTK (>=3)
Requires-Dist: cesium (>=0.9.9)
Requires-Dist: dill (>=0.2.9)
Requires-Dist: numpy (>=1.16.2)
Requires-Dist: pandas (>=0.23.4)
Requires-Dist: schema (>=0.6.8)
Requires-Dist: sklearn (>=0.0)
Requires-Dist: torch (>=1.1.0.post2)
Requires-Dist: torchvision (>=0.3)
Requires-Dist: xlrd (>=1.0.0)


![Lightwood](https://mindsdb.github.io/lightwood/assets/logo.png)
#

[![Build Status](https://travis-ci.org/mindsdb/lightwood.svg?branch=master)](https://travis-ci.org/mindsdb/lightwood)
[![PyPI version](https://badge.fury.io/py/lightwood.svg)](https://badge.fury.io/py/lightwood)

Lightwood has two objectives:

- Make it so simple that you can build predictive models with a line of code.
- Make it so flexible that you can change and customize everything.

Lightwood was inspired on [Ludwig](https://github.com/uber/ludwig) but runs on Pytorch and gives you full control of what you can do.

# Documentation
Learn more  [Lightwood's docs](https://mindsdb.github.io/lightwood/API/)  

# Quick start
```python
pip3 install lightwood
```

### Learn

You can train a Predictor as follows:

```python
from lightwood import Predictor
sensor3_predictor = Predictor(output=['sensor3']).learn(from_data=pandas.read_csv('sensor_data.csv'))

```

### Predict

You can now given new readings from *sensor1* and *sensor2* predict what *sensor3* will be.

```python

prediction = sensor3_predictor.predict(when={'sensor1':1, 'sensor2':-1})

```


