Cover
Contents
Preface
1. Introduction
1.1 Why Data Science?
1.2 Who This Book Is For
1.3 How We Wrote This Book
1.4 How You Might Read This Book
1.5 Additional Resources
PART I. The Data Science Toolbox
2. The Unix Operating System
2.1 Using Unix
2.2 More About Unix
2.3 Additional Resources
3. Version Control
3.1 Getting Started with Git
3.2 Working with Git at the First Level: Tracking Changes That You Make
3.3 Working with Git at the Second Level: Branching and Merging
3.4 Working with Git at the Third Level: Collaborating with Others
3.5 Additional Resources
4. Computational Environments and Computational Containers
4.1 Creating Virtual Environments with Conda
4.2 Containerization with Docker
4.3 Setting Up
4.4 Additional Resources
PART II. Programming
5. A brief Introduction to Python
5.1 What Is Python?
5.2 Variables and Basic Types
5.3 Collections
5.4 Everything in Python Is an Object
5.5 Control Flow
5.6 Namespaces and Imports
5.7 Functions
5.8 Classes
5.9 Additional Resources
6. The Python Environment
6.1 Choosing a Good Editor
6.2 Debugging
6.3 Testing
6.4 Profiling Code
6.5 Summary
6.6 Additional Resources
7. Sharing Code with Others
7.1 What Should Be Shareable?
7.2 From Notebook to Module
7.3 From Module to Package
7.4 The Setup File
7.5 A Complete Project
7.6 Summary
7.7 Additional Resources
PART III. Scientific Computing
8. The Scientific Python Ecosystem
8.1 Numerical Computing in Python
8.2 Introducing NumPy
8.3 Additional Resources
9. Manipulating Tabular Data with Pandas
9.1 Summarizing DataFrames
9.2 Indexing into DataFrames
9.3 Computing with DataFrames
9.4 Joining Different Tables
9.5 Additional Resources
10. Visualizing Data with Python
10.1 Creating Pictures from Data
10.2 Scatter Plots
10.3 Statistical Visualizations
10.4 Additional Resources
PART IV. Neuroimaging in Python
11. Data Science Tools for Neuroimaging
11.1 Neuroimaging in Python
11.2 The Brain Imaging Data Structure Standard
11.3 Additional Resources
12. Reading Neuroimaging Data with NiBabel
12.1 Assessing MRI Data Quality
12.2 Additional Resources
13. Using Nibabel to Align Different Measurements
13.1 Coordinate Frames
13.2 Multiplying Matrices in Python
13.3 Using the Affine
13.4 Additional Resources
PART V. Image Processing
14. Image Processing
14.1 Images Are Arrays
14.2 Images Can Have Two Dimensions or More
14.3 Images Can Have Other Special Dimensions
14.4 Operations with Images
14.5 Additional Resources
15. Image Segmentation
15.1 Intensity-Based Segmentation
15.2 Edge-Based Segmentation
15.3 Additional Resources
16. Image Registration
16.1 Affine Registration
16.2 Summary
16.3 Additional Resources
PART VI. Machine Learning
17. The Core Concepts of Machine Learning
17.1 What Is Machine Learning?
17.2 Supervised versus Unsupervised Learning
17.3 Supervised Learning: Classification versus Regression
17.4 Unsupervised Learning: Clustering and Dimensionality Reduction
17.5 Additional Resources
18. The Scikit-Learn Package
18.1 The ABIDE II Data set
18.2 Regression Example: Brain-Age Prediction
18.3 Classification Example: Autism Classification
18.4 Clustering Example: Are There Neural Subtypes of Autism?
18.5 Additional Resources
19. Overfitting
19.1 Understanding Overfitting
19.2 Additional Resources
20. Validation
20.1 Cross-Validation
20.2 Learning and Validation Curves
20.3 Additional Resources
21. Model Selection
21.1 Bias and Variance
21.2 Regularization
21.3 Beyond Linear Regression
21.4 Additional Resources
22. Deep Learning
22.1 Artificial Neural Networks
22.2 Learning through Gradient Descent and Back Propagation
22.3 Introducing Keras
22.4 Convolutional Neural Networks
22.5 Additional Resources
PART VII. Appendices
Appendix 1: Solutions to Exercises
A1.1 The Data Science Toolbox
A1.2 Programming
A1.3 Scientific Computing
A1.4 Neuroimaging in Python
A1.5 Image Processing
A1.6 Machine Learning
Appendix 2: ndslib Function Reference
Bibliography
Index