Data

Tools

Indexes

Applications

Experiments

Open Source Science

Recent Releases of https://github.com/nixtla/nixtla

https://github.com/nixtla/nixtla - v0.7.0

What's Changed

  • chore: v0.6.7.dev1 by @Yibei990826 in https://github.com/Nixtla/nixtla/pull/630
  • Adjust model input size validation logic, add devcontainer by @goodwanghan in https://github.com/Nixtla/nixtla/pull/632
  • Update package version by @goodwanghan in https://github.com/Nixtla/nixtla/pull/633
  • Relax supported model check by @goodwanghan in https://github.com/Nixtla/nixtla/pull/634
  • feat: new date features tutorial by @ngupta23 in https://github.com/Nixtla/nixtla/pull/653
  • Migrate docs by @loama in https://github.com/Nixtla/nixtla/pull/656
  • Remove nbdev for core developments and use pytest for tests by @JQGoh in https://github.com/Nixtla/nixtla/pull/647
  • CHORE: add nodejs to codespace by @marcopeix in https://github.com/Nixtla/nixtla/pull/658
  • DOCS: Faq and about fixes by @marcopeix in https://github.com/Nixtla/nixtla/pull/657
  • FIX: Add closing steps tag by @marcopeix in https://github.com/Nixtla/nixtla/pull/659
  • add posthog to analytics in mintlify by @loama in https://github.com/Nixtla/nixtla/pull/660
  • [FEAT] Reduce minimum required size for finetuning and fix testing failures by @elephaint in https://github.com/Nixtla/nixtla/pull/640
  • New documentation pipeline by @deven367 in https://github.com/Nixtla/nixtla/pull/663
  • test for staging docs by @deven367 in https://github.com/Nixtla/nixtla/pull/664
  • Release 0.7.0 by @goodwanghan in https://github.com/Nixtla/nixtla/pull/665

New Contributors

  • @goodwanghan made their first contribution in https://github.com/Nixtla/nixtla/pull/632
  • @JQGoh made their first contribution in https://github.com/Nixtla/nixtla/pull/647
  • @deven367 made their first contribution in https://github.com/Nixtla/nixtla/pull/663

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.6.7...v0.7.0

- Jupyter Notebook
Published by Yibei990826 6 months ago

https://github.com/nixtla/nixtla - v0.6.7.dev3

What's Changed

  • Relax supported model check by @goodwanghan in https://github.com/Nixtla/nixtla/pull/634

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.6.7.dev2...v0.6.7.dev3

- Jupyter Notebook
Published by goodwanghan 10 months ago

https://github.com/nixtla/nixtla - v0.6.7.dev2

What's Changed

  • Adjust model input size validation logic, add devcontainer by @goodwanghan in https://github.com/Nixtla/nixtla/pull/632
  • Update package version by @goodwanghan in https://github.com/Nixtla/nixtla/pull/633

New Contributors

  • @goodwanghan made their first contribution in https://github.com/Nixtla/nixtla/pull/632

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.6.7.dev1...v0.6.7.dev2

- Jupyter Notebook
Published by goodwanghan 11 months ago

https://github.com/nixtla/nixtla - v0.6.7.dev1

  • chore: v0.6.7.dev1 @Yibei990826 (#630)
  • refactor: Replace httpx.Client with makeclient @Yibei990826 (#629)
  • [DOC] add faq on simple data forecast @Yibei990826 (#588)
  • [doc] Add Meeting Link to Pricing @Yibei990826 (#626)
  • feat: initial version of the audit & clean data feature @ngupta23 (#611)
  • fix: broken pricing link @ngupta23 (#625)
  • [FEAT] Temporal Hierarchical with TimeGPT @elephaint (#623)
  • doc: unified wording on pricing page @ngupta23 (#624)
  • docs: updated pricing to remove Azure and Free plan. @ngupta23 (#617)
  • doc: updated pricing @ngupta23 (#615)
  • fix: for test failure on windows 3.9 @ngupta23 (#616)
  • doc: added info about team seats @ngupta23 (#603)
  • docs: add tutorial on custom frequencies @MMenchero (#597)

New Features

  • feat: get single finetuned model @jmoralez (#610)

Bug Fixes

  • misc: Fix typing for client timeout @adamantike (#621)

Documentation

  • [FIX] Docs incorrect mailto links @elephaint (#574)
  • docs: update changelog @jmoralez (#595)
  • [FIX] Change html table to md format @Yibei990826 (#596)

Dependencies

  • fix: lint @ngupta23 (#620)
  • chore(deps): bump actions/setup-python from 5.3.0 to 5.4.0 in the ci-dependencies group @dependabot[bot] (#600)
  • chore(deps): bump pypa/gh-action-pypi-publish from 1.12.3 to 1.12.4 in the ci-dependencies group @dependabot[bot] (#598)

- Jupyter Notebook
Published by github-actions[bot] 11 months ago

https://github.com/nixtla/nixtla - v0.6.6

New Features

  • FEAT: online anomaly detection @marcopeix (#546)

Bug Fixes

  • [FIX] exogenous features with partitioning @elephaint (#591)

- Jupyter Notebook
Published by github-actions[bot] about 1 year ago

https://github.com/nixtla/nixtla - v0.6.5

New Features

  • feat: saving and re-using fine-tuned models @jmoralez (#562)
  • feat: add refit argument to cross_validation @jmoralez (#556)
  • feat: zstd-compress requests over 1MB @jmoralez (#559)

Documentation

  • docs: updated to include fill_gaps capability for multiple time series @ngupta23 (#580)
  • docs: cleanup @ngupta23 (#578)
  • feat: add vn1 competition experiment @AzulGarza (#563)
  • docs: FAQ | formatting fix @ngupta23 (#569)
  • [DOCS] Fixes two docs issues @elephaint (#570)
  • docs: updated FAQs @ngupta23 (#564)
  • [FIX] Img links @elephaint (#558)
  • [FIX] Img link @elephaint (#557)
  • DOC: separate tutorial for finetune_depth @marcopeix (#547)
  • fix broken links and image @Yibei990826 (#551)
  • [FIX] Electricity short @elephaint (#555)
  • [FIX] Electricity dataset on tutorials @elephaint (#554)

Enhancement

  • enh: use GET request for model_params @jmoralez (#576)
  • enh: update validateapikey to use GET request @jmoralez (#573)

- Jupyter Notebook
Published by github-actions[bot] about 1 year ago

https://github.com/nixtla/nixtla - v0.6.4

New Features

  • feat: support custom and integer frequencies @jmoralez (#532)
  • feat: usage method @jmoralez (#548)
  • feat: add histexoglist argument to cross_validation @jmoralez (#534)

Documentation

  • Add Why TimeGPT notebook @Yibei990826 (#537)
  • [FIX] Pricing links incorrect @elephaint (#544)
  • [FIX] Update contributing guide docs @elephaint (#539)
  • fix: cleaned the FAQ related to API validation @ngupta23 (#538)
  • docs: instructions on how to contribute @ngupta23 (#526)
  • docs: broken links in intro notebook @ngupta23 (#527)
  • docs: updated dashboard image to latest dashboard @ngupta23 (#528)

- Jupyter Notebook
Published by github-actions[bot] about 1 year ago

https://github.com/nixtla/nixtla - v0.6.3

Bug Fixes

  • fix(deps): bump utils @jmoralez (#524)

- Jupyter Notebook
Published by github-actions[bot] over 1 year ago

https://github.com/nixtla/nixtla - v0.6.2

New Features

  • FEAT: Add finetune_depth parameter @marcopeix (#471)

Breaking Change

  • breaking: raise error for gaps in series @jmoralez (#504)
  • breaking: add hist_exog_list argument to forecast @jmoralez (#505)

Bug Fixes

  • fix: convert level to quantiles in historic forecast @jmoralez (#510)
  • fix: reduce test time @elephaint (#487)
  • fix(ci): increase tolerance in tests @jmoralez (#503)
  • fix: update docs to add hist exog list instead of previous behaviour @AzulGarza (#520)

Documentation

  • Updating Azure getting started guide. @tracykteal (#508)
  • updating Azure and trial information @tracykteal (#500)
  • Adding a pricing page to our docs @tracykteal (#502)
  • docs: add finetune_depth to tutorial on improving accuracy @marcopeix (#497)
  • docs: add improve accuracy content to special topics page @Yibei990826 (#496)
  • docs: add notebook tutorial for improve forecast accuracy @Yibei990826 (#495)
  • docs: update energy demand forecast tutorial @Yibei990826 (#499)

Dependencies

  • chore(deps): bump pypa/gh-action-pypi-publish from 1.10.3 to 1.11.0 in the ci-dependencies group @dependabot (#518)
  • ci(lint): run mypy @jmoralez (#512)
  • chore(deps): bump the ci-dependencies group with 2 updates @dependabot (#506)
  • chore(deps): bump actions/checkout from 4.2.0 to 4.2.1 in the ci-dependencies group @dependabot (#492)
  • chore(deps): bump pypa/gh-action-pypi-publish from 1.10.2 to 1.10.3 in the ci-dependencies group @dependabot (#491)

- chore: release v0.6.2 @AzulGarza (#519)

Enhancement

  • enh: warn when overriding model in Azure endpoint @jmoralez (#511)
  • enh: improve short series error message @jmoralez (#494)

- Jupyter Notebook
Published by github-actions[bot] over 1 year ago

https://github.com/nixtla/nixtla - v0.6.1

New Features

  • feat: support newer azure deployments by @jmoralez in https://github.com/Nixtla/nixtla/pull/478

Documentation

  • [DOCS] Add API call count FAQ by @marcopeix in https://github.com/Nixtla/nixtla/pull/449
  • Adding Azure getting started doc by @tracykteal in https://github.com/Nixtla/nixtla/pull/474

Other

  • chore: remove autogenerated code by @jmoralez in https://github.com/Nixtla/nixtla/pull/468

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.6.0...v0.6.1

- Jupyter Notebook
Published by jmoralez over 1 year ago

https://github.com/nixtla/nixtla - v0.6.0

Breaking changes

  • Removed TimeGPT class in favor of NixtlaClient.
  • Removed NixtlaClient.validate_token method in favor of NixtlaClient.validate_api_key.
  • Removed short-horizon and long-horizon models in favor of timegpt-1 and timegpt-1-long-horizon respectively.
  • Removed fewshot_steps and fewshot_loss in favor of finetune_steps and finetune_loss respectively.
  • Removed TIMEGPT_TOKEN environment variable in favor of NIXTLA_API_KEY.
  • Timestamps in the time_col preserve their type in the outputs (timestamp), previously they were cast to string.
  • Gaps in series are not filled anymore, in line with our documentation. Please use the fill_gaps function if you require to do so.
  • NixtlaClient.weights_x is now a list of lists if num_partitions != None, where each element corresponds to the weights for a specific partition.

Features

  • feat: call v2 endpoints by @jmoralez in https://github.com/Nixtla/nixtla/pull/429
  • feat: orjson serialization by @jmoralez in https://github.com/Nixtla/nixtla/pull/452
  • [FEAT] Add historical exogenous by @elephaint in https://github.com/Nixtla/nixtla/pull/453
  • FEAT: Add feature contributions as attribute and tutorial on how to use by @marcopeix in https://github.com/Nixtla/nixtla/pull/448
  • [FEAT] - Raise error when payload is too large and suggest number of partitions by @marcopeix in https://github.com/Nixtla/nixtla/pull/456

Bug fixes

  • fix: removed data input restriction during cross validation finetune by @Yibei990826 in https://github.com/Nixtla/nixtla/pull/426

Enhancements

  • feat: use TypeVar for dataframes by @jmoralez in https://github.com/Nixtla/nixtla/pull/443
  • feat: set supportedmodels using baseurl by @jmoralez in https://github.com/Nixtla/nixtla/pull/450
  • feat: suggest earlier version for azure endpoints by @jmoralez in https://github.com/Nixtla/nixtla/pull/457

Documentation

  • updating excel docs with some more information by @tracykteal in https://github.com/Nixtla/nixtla/pull/414
  • updating FAQ for fee information and Azure being available by @tracykteal in https://github.com/Nixtla/nixtla/pull/412
  • Update 03exceladdin.ipynb by @tracykteal in https://github.com/Nixtla/nixtla/pull/416
  • [DOC] - Rephrase the sentence for specific loss function by @marcopeix in https://github.com/Nixtla/nixtla/pull/436
  • docs(readme): getting started by @mergenthaler in https://github.com/Nixtla/nixtla/pull/438
  • Adding activate trial link in intro by @tracykteal in https://github.com/Nixtla/nixtla/pull/417
  • [DOC] - Add instructions on saving figures when not working in notebooks by @marcopeix in https://github.com/Nixtla/nixtla/pull/454
  • [BUG]: close img tag in introduction notebook by @marcopeix in https://github.com/Nixtla/nixtla/pull/441
  • docs: add polars quickstart by @jmoralez in https://github.com/Nixtla/nixtla/pull/447

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.5.2...v0.6.0

- Jupyter Notebook
Published by jmoralez over 1 year ago

https://github.com/nixtla/nixtla - v0.5.2

What's Changed

Features

  • Use case on missing values by @MMenchero in https://github.com/Nixtla/nixtla/pull/326
  • Electricity demand use case by @marcopeix in https://github.com/Nixtla/nixtla/pull/321
  • [FEAT] What if - pricing in retail scenario by @elephaint in https://github.com/Nixtla/nixtla/pull/340
  • Update the middleware endpoint to use the new one by @loama in https://github.com/Nixtla/nixtla/pull/407
  • Update excel add in docs to reflect changes in the plugin by @loama in https://github.com/Nixtla/nixtla/pull/406
  • feat: improve readability by @mergenthaler in https://github.com/Nixtla/nixtla/pull/367
  • [DOC] Add azure callouts to use cases by @elephaint in https://github.com/Nixtla/nixtla/pull/357
  • [DOC] - Add links and callouts by @marcopeix in https://github.com/Nixtla/nixtla/pull/355
  • [DOC] Model callouts and descriptions by @MMenchero in https://github.com/Nixtla/nixtla/pull/359
  • feat: add foundation ts arena by @AzulGarza in https://github.com/Nixtla/nixtla/pull/378
  • feat: Added nixtlar to TimeGPT docs by @MMenchero in https://github.com/Nixtla/nixtla/pull/393

Fixes

  • [FIX] SDK Reference by @elephaint in https://github.com/Nixtla/nixtla/pull/342
  • [FIX] Raise warning on missing X_df when df has exogenous by @elephaint in https://github.com/Nixtla/nixtla/pull/295
  • fix: add jupyter lab to dev deps by @mergenthaler in https://github.com/Nixtla/nixtla/pull/350
  • [FIX] Hotfix for old SDK link removal by @elephaint in https://github.com/Nixtla/nixtla/pull/352
  • [Hotfix] Minimum data requirements by @MMenchero in https://github.com/Nixtla/nixtla/pull/364
  • fix: note on morai improvements by @mergenthaler in https://github.com/Nixtla/nixtla/pull/395
  • fix: Clarify how tokens are counted for AzureAI by @MMenchero in https://github.com/Nixtla/nixtla/pull/401
  • Hotfix for links in documentation by @MMenchero in https://github.com/Nixtla/nixtla/pull/341
  • [FIX] Colab-flag by @elephaint in https://github.com/Nixtla/nixtla/pull/349
  • Minor correction to tutorial by @MMenchero in https://github.com/Nixtla/nixtla/pull/394

Chore

  • Readme update by @mergenthaler in https://github.com/Nixtla/nixtla/pull/346
  • Add Fern badge to README.md by @dannysheridan in https://github.com/Nixtla/nixtla/pull/185
  • [DOC] - Reduce code blocks in capabilties by @marcopeix in https://github.com/Nixtla/nixtla/pull/339
  • Better intro/welcome page for doc by @marcopeix in https://github.com/Nixtla/nixtla/pull/343
  • a few updates to getting started by @tracykteal in https://github.com/Nixtla/nixtla/pull/344
  • fix: note on chronos pr by @mergenthaler in https://github.com/Nixtla/nixtla/pull/390
  • fix: Change how data is downloaded for Bitcoin tutorial by @MMenchero in https://github.com/Nixtla/nixtla/pull/391
  • Removed a wrong sentence in README.md by @B-Deforce in https://github.com/Nixtla/nixtla/pull/372

New Contributors

  • @dannysheridan made their first contribution in https://github.com/Nixtla/nixtla/pull/185
  • @B-Deforce made their first contribution in https://github.com/Nixtla/nixtla/pull/372
  • @loama made their first contribution in https://github.com/Nixtla/nixtla/pull/407

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.5.1...v0.5.2

- Jupyter Notebook
Published by AzulGarza over 1 year ago

https://github.com/nixtla/nixtla - v0.5.1

What's Changed

  • [DOCS] - Add a welcome/introduction page to the documentation by @marcopeix in https://github.com/Nixtla/nixtla/pull/319
  • [FIX] Doc fixes by @elephaint in https://github.com/Nixtla/nixtla/pull/324
  • Add capabilities notebooks by @marcopeix in https://github.com/Nixtla/nixtla/pull/312
  • [DOCS] Fix structure by @elephaint in https://github.com/Nixtla/nixtla/pull/329
  • [FIX] Mintlify prefixes, readme file dirs by @elephaint in https://github.com/Nixtla/nixtla/pull/333
  • [FIX] Doc fixes by @elephaint in https://github.com/Nixtla/nixtla/pull/334
  • fix: add pyreadr as dev dep by @AzulGarza in https://github.com/Nixtla/nixtla/pull/336
  • fix: update distributed to computing at scale by @AzulGarza in https://github.com/Nixtla/nixtla/pull/337
  • fix: add model to cross validation path call by @AzulGarza in https://github.com/Nixtla/nixtla/pull/335
  • v0.5.1 by @AzulGarza in https://github.com/Nixtla/nixtla/pull/338

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.5.0...v0.5.1

- Jupyter Notebook
Published by AzulGarza almost 2 years ago

https://github.com/nixtla/nixtla - v0.5.0

What's Changed

New features

  • regenerate fern code to support pydantic v1 and v2 by @jmoralez in https://github.com/Nixtla/nixtla/pull/308
  • convert ids to categorical by @jmoralez in https://github.com/Nixtla/nixtla/pull/313
  • feat: restrict input forecast by @AzulGarza in https://github.com/Nixtla/nixtla/pull/314
  • call corresponding endpoint in cross_validation by @jmoralez in https://github.com/Nixtla/nixtla/pull/300
  • store x_cols as a variable instead of attribute by @jmoralez in https://github.com/Nixtla/nixtla/pull/318

Docs

  • fix: update min version and nixtla_client by @AzulGarza in https://github.com/Nixtla/nixtla/pull/317
  • [FEAT] - Tutorials update (Marco) by @marcopeix in https://github.com/Nixtla/nixtla/pull/311
  • [DOCS] Add tutorials by @elephaint in https://github.com/Nixtla/nixtla/pull/306
  • New versions of how-to-guides for computing at scale by @MMenchero in https://github.com/Nixtla/nixtla/pull/302
  • Updated tutorials by @MMenchero in https://github.com/Nixtla/nixtla/pull/316
  • [DOCS] New structure by @elephaint in https://github.com/Nixtla/nixtla/pull/323

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.4.0...v0.5.0

- Jupyter Notebook
Published by AzulGarza almost 2 years ago

https://github.com/nixtla/nixtla - v0.4.0

What's Changed

Python package name change

We're deprecating the nixtlats package in favor of nixtla. Please ensure you make the following changes:

  1. Install the nixtla package: pip install nixtla
  2. Update your imports accordingly, e.g. from nixtla import NixtlaClient

New features

  • [FEAT] Process multiple partitions in parallel by @elephaint in https://github.com/Nixtla/nixtla/pull/296

Enhancements

  • Create CODEOFCONDUCT.md by @tracykteal in https://github.com/Nixtla/nixtla/pull/292
  • use fillgaps in resampledataframe by @jmoralez in https://github.com/Nixtla/nixtla/pull/267

New Contributors

  • @tracykteal made their first contribution in https://github.com/Nixtla/nixtla/pull/292
  • @elephaint made their first contribution in https://github.com/Nixtla/nixtla/pull/296

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.3.0...v0.4.0

- Jupyter Notebook
Published by jmoralez almost 2 years ago

https://github.com/nixtla/nixtla - v0.3.0

What's Changed

Changelog

0.3.0

🔄 Changes & Deprecations

  • Deprecation of TimeGPT Class: In an effort to streamline our API and align with industry best practices, we're deprecating the TimeGPT class in favor of the new NixtlaClient class. This change is designed to provide a more intuitive and powerful interface for interacting with our services.

Before: ```python from nixtlats import TimeGPT

# Initialize the TimeGPT model timegpt = TimeGPT() ```

After: ```python from nixtlats import NixtlaClient

# Initialize the NixtlaClient nixtla = NixtlaClient() ```

  • Renaming of Configuration Parameters: To enhance clarity and consistency with other SDKs, we've renamed the token parameter to api_key and environment to base_url.

Before: python timegpt = TimeGPT(token='YOUR_TOKEN', environment='YOUR_ENVIRONMENT_URL')

After: python nixtla = NixtlaClient(api_key='YOUR_API_KEY', base_url='YOUR_BASE_URL')

  • Introduction of NixtlaClient.validate_api_key: Replacing the previous NixtlaClient.validate_token method, this update aligns with the new authentication parameter naming and offers a straightforward way to validate API keys.

Before: python timegpt.validate_token()

After: python nixtla.validate_api_key()

  • Environment Variable Changes: In line with the renaming of parameters, we've updated the environment variables to set up the API key and base URL. The TIMEGPT_TOKEN is now replaced with NIXTLA_API_KEY, and we've introduced NIXTLA_BASE_URL for custom API URLs.

  • Backward Compatibility & Future Warnings: These changes are designed to be backward compatible. However, users can expect to see future warnings when utilizing deprecated features, such as the TimeGPT class.

0.2.0 (Previously Released)

🔄 Changes & Deprecations

  • Renaming of Fine-Tuning Parameters: The finetune_steps and finetune_loss parameters were renamed to fewshot_steps and fewshot_loss. Additionally, the model parameter values changed from short-horizon and long-horizon to timegpt-1 and timegpt-1-long-horizon, with an emphasis on preserving backward compatibility. In version 0.3.0, these changes are deprecated in favor of reverting to the original parameter names and values, ensuring a seamless transition for existing users.

Features

  • feat: update docs in https://github.com/Nixtla/nixtla/pull/268
  • feat: add moirai benchmark in https://github.com/Nixtla/nixtla/pull/271
  • feat: replace token by apikey and environment by baseurl in https://github.com/Nixtla/nixtla/pull/275
  • feat: replace TimeGPT class by NixtlaClient class in https://github.com/Nixtla/nixtla/pull/276

Fixes

  • fix: recover finetune and model changes in https://github.com/Nixtla/nixtla/pull/274
  • fix nixtla_client page render in https://github.com/Nixtla/nixtla/pull/279

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.2.0...v0.3.0

- Jupyter Notebook
Published by AzulGarza almost 2 years ago

https://github.com/nixtla/nixtla - v0.2.0

What's Changed

Features

  • feat: SDK support Fern Regeneration -- March 22, 2024 in https://github.com/Nixtla/nixtla/pull/261
  • feat: replace finetune with fewshot in https://github.com/Nixtla/nixtla/pull/262
  • feat: use new endpoints and rename models in https://github.com/Nixtla/nixtla/pull/263

Documentation

  • docs: add azure automl experiment in https://github.com/Nixtla/nixtla/pull/246
  • docs: add finetuning loss function tutorial and link it to finetuning tutorial in https://github.com/Nixtla/nixtla/pull/239
  • docs: tutorial on long-horizon forecasting in https://github.com/Nixtla/nixtla/pull/249
  • docs: add new faqs section in https://github.com/Nixtla/nixtla/pull/250
  • docs: add new sections to documentation in https://github.com/Nixtla/nixtla/pull/255
  • docs: add amazon chronos benchmark in https://github.com/Nixtla/nixtla/pull/257
  • docs: update README.md in https://github.com/Nixtla/nixtla/pull/258

Fixes

  • chore: add pre-commit in https://github.com/Nixtla/nixtla/pull/252
  • chore: collapse experiment results in pr in https://github.com/Nixtla/nixtla/pull/247
  • fix: all transforminputs to handle cases where index column is set as timecol in https://github.com/Nixtla/nixtla/pull/254
  • hotfix: ignore precommit fern in https://github.com/Nixtla/nixtla/pull/260

New Contributors

  • @marcopeix made their first contribution in https://github.com/Nixtla/nixtla/pull/239
  • @MMenchero made their first contribution in https://github.com/Nixtla/nixtla/pull/250
  • @Yibei990826 made their first contribution in https://github.com/Nixtla/nixtla/pull/254
  • @mergenthaler made their first contribution in https://github.com/Nixtla/nixtla/pull/258

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.21...v0.2.0

- Jupyter Notebook
Published by AzulGarza almost 2 years ago

https://github.com/nixtla/nixtla - v0.1.21

What's Changed

Features

  • feat: add contributing file in https://github.com/Nixtla/nixtla/pull/236
  • feat: add quantiles to forecast and cross validation methods in https://github.com/Nixtla/nixtla/pull/242

Fixes

  • add no response bot in https://github.com/Nixtla/nixtla/pull/232
  • fix: upper limit ray version in https://github.com/Nixtla/nixtla/pull/235

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.20...v0.1.21

- Jupyter Notebook
Published by AzulGarza almost 2 years ago

https://github.com/nixtla/nixtla - v0.1.20

What's Changed

Features

  • add prophet comparison experiment in https://github.com/Nixtla/nixtla/pull/204
  • finetune loss in https://github.com/Nixtla/nixtla/pull/218
  • add lag-llama experiment in https://github.com/Nixtla/nixtla/pull/224

Bug Fixes

  • chore: fern-ignore changelog file in https://github.com/Nixtla/nixtla/pull/206
  • chore: add summary results prophet experiment in https://github.com/Nixtla/nixtla/pull/210
  • set upper bound on pandas in https://github.com/Nixtla/nixtla/pull/225

New Contributors

  • @cchallu made their first contribution in https://github.com/Nixtla/nixtla/pull/218

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.19...v0.1.20

- Jupyter Notebook
Published by AzulGarza about 2 years ago

https://github.com/nixtla/nixtla - v0.1.19

What's Changed

Features

  • [FEAT] enable num_partitions for pandas in https://github.com/Nixtla/nixtla/pull/176

Bug fixes

  • chore: add changelog file in https://github.com/Nixtla/nixtla/pull/169
  • docs: add faqs to mintlify index in https://github.com/Nixtla/nixtla/pull/170
  • fix: add correct ex vars to cross validation in https://github.com/Nixtla/nixtla/pull/171
  • fix: solve problem with duplicated dates in https://github.com/Nixtla/nixtla/pull/190

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.18...v0.1.19

- Jupyter Notebook
Published by AzulGarza about 2 years ago

https://github.com/nixtla/nixtla - v0.1.18

What's Changed

🚀 Feature Enhancements

Forecast Using Diverse Models 🌐

Release of new forecasting methods. Among the updates, we've unveiled the timegpt-1-long-horizon model, crafted specifically for long-term forecasts that span multiple seasonalities. To use it, simply specify the model in your methods like so:

```python from nixtlats import TimeGPT

Initialize the TimeGPT model

timegpt = TimeGPT()

Generate forecasts using the long-horizon model

fcst_df = timegpt.forecast(..., model='timegpt-1-long-horizon')

Perform cross-validation with the long-horizon model

cvdf = timegpt.crossvalidation(..., model='timegpt-1-long-horizon')

Detect anomalies with the long-horizon model

anomaliesdf = timegpt.detectanomalies(..., model='timegpt-1-long-horizon') ```

Choose between timegpt-1 for the first version of TimeGPT or timegpt-1-long-horizon for long horizon tasks..

Cross-Validation Methodology 📊

You can dive deeper into your forecasting pipelines with the new cross_validation feature. This method enables you to validate forecasts across different windows efficiently:

```python

Set up cross-validation with a custom horizon, number of windows, and step size

cvdf = timegpt.crossvalidation(df, h=35, nwindows=5, stepsize=5) ```

This will generate 5 distinct forecast sets, each with a horizon of 35, stepping through your data every 5 timestamps.

Retry Behavior for Robust API Calls 🔁

The new retry mechanism allows the making of more robust API calls (preventing them from crashing with large-scale tasks).

  • max_retries: Number of max retries for an API call.
  • retry_interval: Pause between retries.
  • max_wait_time: Total duration of retries.

python timegpt = TimeGPT(max_retries=10, retry_interval=5, max_wait_time=360)

Token Inference Made Simple 🔑

The TimeGPT class now automatically infers your TIMEGPT_TOKEN using os.environ.get('TIMEGPT_TOKEN'), streamlining your setup:

```python

No more manual token handling - TimeGPT has got you covered

timegpt = TimeGPT() ``` For more information visit our FAQS section.

Introducing the FAQ Section 📘

Questions? We've got answers! Our new FAQ section tackles the most common inquiries, from integrating exogenous variables to configuring authorization tokens and understanding long-horizon forecasts.

Specific Changelog

New Features: * Add reference to pandas frequencies in PR #126 * Add automatic evaluation workflow in PR #140 * Retry behavior if api call fails in PR #146 * Add support for new models (long horizon) in PR #156 * Add cross-validation method in PR #159 * Test correct import in CI in PR #163 * Add colab badges to docs in PR #165

Fixes: * Add date features to fernignore in PR #127 * Add new order to docs hosted in readme.com in PR #130 * Refactor to expose endpoints in PR #132 * Add tests for custom endpoint and abstract call api method in PR #143 * Increase max wait time to catch ReadTimeout exception in PR #147 * Fern-ignore new files in PR #149 * Move docs-scripts to action_files in PR #151 * Filter API errors in PR #155

Documentation and Miscellaneous: * Add CONTRIBUTING.md and mint.json in PR #135 * Add docs scripts in PR #136 * Checkout docs repo instead of using submodule in PR #154 * Redirect to mintlify docs in PR #161 * Refactor: default token to os.environ.get and remove os.environ in PR #164 * Add faq docs in PR #166

New Contributors

  • @hahnbeelee made their first contribution in https://github.com/Nixtla/nixtla/pull/135
  • @jmoralez made their first contribution in https://github.com/Nixtla/nixtla/pull/136

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.17...v0.1.18

- Jupyter Notebook
Published by AzulGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.17

What's Changed

  • [!FIX] change plotly to matplotlib in https://github.com/Nixtla/nixtla/pull/119
  • [FEAT] Deploy docs to README in https://github.com/Nixtla/nixtla/pull/120
  • [FIX] Rename deploy readme action in https://github.com/Nixtla/nixtla/pull/121
  • [FEAT] Improve readme docs in https://github.com/Nixtla/nixtla/pull/122
  • [FEAT] Update docs in https://github.com/Nixtla/nixtla/pull/123
  • [FIX] Add end of callout block in https://github.com/Nixtla/nixtla/pull/124
  • [FEAT] Add possibility to use index to infer freq in https://github.com/Nixtla/nixtla/pull/125

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.16...v0.1.17

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.16

What's Changed

  • [FIX] Dependencies and local data in https://github.com/Nixtla/nixtla/pull/111
  • [FEAT] Add plot method in https://github.com/Nixtla/nixtla/pull/113
  • [FEAT] Add holidays and special dates support in https://github.com/Nixtla/nixtla/pull/114
  • [DOCS] Add new structure in https://github.com/Nixtla/nixtla/pull/115

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.15...v0.1.16

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.15

What's Changed

  • :herb: Fern Regeneration -- September 23, 2023 in https://github.com/Nixtla/nixtla/pull/108
  • [FEAT] Handle exogenous variables for historic and anomaly detection endpoints in https://github.com/Nixtla/nixtla/pull/110

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.14...v0.1.15

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.14

What's Changed

  • [FEAT] Add support for distributed exogenous variables in https://github.com/Nixtla/nixtla/pull/107

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.13...v0.1.14

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.13

What's Changed

  • :herb: Fern Regeneration -- August 29, 2023 in https://github.com/Nixtla/nixtla/pull/98
  • :herb: Fern Regeneration -- September 9, 2023 in https://github.com/Nixtla/nixtla/pull/101
  • fix: deploy docs in https://github.com/Nixtla/nixtla/pull/102
  • [FEAT] Cancel concurrent jobs in https://github.com/Nixtla/nixtla/pull/104
  • [FEAT] Add detect anomalies method in https://github.com/Nixtla/nixtla/pull/103

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.12...v0.1.13

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.12

What's Changed

  • feat: add distributed integration (spark,ray,dask) in https://github.com/Nixtla/nixtla/pull/92
  • feat: add custom url option in https://github.com/Nixtla/nixtla/pull/93

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.11...v0.1.12

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.11

What's Changed

  • feat: add robust infer freq for custom frequencies in https://github.com/Nixtla/nixtla/pull/90

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.10...v0.1.11

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.10

What's Changed

  • feat: add warning for shot horizon in https://github.com/Nixtla/nixtla/pull/89

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.9...v0.1.10

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.9

Hot Fix pydantic

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.8

What's Changed

  • [FIX] Use min size in https://github.com/Nixtla/nixtla/pull/81

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.7...v0.1.8

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.7

What's Changed

  • [FEAT] Add fern integration in https://github.com/Nixtla/nixtla/pull/75
  • [FEAT] Add input size validation in https://github.com/Nixtla/nixtla/pull/76
  • [FEAT] Add logger in https://github.com/Nixtla/nixtla/pull/77
  • :herb: Add .fernignore in https://github.com/Nixtla/nixtla/pull/78
  • [FIX] Ubuntu CI/CD in https://github.com/Nixtla/nixtla/pull/79

New Contributors

  • @dsinghvi made their first contribution in https://github.com/Nixtla/nixtla/pull/78

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.6...v0.1.7

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.6

What's Changed

  • [FIX] Use full history exogenous variables in https://github.com/Nixtla/nixtla/pull/74

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.5...v0.1.6

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.5

What's Changed

  • [FEAT] Add date features argument in https://github.com/Nixtla/nixtla/pull/72

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.4...v0.1.5

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.4

What's Changed

  • fix: correct input size based on level and horizon in https://github.com/Nixtla/nixtla/pull/68
  • feat/historic arg in https://github.com/Nixtla/nixtla/pull/70
  • fix: short horizon level in https://github.com/Nixtla/nixtla/pull/71

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.3...v0.1.4

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.3

What's Changed

  • test: float in level arg and typing in https://github.com/Nixtla/nixtla/pull/63
  • fix: wide dataframe in https://github.com/Nixtla/nixtla/pull/64
  • fix: add openbb as dev dep (deploy pages) in https://github.com/Nixtla/nixtla/pull/66
  • feat: add validate token method in https://github.com/Nixtla/nixtla/pull/65
  • fix/deploy pages openbb in https://github.com/Nixtla/nixtla/pull/67

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.2...v0.1.3

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.2

What's Changed

  • fix: improve docs in https://github.com/Nixtla/nixtla/pull/54
  • fix: reduce setup complexity (bug with previous one) in https://github.com/Nixtla/nixtla/pull/55
  • fix: add dev deps in https://github.com/Nixtla/nixtla/pull/56
  • feat/support pandas in https://github.com/Nixtla/nixtla/pull/57
  • fea!: tremove api_url in https://github.com/Nixtla/nixtla/pull/58
  • feat: add unique_id optional and add name of columns in https://github.com/Nixtla/nixtla/pull/59
  • feat: infere freq in https://github.com/Nixtla/nixtla/pull/62

Full Changelog: https://github.com/Nixtla/nixtla/compare/v0.1.0...v0.1.2

- Jupyter Notebook
Published by FedericoGarza over 2 years ago

https://github.com/nixtla/nixtla - v0.1.0

First version TimeGPT SDK for Python.

- Jupyter Notebook
Published by FedericoGarza over 2 years ago