Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of chronos-forecasting

chronos-forecasting - 1.5.3

What's Changed

  • Fix issue with new caching mechanism in transformers and bump versions by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/313

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.5.2...v1.5.3

- Python
Published by abdulfatir 7 months ago

chronos-forecasting - 1.5.2

v1.5.2 relaxes the upper bound on accelerate to <2.

What's Changed

  • Bump accelerate>=0.32,<2 by @Tyler-Hardin in https://github.com/amazon-science/chronos-forecasting/pull/298
  • Bump version to 1.5.2 by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/299

New Contributors

  • @Tyler-Hardin made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/298

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.5.1...v1.5.2

- Python
Published by abdulfatir 10 months ago

chronos-forecasting - 1.5.1

🐛 Fixed an issue with forecasting constant series for Chronos-Bolt. See #294.

What's Changed

  • Bump transformers to >=4.48 by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/280
  • Add example notebook for SageMaker JumpStart by @shchur in https://github.com/amazon-science/chronos-forecasting/pull/281
  • Fix date in readme by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/284
  • Fix scaling that affects constant series by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/294
  • Fix type-checking issues by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/295

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.5.0...v1.5.1

- Python
Published by abdulfatir 11 months ago

chronos-forecasting - 1.5.0

What's Changed

  • Fix training install instructions by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/236
  • remove eval-pr-comment workflow by @canerturkmen in https://github.com/amazon-science/chronos-forecasting/pull/239
  • Add pipeline.embed support for Chronos-Bolt by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/247
  • Update issue templates by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/269
  • Relax torch compatibility to <3 by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/277
  • Bump package version to 1.5.0 by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/278

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.4.1...v1.5.0

- Python
Published by lostella about 1 year ago

chronos-forecasting - 1.4.1

What's Changed

  • Fix padding for int contexts by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/227
  • Bump version number to 1.4.1 by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/228

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.4.0...v1.4.1

- Python
Published by lostella about 1 year ago

chronos-forecasting - 1.4.0

Key Changes

  • predict and predict_quantiles will return predictions on cpu in float32.

What's Changed

  • Remove reference to MPS by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/216
  • Run type checks on Python 3.11 only by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/217
  • Clean up evaluation script by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/218
  • Return predictions in fp32 on CPU by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/219
  • Fix README example to use predict_quantiles by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/220
  • Add workflow to run evaluation on a subset of datasets by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/222
  • Fix auto eval workflow by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/224
  • Use absolute link to images in the README by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/223
  • Bump version to 1.4.0 by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/225

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.3.0...v1.4.0

- Python
Published by abdulfatir about 1 year ago

chronos-forecasting - 1.3.0

Highlight

Chronos-Bolt⚡: a 250x faster, more accurate Chronos model

Chronos-Bolt is our latest foundation model for forecasting. It is based on the T5 encoder-decoder architecture and has been trained on nearly 100 billion time series observations. It chunks the historical time series context into patches of multiple observations, which are then input into the encoder. The decoder then uses these representations to directly generate quantile forecasts across multiple future steps—a method known as direct multi-step forecasting. Chronos-Bolt models are up to 250 times faster and 20 times more memory-efficient than the original Chronos models of the same size.

The following plot compares the inference time of Chronos-Bolt against the original Chronos models for forecasting 1024 time series with a context length of 512 observations and a prediction horizon of 64 steps.

Chronos-Bolt models are not only significantly faster but also more accurate than the original Chronos models. The following plot reports the probabilistic and point forecasting performance of Chronos-Bolt in terms of the Weighted Quantile Loss (WQL) and the Mean Absolute Scaled Error (MASE), respectively, aggregated over 27 datasets (see the Chronos paper for details on this benchmark). Remarkably, despite having no prior exposure to these datasets during training, the zero-shot Chronos-Bolt models outperform commonly used statistical models and deep learning models that have been trained on these datasets (highlighted by *). Furthermore, they also perform better than other FMs, denoted by a +, which indicates that these models were pretrained on certain datasets in our benchmark and are not entirely zero-shot. Notably, Chronos-Bolt (Base) also surpasses the original Chronos (Large) model in terms of the forecasting accuracy while being over 600 times faster.

Chronos-Bolt models are now available on HuggingFace🤗 in four sizes—Tiny (9M), Mini (21M), Small (48M), and Base (205M)—and can also be used on the CPU. Check out the example in the README to learn how to use Chronos-Bolt models. You can use Chronos-Bolt models for forecasting in just a few lines of code.

```py import pandas as pd # requires: pip install pandas import torch from chronos import BaseChronosPipeline

pipeline = BaseChronosPipeline.frompretrained( "amazon/chronos-bolt-base", devicemap="cuda", # use "cpu" for CPU inference 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

Chronos-Bolt models generate quantile forecasts, so forecast has shape

[numseries, numquantiles, prediction_length].

forecast = pipeline.predict( context=torch.tensor(df["#Passengers"]), prediction_length=12 ) ```

[!NOTE] We have also integrated Chronos-Bolt models into AutoGluon which is a more feature complete way of using Chronos models for production use cases. With the addition of Chronos-Bolt models and other enhancements, AutoGluon v1.2 achieves a 70%+ win rate against AutoGluon v1.1! In addition to the new Chronos-Bolt models, AutoGluon 1.2 also enables effortless fine-tuning of Chronos and Chronos-Bolt models. Check out the updated Chronos AutoGluon tutorial to learn how to use and fine-tune Chronos-Bolt models using AutoGluon.

What's Changed

  • Cap transformers <4.41 by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/77
  • Save training job info by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/80
  • Relax torch and transformers versions by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/81
  • Split input_transform into context_input_transform and label_input_transform by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/82
  • Fix citation by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/86
  • Enhance training script: auto tf32 detection and reorder default seed setting by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/91
  • Uncap transformers dependency by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/94
  • Update ci.yml with schedule by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/95
  • Add FAQ badge to README by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/97
  • Remove print statements from train.py by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/101
  • Add issue templates by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/109
  • Add support for causal models by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/113
  • Set drop_prob = 0 for causal models by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/125
  • Add evaluation script by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/134
  • Update README.md with dataset and evaluation details by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/136
  • Add datasets badge by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/137
  • Add generation params to eval script by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/138
  • Bound number of workers by number of datasets by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/157
  • Simplify pretraining README snippet by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/160
  • Fix number of quantisation buckets by @alvaropp in https://github.com/amazon-science/chronos-forecasting/pull/182
  • Force context scaling and quantization in float32, add assertions to tests by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/197
  • Update README.md by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/206
  • :zap: Add support for Chronos-Bolt models by @abdulfatir @canerturkmen @lostella in https://github.com/amazon-science/chronos-forecasting/pull/204
  • Update project information and workflows by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/214

New Contributors

  • @alvaropp made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/182

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.2.0...v1.3.0

- Python
Published by abdulfatir about 1 year ago

chronos-forecasting - 1.2.0

What's Changed

  • Remove Unnecessary F-strings by @pixeeai in https://github.com/amazon-science/chronos-forecasting/pull/34
  • Fix types, add mypy to workflow by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/42
  • Speed up workflow by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/43
  • Simplify tokenizer creation by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/44
  • Update README.md by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/46
  • Add CITATION.cff by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/48
  • Revamp README: Add News, Coverage, Logo, Shields, Emojis, Zero-Shot results by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/56
  • add AGv1.1 announcement to README by @canerturkmen in https://github.com/amazon-science/chronos-forecasting/pull/58
  • Add training script by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/63
  • Add KernelSynth script by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/64
  • Add missing headers by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/65
  • Merge kernel-synth extra into training by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/66
  • Add a README file for the scripts by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/67
  • Update README examples by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/68
  • Add details on pushing model to huggingface hub by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/69
  • Add one space after --config in training readme by @huibinshen in https://github.com/amazon-science/chronos-forecasting/pull/71
  • Use logo with transparent background by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/72
  • Fix output transform, add test to enforce tokenizer consistency by @HugoSenetaire in https://github.com/amazon-science/chronos-forecasting/pull/73
  • Update README and bump version by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/74

New Contributors

  • @pixeeai made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/34
  • @canerturkmen made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/58
  • @huibinshen made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/71
  • @HugoSenetaire made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/73

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.1.0...v1.2.0

- Python
Published by abdulfatir almost 2 years ago

chronos-forecasting - 1.1.0

What's Changed

  • Speed up inference by avoiding unnecessary padding by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/25
  • Add pipeline.embed by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/24
  • Bump package version to 1.1 by @lostella in https://github.com/amazon-science/chronos-forecasting/pull/27

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/v1.0.0...v1.1.0

- Python
Published by lostella almost 2 years ago

chronos-forecasting - 1.0.0

Initial release

What's Changed

  • Update chronos.py - model.device by @michaelfeil in https://github.com/amazon-science/chronos-forecasting/pull/11
  • Add optional inference params to example by @abdulfatir in https://github.com/amazon-science/chronos-forecasting/pull/15

New Contributors

  • @michaelfeil made their first contribution in https://github.com/amazon-science/chronos-forecasting/pull/11

Full Changelog: https://github.com/amazon-science/chronos-forecasting/compare/paper-release...v1.0.0

- Python
Published by lostella almost 2 years ago