*Issue #, if available:*
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:*
Just increased the max version allowed. Tests pass.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir <Abdulfatirs@gmail.com>
*Issue #, if available:* See example build
https://github.com/amazon-science/chronos-forecasting/actions/runs/14302765904/job/40313421985
*Description of changes:*
- Address type-checker complaints, where possible
- Bump bugfix version of the package
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:*
- Add pointers to fev and JumpStart notebook in the README
- Add notebook describing how to deploy Chronos with SageMaker JumpStart
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:* Solves #273
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* remove blank issue button, update description
of link to discussions
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:* Fixes#235
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:* On Linux, the final call to `.to` creates
trouble when input tensors are integer. For example:
```
>>> a = torch.tensor([1])
>>> b = torch.stack([torch.full((1,), torch.nan), a])
>>> b
tensor([[nan],
[1.]])
>>> b.to(a)
tensor([[-9223372036854775808],
[ 1]])
```
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:* Title.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:*
*Description of changes:* This PR uses absolute link to the images so
they show up correct on other places such as PyPi.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:* This PR fixes the auto evaluation workflow.
The second workflow step did not work because it did not know the right
PR number to post the comment on. The fix is to include the PR number in
the CSV file name and read it in the second workflow.
PS: This is a really poor user experience because there's no way to test
that this works right without merging!
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:*
*Description of changes:* This PR adds a workflow that will run the
evaluation script on `chronos-bolt-small` for a subset of datasets
specified in `ci/evaluate/backtest_configs.yaml`. After evaluation, a
comment will be made on the PR. The workflow will only run if the
`run-eval` label is present on a PR. The end-to-end workflow has been
split into two workflows:
- `eval-model.yml`: only has read access (can be run from forks). This
will evaluate the model and upload the metrics CSV file as a Github
artifact.
- `eval-pr-comment.yml`: has read and write access (can only be run when
in the `main` branch). This will be triggered when the first job
finishes, will download the CSV from the eval job and make the comment.
According to [this
post](https://securitylab.github.com/resources/github-actions-preventing-pwn-requests/),
splitting into two jobs as done here is the recommended and secure way
to do this.
**NOTE**: The first steps works as expected, but we can only test the
second step after the merging because this workflow needs to be part of
the `main` branch for this to work.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:*
*Description of changes:* `predict` returns different things based on
model type. This fixes the example to use `predict_quantiles` which will
give correct quantiles.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:* N/A
*Description of changes:* This PR ensures that predictions are returned
in FP32 and on the CPU device. This choice is now better because we have
two types of models which have different types of forecasts (samples vs.
quantiles). Furthermore, `int64` input_type (our README example is one
such case) ran into issues with `predict_quantiles` before. This choice
also fixes that.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:*
*Description of changes:* This PR cleans up eval script by using
`DateTimeIndex.to_period()` instead of the ugly frequency mapping. Not
sure what I was doing before. 🫠
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:*
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:*
*Description of changes:* MPS mostly causes issues for users, so let's
remove the reference to MPS from the README. Plus, Chronos-Bolt models
currently fail on MPS.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Description of changes:* This PR updates project information and
workflows to allow for PyPi release.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Issue #, if available:* N/A
*Description of changes:* This PR adds support for Chronos-Bolt models.
TODOs:
- [x] Update evaluation script
- [x] Fix and add tests for Bolt
- [x] Update docstrings
- [x] Update README example and mention Chronos-Bolt
- [x] Update results bar plot in README
- [x] Add versions for libraries in `pyproject.toml`
- [x] Check that the training and eval scripts work
- [x] Change `autogluon` -> `amazon` in model names
Post Merge:
- [ ] Update Citation style in README, both Github and HuggingFace repos
- [ ] Remove note about AutoGluon
- [ ] Update READMEs of original Chronos models to refer to Chronos-Bolt
NOTE: To be merged after Chronos-Bolt models are available under the
`amazon` namespace on HF.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
Co-authored-by: Caner Turkmen <turkmen.ac@gmail.com>
Co-authored-by: Lorenzo Stella <stellalo@amazon.com>
*Issue #, if available:*
*Description of changes:* Update README.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:* Fixes#193
*Description of changes:* Passing in contexts in lower precision than
float32 may result in a drop of accuracy. This change ensures that the
tokenizer (which does scaling and quantization) operates on a float32
batch.
Tested across GPU/CPU and different context dtypes with
```python
from itertools import product
import pandas as pd
import torch
from chronos import ChronosPipeline
import matplotlib.pyplot as plt # requires: pip install matplotlib
import numpy as np
df = pd.read_csv("https://raw.githubusercontent.com/AileenNielsen/TimeSeriesAnalysisWithPython/master/data/AirPassengers.csv")
for context_dtype, context_device, model_dtype, model_device in product(
[torch.bfloat16, torch.float16, torch.float32],
["cpu"], # only cpu input supported at the moment
[torch.bfloat16, torch.float16, torch.float32],
["cpu", "cuda"],
):
pipeline = ChronosPipeline.from_pretrained(
"amazon/chronos-t5-tiny",
device_map=model_device,
torch_dtype=model_dtype,
)
forecast = pipeline.predict(
context=torch.tensor(df["#Passengers"]).to(dtype=context_dtype, device=context_device),
prediction_length=65,
num_samples=20,
limit_prediction_length=False,
)
assert forecast.dtype == context_dtype, f"{forecast.dtype=} but {context_dtype=}"
assert str(forecast.device) == context_device, f"{forecast.device=} but {context_device=}"
forecast_index = range(len(df), len(df) + 65)
low, median, high = np.quantile(forecast[0].to(device="cpu", dtype=torch.float32).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()
```
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Fixes https://github.com/amazon-science/chronos-forecasting/issues/181.
Chronos' tokenizer has a vocabulary size of `n_tokens`. Among these,
there are `n_special_tokens` reserved for EOS, PAD, etc. and `n_tokens -
n_special_tokens` allocated to numerical values. However, the provided
`MeanScaleUniformBins` tokenizer creates` n_tokens - n_special_tokens +
1` different buckets, resulting in a total of `n_tokens + 1` possible
tokens. This causes training and inference errors when one of the data
points gets allocated to the largest bucket, as the model requires 0 <=
token_id < n_tokens.
This PR modifies the `MeanScaleUniformBins` tokenizer, so that it
creates one less bucket for numerical values.
---
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Lorenzo Stella <lorenzostella@gmail.com>
*Issue #, if available:*
*Description of changes:*
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Issue #, if available:* Fixes#154
*Description of changes:* Prior to the fix, some workers have no dataset
to consume if `dataloader_num_workers > len(training_data_paths)`.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* Adds generation params to command line options
for the evaluation script.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* Title.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* This PR updates README.md with dataset and
evaluation details
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* This PR adds configs and a script to evaluate
Chronos models in the same way as described in the paper.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Description of changes:* This PR sets `drop_prob = 0` when training
causal models. Missing values are problematic for causal model training.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* This PR adds support for training
causal/decoder-only models.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Description of changes:* adding templates for GitHub issues.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* Removes print statements that got left inside
from a debugging session.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
*Description of changes:* Run CI at 8 AM UTC every day.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
Co-authored-by: Lorenzo Stella <stellalo@amazon.com>
*Description of changes:* Automatically set `tf32` to `False` if used on
an older NVIDIA GPU. Reorder seed so that the seed is saved as part of
the training config.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
---------
Co-authored-by: Abdul Fatir Ansari <ansarnd@amazon.de>
*Description of changes:* Updates the citation.
By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.
