Chronos User Guide

1. Overview

BigDL-Chronos (Chronos for short) is an application framework for building a fast, accurate and scalable time series analysis application.

You can use Chronos to do:

• Data pre/post-processing and feature generation (using TSDataset)

• Time Series Forecasting (using Standalone Forecasters, Auto Models (with HPO) or AutoTS (full AutoML enabled pipelines))

• Anomaly Detection (using Anomaly Detectors)

• Synthetic Data Generation (using Simulators)

• Speed up or tune your customized time-series model (using TSTrainer and AutoTS)

---

2. Install

Functionality	Forecasting	Anomaly Detection		Simulation
Model	Deep learning models	Prophet		ARIMA
DL framework	PyTorch (Recommended)		Tensorflow
OS	Linux		Windows
Auto Tuning	No		Yes
Hardware	Single node		Cluster
Package	Pip		Docker
Version	Nightly (2.1.0b)		Stable (2.0.0)
Install CMD	NA

2.1 Pypi

When you install bigdl-chronos from PyPI. We recommend to install with a conda virtual environment. To install Conda, please refer to here.

conda create -n my_env python=3.7 setuptools=58.0.4
conda activate my_env
pip install --pre --upgrade bigdl-chronos[pytorch]  # or other options you may want to use
source bigdl-nano-init

2.2 Tensorflow backend

Tensorflow is one of the supported backend of Chronos in nightly release version, while it can not work alone without pytorch in Chronos for now. We will fix it soon. If you want to use tensorflow backend, please

pip install --pre --upgrade bigdl-nano[tensorflow]

after you install the pytorch backend chronos.

2.3 OS and Python version requirement

Note

Supported OS:

Chronos is thoroughly tested on Ubuntu (16.04/18.04/20.04), and should works fine on CentOS. If you are a Windows user, the most convenient way to use Chronos on a windows laptop might be using WSL2, you may refer to https://docs.microsoft.com/en-us/windows/wsl/setup/environment or just install a ubuntu virtual machine.

Note

Supported Python Version:

Chronos only supports Python 3.7.2 ~ latest 3.7.x. We are validating more Python versions.

---

3. Which document to see?

Quick Tour

You may understand the basic usage of Chronos’ components and learn to write the first runnable application in this quick tour page.

Quick Tour

User Guides

Our user guides provide you with in-depth information, concepts and knowledges about Chronos.

Data process / Forecast / Detect / Simulate

How-to-Guide

If you are meeting with some specific problems during the usage, how-to guides are good place to be checked.

Work In Progress

API Document

API Document provides you with a detailed description of the Chronos APIs.

API Document

---

4. Examples and Demos

• Quickstarts

  • Use AutoTSEstimator for Time-Series Forecasting

  • Use TSDataset and Forecaster for Time-Series Forecasting

  • Use Anomaly Detector for Unsupervised Anomaly Detection

• Examples

  • Use AutoLSTM on nyc taxi dataset

  • Use AutoProphet on nyc taxi dataset

  • High dimension time series forecasting with Chronos TCMFForecaster

  • Use distributed training with Chronos Seq2SeqForecaster

  • Use ONNXRuntime to accelerate the inference of AutoTSEstimator

  • Use ONNXRuntime to accelerate the inference of Seq2SeqForecaster

  • Generate synthetic data with DPGANSimulator in a data-driven fashion

  • Quantizate your forecaster to speed up inference

• Use cases

  • Unsupervised Anomaly Detection

  • Unsupervised Anomaly Detection based on Forecasts

  • Stock Price Prediction with LSTM

  • Stock Price Prediction with ProphetForecaster and AutoProphet

  • Network Traffic Forecasting with AutoTSEstimator

  • Network Traffic Forecasting (using multivariate time series data)

  • Network Traffic Forecasting (using multistep time series data)

  • Network Traffic Forecasting with Customized Model

  • Help pytorch-forecasting improve the training speed of DeepAR model

  • Help pytorch-forecasting improve the training speed of TFT model