Time Series Modeling - BKJackson/BKJackson_Wiki GitHub Wiki

Tutorials

An End-to-End Project on Time Series Analysis and Forecasting with Python - July 8, 2018
11 Classical Time Series Forecasting Methods in Python (Cheat Sheet) - Jason Brownlee, July 1, 2020
How to Convert a Time Series to a Supervised Learning Problem in Python - Jason Brownlee, Aug 21, 2019
A Step-by-Step Guide to Calculating Autocorrelation and Partial Autocorrelation - How to calculate the ACF and PACF values from scratch in Python

GluonTS - Time Series Modeling in Python

GluonTS
GluonTS - Extended Forecasting Tutorial

TimeSeriesAI - tsai

tsai github home
tsai documentation

Neural Network Approaches

Nixtla Neural Forecast - Scalable and user friendly neural 🧠 forecasting algorithms.
Signal denoising using RNNs in PyTorch
Neural Ordinary Differential Equations PDF
Liquid Time Constant Networks - Github
Neural Circuit Policies for PyTorch and TensorFlow - Github
Discrete-Event Continuous-Time Recurrent Nets PDF
Liquid Neural Network Foundation Models

Facebook Prophet

Prophet Quick Start

Delorean

Delorean - a python library for enhancing DateTime. Delorean stands on the shoulders of giants pytz and dateutil. Delorean docs

from delorean import Delorean

d = Delorean()
d = d.shift('US/Eastern')
return d  

Arrow

Arrow - Better dates and times for Python. Python library that offers a sensible and human-friendly approach to creating, manipulating, formatting and converting dates, times and timestamps.

PyFlux

PyFlux docs - a library for time series analysis and prediction.

PyTZ

PyTZ docs - World timezone definitions for python

Cross-validation for time series

Cross-validation for time series
R code for the time series plots - Gist

StatsModels - statistics in Python

StatsModels Module Index

Sequence learning

hmmlearn - set of algorithms for unsupervised learning and inference of Hidden Markov Models
seqlearn - sequence classification toolkit for Python, for supervised learning of HMMs and similar models

Bayesian Approaches

Bayesian Structural Time Series - Proposed by Scott and Varian in 2013, Bayesian structural time series is a powerful set of methods that cover a large class of time series models using the State Space representation of time series and Bayesian statistics.

CommPy - Digital Communication with Python - Includes turbo decoder
Plotting Trellis Diagrams with CommPy in Python
The Viterbi Algorithm - Illustrated!

Books with code

Forecasting: Principles and Practice - By Rob J Hyndman and George Athanasopoulos, online text with R code