==============================================================
 PGBM
 Copyright 2021 Olivier Sprangers as part of Airlab Amsterdam
==============================================================

The core package makes use of:
	PyTorch: 
		PyTorch (https://pytorch.org/)
		Copyright (c) 2016-     Facebook, Inc            (Adam Paszke)
		Copyright (c) 2014-     Facebook, Inc            (Soumith Chintala)
		Copyright (c) 2011-2014 Idiap Research Institute (Ronan Collobert)
		Copyright (c) 2012-2014 Deepmind Technologies    (Koray Kavukcuoglu)
		Copyright (c) 2011-2012 NEC Laboratories America (Koray Kavukcuoglu)
		Copyright (c) 2011-2013 NYU                      (Clement Farabet)
		Copyright (c) 2006-2010 NEC Laboratories America (Ronan Collobert, Leon Bottou, Iain Melvin, Jason Weston)
		Copyright (c) 2006      Idiap Research Institute (Samy Bengio)
		Copyright (c) 2001-2004 Idiap Research Institute (Ronan Collobert, Samy Bengio, Johnny Mariethoz)
	
	Numpy:
		Numpy(https://github.com/numpy/numpy)
		Copyright (c) 2005-2021, NumPy Developers.
	
	
	Pandas:
		Pandas(https://github.com/pandas-dev/pandas)
		Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team. All rights reserved.
		Copyright (c) 2011-2021, Open source contributors.
	
	Numba:
		Numba (http://numba.pydata.org/)
		Copyright (c) 2012, Anaconda, Inc.

In the experimental section the following additional packages are used:
	LightGBM (https://github.com/microsoft/LightGBM)
	Copyright (c) Microsoft Corporation

	Scikit-learn (https://github.com/scikit-learn/scikit-learn)
	Copyright (c) 2007-2020 The scikit-learn developers.

	Properscoring (https://github.com/TheClimateCorporation/properscoring)
	Copyright (c) 2015 The Climate Corporation
		
	NGBoost (https://github.com/stanfordmlgroup/ngboost)
	Copyright (c) 2019 Tony Duan, Anand Avati, Daisy Yi Ding, Khanh K. Thai, Sanjay Basu, Andrew Y. Ng, Alejandro Schuler

	Matplotlib (https://matplotlib.org/)
	Copyright (c) 2002 - 2012 John Hunter, Darren Dale, Eric Firing, Michael Droettboom and the Matplotlib development team.
	Copyright (c) 2012 - 2021 The Matplotlib development team. 

We use the following datasets from the UCI Machine Learning Repository:
	* [yacht](https://archive.ics.uci.edu/ml/datasets/yacht+hydrodynamics)
	* [boston](https://archive.ics.uci.edu/ml/machine-learning-databases/housing/)
	* [energy](https://archive.ics.uci.edu/ml/datasets/energy+efficiency)
	* [concrete](https://archive.ics.uci.edu/ml/machine-learning-databases/concrete/compressive/)
	* [wine](https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/)
	* [power](https://archive.ics.uci.edu/ml/datasets/combined+cycle+power+plant)
	* [naval](http://archive.ics.uci.edu/ml/datasets/condition+based+maintenance+of+naval+propulsion+plants)
	* [protein](https://archive.ics.uci.edu/ml/datasets/Physicochemical+Properties+of+Protein+Tertiary+Structure)
	* [msd](https://archive.ics.uci.edu/ml/datasets/YearPredictionMSD)
	* [higgs](https://archive.ics.uci.edu/ml/datasets/HIGGS) (pre-download and extract to pgbm/datasets)

We use the following datasets from the openml archive:
	* [kin8nm](https://www.openml.org/d/189)

We use the following datasets from Kaggle:
	* [m5](https://www.kaggle.com/c/m5-forecasting-accuracy/data) (pre-download and extract to pgbm/datasets/m5)


