carefree-learn

carefree-learn is a minimal Automatic Machine Learning (AutoML) solution for tabular datasets based on PyTorch.

Carefree?

carefree-learn aims to provide CAREFREE usages for both users and developers.

User Side

import cflearn
import numpy as np

x = np.random.random([1000, 10])
y = np.random.random([1000, 1])
m = cflearn.make().fit(x, y)

Developer Side

import cflearn
import numpy as np

cflearn.register_model("wnd_full", pipes=[cflearn.PipeInfo("fcnn"), cflearn.PipeInfo("linear")])
x = np.random.random([1000, 10])
y = np.random.random([1000, 1])
m = cflearn.make("wnd_full").fit(x, y)

Please refer to Quick Start and Build Your Own Models for detailed information.

Why carefree-learn?

carefree-learn

  • Provides a scikit-learn-like interface with much more 'carefree' usages, including:
    • Automatically deals with data pre-processing.
    • Automatically handles datasets saved in files (.txt, .csv).
    • Supports Distributed Training, which means hyper-parameter tuning can be very efficient in carefree-learn.
  • Includes some brand new techniques which may boost vanilla Neural Network (NN) performances on tabular datasets, including:
  • Supports many convenient functionality in deep learning, including:
    • Early stopping.
    • Model persistence.
    • Learning rate schedulers.
    • And more...
  • Full utilization of the WIP ecosystem cf*, such as:
    • carefree-toolkit: provides a lot of utility classes & functions which are 'stand alone' and can be leveraged in your own projects.
    • carefree-data: a lightweight tool to read -> convert -> process ANY tabular datasets. It also utilizes cython to accelerate critical procedures.

From the above, it comes out that carefree-learn could be treated as a minimal Automatic Machine Learning (AutoML) solution for tabular datasets when it is fully utilized. However, this is not built on the sacrifice of flexibility. In fact, the functionality we've mentioned are all wrapped into individual modules in carefree-learn and allow users to customize them easily.

Installation

carefree-learn requires Python 3.6 or higher.

Pre-Installing PyTorch

carefree-learn requires pytorch>=1.8.0. Please refer to PyTorch, and it is highly recommended to pre-install PyTorch with conda.

pip installation

After installing PyTorch, installation of carefree-learn would be rather easy:

If you pre-installed PyTorch with conda, remember to activate the corresponding environment!

pip install carefree-learn

Examples

  • Iris – perhaps the best known database to be found in the pattern recognition literature.
  • Titanic – the best, first challenge for you to dive into ML competitions and familiarize yourself with how the Kaggle platform works.
  • Operations - toy datasets for us to illustrate how to build your own models in carefree-learn.

Citation

If you use carefree-learn in your research, we would greatly appreciate if you cite this library using this Bibtex:

@misc{carefree-learn,
  year={2020},
  author={Yujian He},
  title={carefree-learn, a minimal Automatic Machine Learning (AutoML) solution for tabular datasets based on PyTorch},
  howpublished={\url{https://https://github.com/carefree0910/carefree-learn/}},
}

GitHub

https://github.com/carefree0910/carefree-learn