book

Deep Learning for Time Series Cookbook

Name: Deep Learning for Time Series Cookbook
ISBN: 9781805129233

by Vitor Cerqueira, Luís Roque

March 2024

Beginner to intermediate

274 pages

5h 50m

English

Packt Publishing

Read now

Unlock full access

Deep Learning for Time Series Cookbook
ContributorsAbout the authorsAbout the reviewer
Preface
Who this book is forWhat this book coversTo get the most out of this bookDownload the example code filesConventions usedSectionsGetting readyHow to do it…How it works…There’s more…See alsoGet in touchShare Your ThoughtsDownload a free PDF copy of this book
Chapter 1: Getting Started with Time Series
Technical requirementsLoading a time series using pandasGetting readyHow to do it…How it works…Visualizing a time seriesGetting readyHow to do it…How it works…There’s more…Resampling a time seriesGetting readyHow to do it…How it works…There’s more…Dealing with missing valuesGetting readyHow to do it…How it works…There’s more…Decomposing a time seriesGetting readyHow to do it…How it works…There’s more…See alsoComputing autocorrelationGetting readyHow to do it…How it works…There’s more…Detecting stationarityGetting readyHow to do it…How it works…There’s more…Dealing with heteroskedasticityGetting readyHow to do it…How it works…There’s more…See alsoLoading and visualizing a multivariate time seriesGetting readyHow to do it…How it works…Resampling a multivariate time seriesGetting readyHow to do it…How it works…Analyzing correlation among pairs of variablesGetting readyHow to do it…How it works…
Chapter 2: Getting Started with PyTorch
Technical requirementsInstalling PyTorchGetting readyHow to do it…How it works…Basic operations in PyTorchGetting readyHow to do it…How it works…Advanced operations in PyTorchGetting readyHow to do it…How it works…Building a simple neural network with PyTorchGetting readyHow to do it…There’s more…Training a feedforward neural networkGetting readyHow to do it…How it works…Training a recurrent neural networkGetting readyHow to do it…How it works…Training an LSTM neural networkGetting readyHow to do it…How it works…Training a convolutional neural networkGetting readyHow to do it…How it works…
Chapter 3: Univariate Time Series Forecasting
Technical requirementsBuilding simple forecasting modelsGetting readyHow to do it…How it works…There’s more…Univariate forecasting with ARIMAGetting readyHow to do it…How it works…There’s more…Preparing a time series for supervised learningGetting readyHow to do it…How it works…There’s more…Univariate forecasting with a feedforward neural networkGetting readyHow to do it…How it works…There’s more…Univariate forecasting with an LSTMGetting readyHow to do it…How it works…There’s more…Univariate forecasting with a GRUGetting readyHow to do it…How it works…There’s more…Univariate forecasting with a Stacked LSTMGetting readyHow to do it…How it works…Combining an LSTM with multiple fully connected layersGetting readyHow to do it…How it works…There’s more…Univariate forecasting with a CNNGetting readyHow to do it…How it works…There’s more…Handling trend – taking first differencesGetting readyHow to do it…How it works…There’s more…Handling seasonality – seasonal dummies and Fourier seriesGetting readyHow to do it…How it works…There’s more…Handling seasonality – seasonal differencingGetting readyHow to do it…How it works…Handling seasonality – seasonal decompositionGetting readyHow to do it…How it works…Handling non-constant variance – log transformationGetting readyHow to do it…How it works…
Chapter 4: Forecasting with PyTorch Lightning
Technical requirementsPreparing a multivariate time series for supervised learningGetting readyHow to do it…How it works…Training a linear regression model for forecasting with a multivariate time seriesGetting readyHow to do it…How it works…Feedforward neural networks for multivariate time series forecastingGetting readyHow to do it…How it works…There’s more…LSTM neural networks for multivariate time series forecastingGetting readyHow to do it…How it works…There’s more…Monitoring the training process using TensorboardGetting readyHow to do it…How it works…There’s more…Evaluating deep neural networks for forecastingGetting readyHow to do it…How it works…There’s more…Using callbacks – EarlyStoppingGetting readyHow to do it…How it works…There’s more…
Chapter 5: Global Forecasting Models
Technical requirementsMulti-step forecasting with multivariate time seriesGetting readyHow to do it…How it works…There’s more…Multi-step and multi-output forecasting with multivariate time seriesGetting readyHow to do it…How it works…Preparing multiple time series for a global modelGetting readyHow to do it…How it works…Training a global LSTM with multiple time seriesGetting readyHow to do it…How it works…Global forecasting models for seasonal time seriesGetting readyHow to do it…How it works…There’s more…Hyperparameter optimization using Ray TuneGetting readyHow to do it…How it works…There’s more…
Chapter 6: Advanced Deep Learning Architectures for Time Series Forecasting
Technical requirementsInterpretable forecasting with N-BEATSGetting readyHow to do it…How it works…There’s more…Optimizing the learning rate with PyTorch ForecastingGetting readyHow to do it…How it works…There’s more…Getting started with GluonTSGetting readyHow to do it…How it works…Training a DeepAR model with GluonTSGetting readyHow to do it…How it works…There’s more…Training a Transformer model with NeuralForecastGetting readyHow to do it…How it works…There’s more…Training a Temporal Fusion Transformer with GluonTSGetting readyHow to do it…How it works…There’s more…Training an Informer model with NeuralForecastGetting readyHow to do it…How it works…There’s more…Comparing different Transformers with NeuralForecastGetting readyHow to do it…How it works…
Chapter 7: Probabilistic Time Series Forecasting
Technical requirementsIntroduction to exceedance probability forecastingGetting readyHow to do it…How it works…There’s more…Exceedance probability forecasting with an LSTMGetting readyHow to do it…How it works…There’s more…Creating prediction intervals using conformal predictionGetting readyHow to do it…How it works…Probabilistic forecasting with an LSTMGetting readyHow to do it…How it works…Probabilistic forecasting with DeepARGetting readyHow to do it…How it works…Introduction to Gaussian ProcessesGetting readyHow to do it…How it works…Using Prophet for probabilistic forecastingGetting readyHow to do it…How it works…There’s more…
Chapter 8: Deep Learning for Time Series Classification
Technical requirementsTackling TSC with K-nearest neighborsGetting readyHow to do it…How it works…There’s more…Building a DataModule class for TSCGetting readyHow to do it…How it works…Convolutional neural networks for TSCGetting readyHow to do it…How it works…ResNets for TSCGetting readyHow to do it…How it works…Tackling TSC problems with sktimeGetting readyHow to do it…How it works…There’s more…

Chapter 9: Deep Learning for Time Series Anomaly Detection
Technical requirementsTime series anomaly detection with ARIMAGetting readyHow to do it…How it works…There’s more…Prediction-based anomaly detection using DLGetting readyHow to do it…How it works…There’s more…Anomaly detection using an LSTM AEGetting readyHow to do it…How it works…Building an AE using PyODGetting readyHow to do it…How it works…There’s more…Creating a VAE for time series anomaly detectionGetting readyHow to do it…How it works…There’s more…Using GANs for time series anomaly detectionGetting ready…How to do it…How it works…There’s more…
Index
Why subscribe?
Other Books You May EnjoyPackt is searching for authors like youShare Your ThoughtsDownload a free PDF copy of this book

Content preview from Deep Learning for Time Series Cookbook

6 Advanced Deep Learning Architectures for Time Series Forecasting

In previous chapters, we’ve learned how to create forecasting models using different types of neural networks but, so far, we’ve worked with basic architectures such as feedforward neural networks or LSTMs. This chapter describes how to build forecasting models with state-of-the-art approaches such as DeepAR or Temporal Fusion Transformers. These have been developed by tech giants such as Google and Amazon and are available in different Python libraries. These advanced deep learning architectures are designed to tackle different types of forecasting problems.

We’ll cover the following recipes:

Interpretable forecasting with N-BEATS
Optimizing the learning rate with PyTorch Forecasting ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Time Series Analysis with Python Cookbook

Publisher Resources

ISBN: 9781805129233

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Deep Learning for Time Series Cookbook

by Vitor Cerqueira, Luís Roque

6

Advanced Deep Learning Architectures for Time Series Forecasting

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.