Home

Awesome

<div align="center"> <img src="figures/chronos-logo.png" width="60%">

Chronos: Learning the Language of Time Series

preprint huggingface huggingface faq License: MIT

</div>

๐Ÿš€ News

โœจ Introduction

Chronos is a family of pretrained time series forecasting models based on language model architectures. A time series is transformed into a sequence of tokens via scaling and quantization, and a language model is trained on these tokens using the cross-entropy loss. Once trained, probabilistic forecasts are obtained by sampling multiple future trajectories given the historical context. Chronos models have been trained on a large corpus of publicly available time series data, as well as synthetic data generated using Gaussian processes.

For details on Chronos models, training data and procedures, and experimental results, please refer to the paper Chronos: Learning the Language of Time Series.

<p align="center"> <img src="figures/main-figure.png" width="100%"> <br /> <span> Fig. 1: High-level depiction of Chronos. (<b>Left</b>) The input time series is scaled and quantized to obtain a sequence of tokens. (<b>Center</b>) The tokens are fed into a language model which may either be an encoder-decoder or a decoder-only model. The model is trained using the cross-entropy loss. (<b>Right</b>) During inference, we autoregressively sample tokens from the model and map them back to numerical values. Multiple trajectories are sampled to obtain a predictive distribution. </span> </p>

Architecture

The models in this repository are based on the T5 architecture. The only difference is in the vocabulary size: Chronos-T5 models use 4096 different tokens, compared to 32128 of the original T5 models, resulting in fewer parameters.

<div align="center">
ModelParametersBased on
chronos-t5-tiny8Mt5-efficient-tiny
chronos-t5-mini20Mt5-efficient-mini
chronos-t5-small46Mt5-efficient-small
chronos-t5-base200Mt5-efficient-base
chronos-t5-large710Mt5-efficient-large
</div>

Zero-Shot Results

The following figure showcases the remarkable zero-shot performance of Chronos models on 27 datasets against local models, task-specific models and other pretrained models. For details on the evaluation setup and other results, please refer to the paper.

<p align="center"> <img src="figures/zero_shot-agg_scaled_score.png" width="80%"> <br /> <span> Fig. 2: Performance of different models on Benchmark II, comprising 27 datasets <b>not seen</b> by Chronos models during training. This benchmark provides insights into the zero-shot performance of Chronos models against local statistical models, which fit parameters individually for each time series, task-specific models <i>trained on each task</i>, and pretrained models trained on a large corpus of time series. Pretrained Models (Other) indicates that some (or all) of the datasets in Benchmark II may have been in the training corpus of these models. The probabilistic (WQL) and point (MASE) forecasting metrics were normalized using the scores of the Seasonal Naive baseline and aggregated through a geometric mean to obtain the Agg. Relative WQL and MASE, respectively. </span> </p>

๐Ÿ“ˆ Usage

To perform inference with Chronos models, install this package by running:

pip install git+https://github.com/amazon-science/chronos-forecasting.git

[!TIP]
The recommended way of using Chronos for production use cases is through AutoGluon, which features ensembling with other statistical and machine learning models for time series forecasting as well as seamless deployments on AWS with SageMaker ๐Ÿง . Check out the AutoGluon Chronos tutorial.

Forecasting

A minimal example showing how to perform forecasting using Chronos models:

import pandas as pd  # requires: pip install pandas
import torch
from chronos import ChronosPipeline

pipeline = ChronosPipeline.from_pretrained(
    "amazon/chronos-t5-small",
    device_map="cuda",  # use "cpu" for CPU inference and "mps" for Apple Silicon
    torch_dtype=torch.bfloat16,
)

df = pd.read_csv("https://raw.githubusercontent.com/AileenNielsen/TimeSeriesAnalysisWithPython/master/data/AirPassengers.csv")

# context must be either a 1D tensor, a list of 1D tensors,
# or a left-padded 2D tensor with batch as the first dimension
# forecast shape: [num_series, num_samples, prediction_length]
forecast = pipeline.predict(
    context=torch.tensor(df["#Passengers"]),
    prediction_length=12,
    num_samples=20,
)

More options for pipeline.predict can be found with:

print(ChronosPipeline.predict.__doc__)

We can now visualize the forecast:

import matplotlib.pyplot as plt  # requires: pip install matplotlib
import numpy as np

forecast_index = range(len(df), len(df) + 12)
low, median, high = np.quantile(forecast[0].numpy(), [0.1, 0.5, 0.9], axis=0)

plt.figure(figsize=(8, 4))
plt.plot(df["#Passengers"], color="royalblue", label="historical data")
plt.plot(forecast_index, median, color="tomato", label="median forecast")
plt.fill_between(forecast_index, low, high, color="tomato", alpha=0.3, label="80% prediction interval")
plt.legend()
plt.grid()
plt.show()

Extracting Encoder Embeddings

A minimal example showing how to extract encoder embeddings from Chronos models:

import pandas as pd
import torch
from chronos import ChronosPipeline

pipeline = ChronosPipeline.from_pretrained(
    "amazon/chronos-t5-small",
    device_map="cuda",
    torch_dtype=torch.bfloat16,
)

df = pd.read_csv("https://raw.githubusercontent.com/AileenNielsen/TimeSeriesAnalysisWithPython/master/data/AirPassengers.csv")

# context must be either a 1D tensor, a list of 1D tensors,
# or a left-padded 2D tensor with batch as the first dimension
context = torch.tensor(df["#Passengers"])
embeddings, tokenizer_state = pipeline.embed(context)

Pretraining, fine-tuning and evaluation

Scripts for pretraining, fine-tuning and evaluating Chronos models can be found in this folder.

:floppy_disk: Datasets

Datasets used in the Chronos paper for pretraining and evaluation (both in-domain and zero-shot) are available through the HuggingFace repos: autogluon/chronos_datasets and autogluon/chronos_datasets_extra. Check out these repos for instructions on how to download and use the datasets.

๐Ÿ”ฅ Coverage

๐Ÿ“ Citation

If you find Chronos models useful for your research, please consider citing the associated paper:

@article{ansari2024chronos,
  author  = {Ansari, Abdul Fatir and Stella, Lorenzo and Turkmen, Caner and Zhang, Xiyuan and Mercado, Pedro and Shen, Huibin and Shchur, Oleksandr and Rangapuram, Syama Syndar and Pineda Arango, Sebastian and Kapoor, Shubham and Zschiegner, Jasper and Maddix, Danielle C. and Wang, Hao and Mahoney, Michael W. and Torkkola, Kari and Gordon Wilson, Andrew and Bohlke-Schneider, Michael and Wang, Yuyang},
  title   = {Chronos: Learning the Language of Time Series},
  journal = {arXiv preprint arXiv:2403.07815},
  year    = {2024}
}

๐Ÿ›ก๏ธ Security

See CONTRIBUTING for more information.

๐Ÿ“ƒ License

This project is licensed under the Apache-2.0 License.