Contents
Acknowledgements iii
Preface viii
How to Get the Absolute Most Possible Benefit from this Book 1
Getting Python . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Learning Python . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
Using Packages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 5
1 The Characteristics of Time Series Data Simplified 7
Understanding the Data Generating Mechanism . . . . . . . . . . . . . . . . . 7
Generating a Simple Time Series using Python . . . . . . . . . . . . . . . . . 9
Randomness and Reproducibility . . . . . . . . . . . . . . . . . . . . . . . . 12
The Importance of Temporal Order . . . . . . . . . . . . . . . . . . . . . . . . 13
The Ultimate Goal . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
For Additional Exploration . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2 Deep Neural Networks Explained 17
What is a Neural Network? . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
The Role of Neuron . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
Deep Learning in a Nutshell . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
Generating Data for use with a Deep Neural Network . . . . . . . . . . . . . 21
Exploring the Sample Data . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
Translating Sample Data into a Suitable Format . . . . . . . . . . . . . . . . 25
A Super Easy Deep Neural Network Tool . . . . . . . . . . . . . . . . . . . . 26
Assessing Model Performance . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 30
3 Deep Neural Networks for Time Series Forecasting the Easy Way 31
Getting the Data from the Internet . . . . . . . . . . . . . . . . . . . . . . . 31
Cleaning up Downloaded Spreadsheet Files . . . . . . . . . . . . . . . . . . . 33
Understanding Activation Functions . . . . . . . . . . . . . . . . . . . . . . . 36
How to Scale the Input attributes . . . . . . . . . . . . . . . . . . . . . . . . 39
Assessing Partial Autocorrelation . . . . . . . . . . . . . . . . . . . . . . . . . 42
A Neural Network Architecture for Time Series Forecasting . . . . . . . . . . 45
Additional Resources to Check Out . . . . . . . . . . . . . . . . . . . . . . . . 49
i
评论7