User Guide

You will find here some more detailed information about Darts.

Note: The user guide is not yet complete and still under construction.

• TimeSeries
  • Multivariate time series -vs- multiple time series
  • Probabilistic and deterministic series
  • Creating TimeSeries
  • Implementation
  • Exporting data from a TimeSeries
  • Static Covariates
  • Hierarchical Time Series
  • More information and documentation
• Overview of Forecasting Models
  • Generalities
  • Saving and Loading Models
  • Support for multivariate series
  • Handling multiple series
  • Support for Covariates
  • Probabilistic forecasts
• Torch Forecasting Models
  • Content of this guide
  • Introduction
  • Top level look at training and predicting with chunks
  • Torch Forecasting Model Covariates Support
  • Required target time spans for training, validation and prediction
  • In-depth look at how input data is used when training and predicting with TFMs
  • Forecast/Prediction
  • Advanced Functionnalities
  • Performance Recommendations
• Using Torch Models with GPUs and TPUs
  • Use CPU
  • Use a GPU
  • Use a TPU
• Covariates
  • Summary - TL;DR
  • Introduction - What are covariates (in Darts)?
  • Forecasting Model Covariate Support
  • Quick guide on how to use past and/or future covariates with Darts’ forecasting models
  • Covariate time span requirements for Local and Global Forecasting Models
  • Examples
• Hyperparameter Optimization in Darts
  • Hyperparameter optimization with Optuna
  • Hyperparameter optimization with Ray Tune
  • Hyperparameter optimization using gridsearch()
• Frequently Asked Questions

previous

Quickstart

next

TimeSeries