Kats, a kit to analyze time series data, a lightweight, easy-to-use, generalizable, and extendable framework to perform time series analysis, from understanding the key statistics and characteristics, detecting change points and anomalies, to forecasting future trends.
Repository Index
87,075 visible repositories in the index
1–13 of 13 · Most stars
Chronos: Pretrained Models for Time Series Forecasting
- forecasting
- large-language-models
- llm
- machine-learning
An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"
- deep-learning
- forecasting
- forecasting-model
- linear-models
About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008
Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight)
- time-series-forecasting
- transformer
Unified Training of Universal Time Series Forecasting Transformers
- deep-learning
- forecasting
- machine-learning
- pre-trained-models
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
- forecasting
- foundation-models
- time-series
- time-series-forecasting
Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models
- forecasting
- scikit-learn
- machine-learning
- python
Supply a wrapper ``StockDataFrame`` based on the ``pandas.DataFrame`` with inline stock statistics/indicators support.
A Python Pandas implementation of technical analysis indicators
NitroFE is a Python feature engineering engine which provides a variety of modules designed to internally save past dependent values for providing continuous calculation.
- feature-engineering
- machine-learning
- feature
- features
Streaming-first technical indicators with a Rust core: native Python, Node.js and WebAssembly bindings plus a C ABI hub for C, C++, C#, Go, Java and R. 514 indicators, O(1) per-tick updates, no system dependencies. Drop-in TA-Lib replacement.
- algotrading
- backtesting
- bollinger-bands
- cryptocurrency