sklearn-xarray is an open-source python package that combines the n-dimensional labeled arrays of xarray with the machine learning and model selection tools of scikit-learn. The package contains wrappers that allow the user to apply scikit-learn estimators to xarray types without losing their labels.
The package documentation can be found at https://phausamann.github.io/sklearn-xarray/
- Makes sklearn estimators compatible with xarray DataArrays and Dataset.
- Allows for estimators to change the number of samples.
- Adds a large number of pre-processing transformers.
Required dependencies:
- Python 2.7, 3.4, 3.5, or 3.6
- scikit-learn (0.19 or later, depends on numpy & scipy)
- xarray (0.10 or later)
- pandas (0.20 or later)
The package can be installed from pip
:
$ pip install sklearn-xarray
For the latest version, you can also install from source:
$ git clone https://github.com/phausamann/sklearn-xarray.git $ cd sklearn-xarray $ python setup.py install
The activity recognition example demonstrates how to use the package for cross-validated grid search for an activity recognition task. The example is also present as a jupyter notebook.
Please read the contribution guide if you want to contribute to this project.