Package `python_scripts`

This directory contains Python scripts for processing, analyzing, and generating models for soil science as part of the AgReFed project. The software was developed by the Sydney Informatics Hub, a core research facility of the University of Sydney, as part of the project Mechanistic and data-driven models under uncertainty for agricultural systems for the Agricultural Research Federation (AgReFed). https://github.com/Sydney-Informatics-Hub/AgReFed-ML

Expand source code

# This directory contains Python scripts for processing, analyzing, and generating models for soil science.

__title__ = "AgReFed-ML: Machine learning tools for modelling and predicting agriculture systems and their uncertainties"
__description__ = """
This directory contains Python scripts for processing, analyzing, and generating models for soil science
as part of the AgReFed project.
The software was developed by the Sydney Informatics Hub, a core research facility of the University of Sydney, 
as part of the project Mechanistic and data-driven models under uncertainty for agricultural systems for the 
Agricultural Research Federation (AgReFed).
"""
__uri__ = "https://github.com/Sydney-Informatics-Hub/AgReFed-ML"
__doc__ = __description__ + " <" + __uri__ + ">"
__version__ = "0.2.0"

__author__ = "Sebastian Haan"
__license__ = "LGPL-3.0 License"

Sub-modules

python_scripts.GPmodel: Custom kernel library for Gaussian Processes including sparse kernels and cross-covariance terms …
python_scripts.model_blr: Bayesian Linear Regression with uncertainty estimates and feature importance …
python_scripts.model_rf: Random Forest Model with uncertainty estimates and feature importance …
python_scripts.preprocessing: Preprocessing functions for geospatial soil data …
python_scripts.sigmastats: Functions for calculating multiple statistics with uncertainties.
python_scripts.soilmod_predict: Machine Learning model for 3D Cube Soil Generator using Gaussian Process Priors with mean functions …
python_scripts.soilmod_predict_change: Machine Learning model for Change prediction and uncertainties using Gaussian Processes …
python_scripts.soilmod_predict_st: Machine Learning model for spatial-temporal soil mapping using Gaussian Process Priors with mean functions …
python_scripts.soilmod_xval: Probabilistic machine learning models and evaluation using Gaussian Process Priors with mean functions …
python_scripts.synthgen: Toolset for generating geospatial synthetic data-sets with multiple features, noise and spatial correlations …
python_scripts.utils: Some utility functions …