RamiKrispin/atsaf

Applied Time Series Analysis and Forecasting with R

As the name implies, the book focuses on applied data science methods for time series analysis and forecasting, covering (see the full table of content below):

• Working with time-series data
• Time series analysis methods
• Forecasting methods
• Scaling and productionize approaches

Get updates on the book’s progress on Twitter, Telegram channel, and Github project tracker:

This repository hosts the book materials. It follows the Monorepo philosophy, hosting all the book's content, code, packages, and other supporting materials under one repository. In addition, to ensure a high level of reproducibility, the book is developed in a dockerized environment.

Here is the current repository folder structure:

.
├── R
├── docker
└── docs

• The R folder contains the book's supporting R packages
• The docker folder provides the build files for the book Docker image
• The docs folder hosts the book website files

Roadmap

Below is the book roadmap:

• V1 - Foundation of time series analysis
• V2 - Traditional time series forecasting methods (Smoothing, ARIMA, Linear Regression)
• V3 - Advanced regression methods (GLM, GAM, etc.)
• V4 - Bayesian forecasting approaches
• V5 - Machine and deep learning methods
• V6 - Scaling and production approaches

Docker

While it is not required, the book is built with Docker to ensure a high level of reproducibility.

Table of Contents

• Preface (V1)
• Introduction (V1)
• Prerequisites (V1)
• Dates and Times Objects (V1)
• The ts Class (V1)
• The timetk Class (V1)
• The tsibble Class (V1)
• Working with APIs (V2)
• Plotting Time Series Objects (V1)
• Seasonal Analysis (V1)
• Correlation Analysis (V1)
• Cluster Analysis (V2)
• Smoothing Methods (V1)
• Time Series Decomposition (V1)
• Forecasting Strategies (V2)
• Forecasting with Smoothing Models (V2)
• Time Series Properties (V2)
• Forecasting with ARIMA Models (V2)
• Forecasting with Linear Regression Model (V2)
• Forecasting with GLM Model (V3)
• Forecasting with GAM Model (V3)
• Forecasting with Bayesian Methods (V4)
• Forecasting with Machine Learning Methods (V5)
• Forecasting with Deep Learning Methods (V5)
• Forecasting at Scale (V6)
• Forecasting in Production (V6)

License

This book is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.