Version 1 Release¶
We currently only support annual forecasts, but our focus is to support sub-annual (e.g., seasonal, monthly, weekly, daily) in our next major release (v2.0.0). We provide a host of deterministic metrics, as well as some probabilistic metrics, although the latter have not been tested rigorously. We support both perfect-model and hindcast prediction ensembles, and provide PerfectModelEnsemble
and HindcastEnsemble
classes to make analysis easier.
See quick start and our examples to get started.
Installation¶
You can install the latest release of climpred
using pip
or conda
:
pip install climpred
conda install -c conda-forge climpred
You can also install the bleeding edge (pre-release versions) by cloning this repository and running pip install . --upgrade
in the main directory
Getting Started
User Guide
- Setting Up Your Dataset
- PredictionEnsemble Objects
- Comparisons
- Metrics
- Prediction Terminology
- Baseline Forecasts
Help & Reference
- API Reference
- What’s New
- Helpful Links
- Publications Using climpred
- Contribution Guide
- Release Procedure
- Contributors