Fully automated machine learning in one-liners.
Project description
Fully Automated Machine Learning in One-Liners
Libra is a deep learning API that allows users to use machine learning in their workflows in fluent one-liners. It is written in Python and TensorFlow and makes training neural networks as simple as a one line function call. It was written to make deep learning as simple as possible to every user.
Installation
Install latest release version:
pip install -U libra
Install directory from github:
git clone https://github.com/Palashio/libra.git
cd libra
pip install .
From Conda:
conda install libra -c conda-forge
Usage: the basics
A new client object should be created for every dataset that you're working with. This is where the results of your models for the dataset will be stored.
You can then call different queries on that client object, and the dataset you passed to it will be used.
from libra.queries import client
newClient = client('path/to/dataset')
newClient.neural_network_query('please model the median number of households')
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.