Book Image

Deep Learning for Time Series Cookbook

By : Vitor Cerqueira, Luís Roque
Book Image

Deep Learning for Time Series Cookbook

By: Vitor Cerqueira, Luís Roque

Overview of this book

Most organizations exhibit a time-dependent structure in their processes, including fields such as finance. By leveraging time series analysis and forecasting, these organizations can make informed decisions and optimize their performance. Accurate forecasts help reduce uncertainty and enable better planning of operations. Unlike traditional approaches to forecasting, deep learning can process large amounts of data and help derive complex patterns. Despite its increasing relevance, getting the most out of deep learning requires significant technical expertise. This book guides you through applying deep learning to time series data with the help of easy-to-follow code recipes. You’ll cover time series problems, such as forecasting, anomaly detection, and classification. This deep learning book will also show you how to solve these problems using different deep neural network architectures, including convolutional neural networks (CNNs) or transformers. As you progress, you’ll use PyTorch, a popular deep learning framework based on Python to build production-ready prediction solutions. By the end of this book, you'll have learned how to solve different time series tasks with deep learning using the PyTorch ecosystem.

Related Content you might be interested in

Current Title:

Small book image
Deep Learning for Time Series Cookbook
Vitor Cerqueira | Luís Roque
Mar, 2024 | 274 pages
Small book image
Azure Strategy and Implementation Guide, Fourth Edition
Jason Milgram | David Rendoacuten | Aaditya Pokkunuri | Greg Leonardo | Jack Lee
May, 2021 | 228 pages
Small book image
Azure Integration Guide for Business
Meacutelony Qin | Joshua Garverick | Trevoir Williams | Jack Lee
Sep, 2023 | 268 pages
Small book image
SAP on Azure Implementation Guide
Nick Morgan | Bartosz Jarkowski
Feb, 2020 | 242 pages
Table of Contents (12 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Conventions used
Sections
Get in touch
Share Your Thoughts
Download a free PDF copy of this book
Free Chapter
1
Chapter 1: Getting Started with Time Series
Chapter 1: Getting Started with Time Series
Technical requirements
Loading a time series using pandas
Visualizing a time series
Resampling a time series
Dealing with missing values
Decomposing a time series
Computing autocorrelation
Detecting stationarity
Dealing with heteroskedasticity
Loading and visualizing a multivariate time series
Resampling a multivariate time series
Analyzing correlation among pairs of variables
2
Chapter 2: Getting Started with PyTorch
Chapter 2: Getting Started with PyTorch
Technical requirements
Installing PyTorch
Basic operations in PyTorch
Advanced operations in PyTorch
Building a simple neural network with PyTorch
Training a feedforward neural network
Training a recurrent neural network
Training an LSTM neural network
Training a convolutional neural network
3
Chapter 3: Univariate Time Series Forecasting
Chapter 3: Univariate Time Series Forecasting
Technical requirements
Building simple forecasting models
Univariate forecasting with ARIMA
Preparing a time series for supervised learning
Univariate forecasting with a feedforward neural network
Univariate forecasting with an LSTM
Univariate forecasting with a GRU
Univariate forecasting with a Stacked LSTM
Combining an LSTM with multiple fully connected layers
Univariate forecasting with a CNN
Handling trend – taking first differences
Handling seasonality – seasonal dummies and Fourier series
Handling seasonality – seasonal differencing
Handling seasonality – seasonal decomposition
Handling non-constant variance – log transformation
4
Chapter 4: Forecasting with PyTorch Lightning
Chapter 4: Forecasting with PyTorch Lightning
Technical requirements
Preparing a multivariate time series for supervised learning
Training a linear regression model for forecasting with a multivariate time series
Feedforward neural networks for multivariate time series forecasting
LSTM neural networks for multivariate time series forecasting
Monitoring the training process using Tensorboard
Evaluating deep neural networks for forecasting
Using callbacks – EarlyStopping
5
Chapter 5: Global Forecasting Models
Chapter 5: Global Forecasting Models
Technical requirements
Multi-step forecasting with multivariate time series
Multi-step and multi-output forecasting with multivariate time series
Preparing multiple time series for a global model
Training a global LSTM with multiple time series
Global forecasting models for seasonal time series
Hyperparameter optimization using Ray Tune
6
Chapter 6: Advanced Deep Learning Architectures for Time Series Forecasting
Chapter 6: Advanced Deep Learning Architectures for Time Series Forecasting
Technical requirements
Interpretable forecasting with N-BEATS
Optimizing the learning rate with PyTorch Forecasting
Getting started with GluonTS
Training a DeepAR model with GluonTS
Training a Transformer model with NeuralForecast
Training a Temporal Fusion Transformer with GluonTS
Training an Informer model with NeuralForecast
Comparing different Transformers with NeuralForecast
7
Chapter 7: Probabilistic Time Series Forecasting
Chapter 7: Probabilistic Time Series Forecasting
Technical requirements
Introduction to exceedance probability forecasting
Exceedance probability forecasting with an LSTM
Creating prediction intervals using conformal prediction
Probabilistic forecasting with an LSTM
Probabilistic forecasting with DeepAR
Introduction to Gaussian Processes
Using Prophet for probabilistic forecasting
8
Chapter 8: Deep Learning for Time Series Classification
Chapter 8: Deep Learning for Time Series Classification
Technical requirements
Tackling TSC with K-nearest neighbors
Building a DataModule class for TSC
Convolutional neural networks for TSC
ResNets for TSC
Tackling TSC problems with sktime
9
Chapter 9: Deep Learning for Time Series Anomaly Detection
Chapter 9: Deep Learning for Time Series Anomaly Detection
Technical requirements
Time series anomaly detection with ARIMA
Prediction-based anomaly detection using DL
Anomaly detection using an LSTM AE
Building an AE using PyOD
Creating a VAE for time series anomaly detection
Using GANs for time series anomaly detection
10
Index
Index
Why subscribe?
11
Other Books You May Enjoy
Other Books You May Enjoy
Packt is searching for authors like you
Share Your Thoughts
Download a free PDF copy of this book

Visualizing a time series

Now, we have a time series loaded in a Python session. This recipe walks you through the process of visualizing a time series in Python. Our goal is to create a line plot of the time series data, with the dates on the x axis and the value of the series on the y axis.

Getting ready

There are several data visualization libraries in Python. Visualizing a time series is useful to quickly identify patterns such as trends or seasonal effects. A graphic is an easy way to understand the dynamics of the data and to spot any anomalies within it.

In this recipe, we will create a time series plot using two different libraries: pandas and seaborn. seaborn is a popular data visualization Python library.

How to do it…

pandas Series objects contain a plot() method for visualizing time series. You can use it as follows:

series.plot(figsize=(12,6), title='Solar radiation time series')

The plot() method is called with two arguments. We use the figsize argument to change the size of the plot. In this case, we set the width and height of the figure to 12 and 6 inches, respectively. Another argument is title, which we set to Solar radiation time series. You can check the pandas documentation for a complete list of acceptable arguments.

You use it to plot a time series using seaborn as follows:

import matplotlib.pyplot as plt
import seaborn as sns
series_df = series.reset_index()
plt.rcParams['figure.figsize'] = [12, 6]
sns.set_theme(style='darkgrid')
sns.lineplot(data=series_df, x='Datetime', y='Incoming Solar')
plt.ylabel('Solar Radiation')
plt.xlabel('')
plt.title('Solar radiation time series')
plt.show()
plt.savefig('assets/time_series_plot.png')

The preceding code includes the following steps:

  1. Import seaborn and matplotlib, two data visualization libraries.
  2. Transform the time series into a pandas DataFrame object by calling the reset_index() method. This step is required because seaborn takes DataFrame objects as the main input.
  3. Configure the figure size using plt.rcParams to a width of 12 inches and a height of 6 inches.
  4. Set the plot theme to darkgrid using the set_theme() method.
  5. Use the lineplot() method to build the plot. Besides the input data, it takes the name of the column for each of the axes: Datetime and Incoming Solar for the x axis and y axis, respectively.
  6. Configure the plot parameters, namely the y-axis label (ylabel), x-axis label (xlabel), and title.
  7. Finally, we use the show method to display the plot and savefig to store it as a .png file.

How it works…

The following figure shows the plot obtained from the seaborn library:

Figure 1.1: Time series plot using seaborn

Figure 1.1: Time series plot using seaborn

The example time series shows a strong yearly seasonality, where the average level is lower at the start of the year. Apart from some fluctuations and seasonality, the long-term average level of the time series remains stable over time.

We learned about two ways of creating a time series plot. One uses the plot() method that is available in pandas, and another one uses seaborn, a Python library dedicated to data visualization. The first one provides a quick way of visualizing your data. But seaborn has a more powerful visualization toolkit that you can use to create beautiful plots.

There’s more…

The type of plot created in this recipe is called a line plot. Both pandas and seaborn can be used to create other types of plots. We encourage you to go through the documentation to learn about these.

Previous Section
End of Section 4
Next Section