Skip to main content

AutoGluon Time Series forecasting widget for Orange3 with local Chronos support

Project description

AutoGluon TimeSeries Widget for Orange3

Прогнозирование временных рядов с помощью AutoGluon TimeSeries через интерфейс Orange3.

🧠 Возможности

  • Поддержка пользовательских столбцов и частоты
  • Автоопределение частоты временного ряда
  • Настройка метрики и длины прогноза
  • Учет праздничных дней
  • Очистка от отрицательных и некорректных значений
  • Удобный лог и вывод модели

🧪 Зависимости

  • Orange3 >= 3.38
  • AutoGluon >= 1.3.1
  • pandas == 2.2.3
  • Python 3.9+
  • numpy >= 1.25
  • PyQt5 >= 5.15
  • matplotlib >= 3.5
  • holidays >= 0.20

🚀 Установка

git clone https://github.com/KordyakIM/autogluon-timeseries-widget.git
cd autogluon-timeseries-widget
pip install .

or

pip install orange3-autogluon-timeseries

📦 Добавление виджета в Orange если устанавливаешь вручную

Скопируйте папку widget в директорию пользовательских виджетов Orange:

mkdir -p ~/orange3-widgets/autogluon_timeseries
cp -r widget/* ~/orange3-widgets/autogluon_timeseries/

📝 Лицензия

MIT License

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

orange3_autogluon_timeseries-1.4.8.tar.gz (2.8 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

orange3_autogluon_timeseries-1.4.8-py3-none-any.whl (2.8 MB view details)

Uploaded Python 3

File details

Details for the file orange3_autogluon_timeseries-1.4.8.tar.gz.

File metadata

File hashes

Hashes for orange3_autogluon_timeseries-1.4.8.tar.gz
Algorithm Hash digest
SHA256 452d4bf2aec7cf8a39552e9858d09142df97c34db0b79170881adf9f26bc67da
MD5 aef38b7321257e32fa606b7604c7b5c0
BLAKE2b-256 287afdc76d85d9feb440eae6d9b26964db0b0a23a38ff5415e0598b70f99d6cb

See more details on using hashes here.

File details

Details for the file orange3_autogluon_timeseries-1.4.8-py3-none-any.whl.

File metadata

File hashes

Hashes for orange3_autogluon_timeseries-1.4.8-py3-none-any.whl
Algorithm Hash digest
SHA256 41c2194e1b90a4955ff0d09ac90068061d156a1cf459f8d53c23e0b217ae1919
MD5 e82f96e5638eab535d438ebd5f3d9187
BLAKE2b-256 a740e6fd9a062a7fbc89293509b67ab156ff7e329c05a1cabc8535d935ade191

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page