Skip to content
A minimalist framework to streamline the work with PyTorch
Branch: master
Clone or download


Build Status PyPI version

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 but runs on Pytorch and gives you full control of what you can do.


Learn more Lightwood's docs

Quick start

pip3 install lightwood


You can train a Predictor as follows:

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


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

prediction = sensor3_predictor.predict(when={'sensor1':1, 'sensor2':-1})
You can’t perform that action at this time.