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:

  from nixtlats import TimeGPT
  
  # Initialize the TimeGPT model
  timegpt = TimeGPT()

  After:

  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:

  timegpt = TimeGPT(token='YOUR_TOKEN', environment='YOUR_ENVIRONMENT_URL')

  After:

  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:

  timegpt.validate_token()

  After:

  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 #268
• feat: add moirai benchmark in #271
• feat: replace token by api_key and environment by base_url in #275
• feat: replace TimeGPT class by NixtlaClient class in #276

Fixes

• fix: recover finetune and model changes in #274
• fix nixtla_client page render in #279

Full Changelog: v0.2.0...v0.3.0

v0.2.0

What's Changed

Features

• feat: SDK support Fern Regeneration -- March 22, 2024 in #261
• feat: replace finetune with fewshot in #262
• feat: use new endpoints and rename models in #263

Documentation

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

Fixes

• chore: add pre-commit in #252
• chore: collapse experiment results in pr in #247
• fix: all transform_inputs to handle cases where index column is set as time_col in #254
• hotfix: ignore precommit fern in #260

New Contributors

• @marcopeix made their first contribution in #239
• @MMenchero made their first contribution in #250
• @Yibei990826 made their first contribution in #254
• @mergenthaler made their first contribution in #258

Full Changelog: v0.1.21...v0.2.0

v0.1.21

What's Changed

Features

• feat: add contributing file in #236
• feat: add quantiles to forecast and cross validation methods in #242

Fixes

• add no response bot in #232
• fix: upper limit ray version in #235

Full Changelog: v0.1.20...v0.1.21

v0.1.20

What's Changed

Features

• add prophet comparison experiment in #204
• finetune loss in #218
• add lag-llama experiment in #224

Bug Fixes

• chore: fern-ignore changelog file in #206
• chore: add summary results prophet experiment in #210
• set upper bound on pandas in #225

New Contributors

• @cchallu made their first contribution in #218

Full Changelog: v0.1.19...v0.1.20

v0.1.19

What's Changed

Features

• [FEAT] enable num_partitions for pandas in #176

Bug fixes

• chore: add changelog file in #169
• docs: add faqs to mintlify index in #170
• fix: add correct ex vars to cross validation in #171
• fix: solve problem with duplicated dates in #190

Full Changelog: v0.1.18...v0.1.19

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:

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
cv_df = timegpt.cross_validation(..., model='timegpt-1-long-horizon')

# Detect anomalies with the long-horizon model
anomalies_df = timegpt.detect_anomalies(..., 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:

# Set up cross-validation with a custom horizon, number of windows, and step size
cv_df = timegpt.cross_validation(df, h=35, n_windows=5, step_size=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.

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:

# 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 #135
• @jmoralez made their first contribution in #136

Full Changelog: v0.1.17...v0.1.18

v0.1.17

What's Changed

• [!FIX] change plotly to matplotlib in #119
• [FEAT] Deploy docs to README in #120
• [FIX] Rename deploy readme action in #121
• [FEAT] Improve readme docs in #122
• [FEAT] Update docs in #123
• [FIX] Add end of callout block in #124
• [FEAT] Add possibility to use index to infer freq in #125

Full Changelog: v0.1.16...v0.1.17

v0.1.16

What's Changed

• [FIX] Dependencies and local data in #111
• [FEAT] Add plot method in #113
• [FEAT] Add holidays and special dates support in #114
• [DOCS] Add new structure in #115

Full Changelog: v0.1.15...v0.1.16

v0.1.15

What's Changed

• 🌿 Fern Regeneration -- September 23, 2023 in #108
• [FEAT] Handle exogenous variables for historic and anomaly detection endpoints in #110

Full Changelog: v0.1.14...v0.1.15

v0.1.14

What's Changed

• [FEAT] Add support for distributed exogenous variables in #107

Full Changelog: v0.1.13...v0.1.14