Time Series Forecasting Python Packages

gluonts

Probabilistic time series modeling in Python

chronos-forecasting

Chronos: Pretrained Models for Time Series Forecasting

hierarchicalforecast

Probabilistic Hierarchical forecasting 👑 with statistical and econometric methods.

nixtla

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

skforecast

Python library for time series forecasting using scikit-learn compatible models, statistical methods, and foundation models

eland

Python Client and Toolkit for DataFrames, Big Data, Machine Learning and ETL in Elasticsearch

fev

Forecast evaluation library

tabpfn-time-series

Zero-shot Time Series Forecasting with TabPFN (work accepted at NeurIPS 2024 TRL and TSALM workshops)

momentfm

MOMENT: A Family of Open Time-series Foundation Models, ICML'24

nixtlats

TimeGPT-1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.

itransformer

Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group

timecopilot-chronos-forecasting

Chronos: Pretrained Models for Time Series Forecasting

timecast-nightly

Performant, composable online learning

pipelinets

One-stop time series analysis tool, supporting time series data preprocessing, feature engineering, model training, model evaluation, model prediction, etc. Based on spinesTS.

fabba

An efficient symbolic time series approximation with ABBA.

apdtflow

APDTFlow: A modular forecasting framework for time series data

expsmoothing

Exponential smoothing forecast model

spinests

spinesTS, a powerful timeseries toolsets.

pytorchtime

Datasets, Transforms and Models specific to Time Series, powered by PyTorch

padelf

Load publicly available electric load forecasting datasets as pandas DataFrames.

tsfmx

Multimodal extension for time series foundation models

foretis

Time Series Forecasting in Python

conformal-tights

👖 Conformal Tights adds conformal prediction of coherent quantiles and intervals to any scikit-learn regressor or Darts forecaster

simba-ml

SimbaML is an all-in-one framework for integrating prior knowledge of ODE models into the ML process by synthetic data augmentation. It allows for the convenient generation of realistic synthetic data by sparsifying and adding noise. Furthermore, our framework provides customizable pipelines for various ML experiments, such as transfer learning.