数据科学中的实用线性代数（影印版）
数据科学中的实用线性代数（影印版）
Mike X Cohen 著
出版时间：2023年03月
页数：311
“对于新手来说，线性代数的抽象本质使他们难以看到这门学科有什么用处，尽管其应用十分广泛。这本书很好地讲授了线性代数的实际应用以及来龙去脉。”
——Thomas Nield
Nield Consulting Group，Essential Math for Data Science和Getting Started with SQL作者

如果你想从事计算或技术领域的工作，理解线性代数是少不了的。线性代数的研究对象是矩阵及其运算，是几乎所有计算机算法和分析的数学基础。但它在几十年前的教科书中的呈现方式与专业人员如今用来解决现实世界问题的方式有很大不同。
这本来自Mike X Cohen的实用指南讲授了以Python实现的线性代数的核心概念，包括如何在数据科学、机器学习、深度学习、计算模拟和生物医学数据处理应用中使用它们。有了这本书，理解、实现和适应繁多的现代分析方法和算法将不再是问题。
本书适用于使用计算机技术和算法的业界人士和学生，内容包括：
● 向量和矩阵的讲解和应用
● 矩阵运算（各种矩阵乘法和变换）
● 独立性、秩、转置
● 线性代数中使用的重要分解（包括LU和QR）
● 特征分解和奇异值分解
● 最小二乘模型拟合和主成分分析等应用
  1. Preface
  2. 1. Introduction
  3. What Is Linear Algebra and Why Learn It?
  4. About This Book
  5. Prerequisites
  6. Mathematical Proofs Versus Intuition from Coding
  7. Code, Printed in the Book and Downloadable Online
  8. Code Exercises
  9. How to Use This Book (for Teachers and Self Learners)
  10. 2. Vectors, Part 1
  11. Creating and Visualizing Vectors in NumPy
  12. Operations on Vectors
  13. Vector Magnitude and Unit Vectors
  14. The Vector Dot Product
  15. Other Vector Multiplications
  16. Orthogonal Vector Decomposition
  17. Summary
  18. Code Exercises
  19. 3. Vectors, Part 2
  20. Vector Sets
  21. Linear Weighted Combination
  22. Linear Independence
  23. Subspace and Span
  24. Basis
  25. Summary
  26. Code Exercises
  27. 4. Vector Applications
  28. Correlation and Cosine Similarity
  29. Time Series Filtering and Feature Detection
  30. k-Means Clustering
  31. Code Exercises
  32. 5. Matrices, Part 1
  33. Creating and Visualizing Matrices in NumPy
  34. Matrix Math: Addition, Scalar Multiplication, Hadamard Multiplication
  35. Standard Matrix Multiplication
  36. Matrix Operations: Transpose
  37. Matrix Operations: LIVE EVIL (Order of Operations)
  38. Symmetric Matrices
  39. Summary
  40. Code Exercises
  41. 6. Matrices, Part 2
  42. Matrix Norms
  43. Matrix Spaces (Column, Row, Nulls)
  44. Rank
  45. Rank Applications
  46. Determinant
  47. Summary
  48. Code Exercises
  49. 7. Matrix Applications
  50. Multivariate Data Covariance Matrices
  51. Geometric Transformations via Matrix-Vector Multiplication
  52. Image Feature Detection
  53. Summary
  54. Code Exercises
  55. 8. Matrix Inverse
  56. The Matrix Inverse
  57. Types of Inverses and Conditions for Invertibility
  58. Computing the Inverse
  59. The Inverse Is Unique
  60. Moore-Penrose Pseudoinverse
  61. Numerical Stability of the Inverse
  62. Geometric Interpretation of the Inverse
  63. Summary
  64. Code Exercises
  65. 9. Orthogonal Matrices and QR Decomposition
  66. Orthogonal Matrices
  67. Gram-Schmidt
  68. QR Decomposition
  69. Summary
  70. Code Exercises
  71. 10. Row Reduction and LU Decomposition
  72. Systems of Equations
  73. Row Reduction
  74. LU Decomposition
  75. Summary
  76. Code Exercises
  77. 11. General Linear Models and Least Squares
  78. General Linear Models
  79. Solving GLMs
  80. GLM in a Simple Example
  81. Least Squares via QR
  82. Summary
  83. Code Exercises
  84. 12. Least Squares Applications
  85. Predicting Bike Rentals Based on Weather
  86. Polynomial Regression
  87. Grid Search to Find Model Parameters
  88. Summary
  89. Code Exercises
  90. 13. Eigendecomposition
  91. Interpretations of Eigenvalues and Eigenvectors
  92. Finding Eigenvalues
  93. Finding Eigenvectors
  94. Diagonalizing a Square Matrix
  95. The Special Awesomeness of Symmetric Matrices
  96. Eigendecomposition of Singular Matrices
  97. Quadratic Form, Definiteness, and Eigenvalues
  98. Generalized Eigendecomposition
  99. Summary
  100. Code Exercises
  101. 14. Singular Value Decomposition
  102. The Big Picture of the SVD
  103. SVD in Python
  104. SVD and Rank-1 “Layers” of a Matrix
  105. SVD from EIG
  106. SVD and the MP Pseudoinverse
  107. Summary
  108. Code Exercises
  109. 15. Eigendecomposition and SVD Applications
  110. PCA Using Eigendecomposition and SVD
  111. Linear Discriminant Analysis
  112. Low-Rank Approximations via SVD
  113. Summary
  114. Exercises
  115. 16. Python Tutorial
  116. Why Python, and What Are the Alternatives?
  117. IDEs (Interactive Development Environments)
  118. Using Python Locally and Online
  119. Variables
  120. Functions
  121. Visualization
  122. Translating Formulas to Code
  123. Print Formatting and F-Strings
  124. Control Flow
  125. Measuring Computation Time
  126. Getting Help and Learning More
  127. Summary
  128. Index
书名：数据科学中的实用线性代数（影印版）
作者：Mike X Cohen 著
国内出版社：东南大学出版社
出版时间：2023年03月
页数：311
书号：978-7-5766-0588-4
原版书书名：Practical Linear Algebra for Data Science
原版书出版商：O'Reilly Media
Mike X Cohen
 
Mike X Cohen是荷兰唐德斯研究所（拉德堡德大学医学中心）的神经科学副教授。他在科学编程、数据分析、统计学和相关主题的教学方面拥有20多年的经验，并且已经创作了多门在线课程和教材。Mike身上有一种冷幽默感，喜欢紫色的东西。
 
 
The animal on the cover of Practical Linear Algebra for Data Science is a nays antelope, also known as the lowland nyala or simply nyala (Tragelaphus angasii). Female and juvenile nyalas are typically a light reddish-brown, while adult males have a dark brown or even grayish coat. Both males and females have white stripes along the body and white spots on the flank. Males have spiral-shaped horns that can grow up to 33 inches long, and their coats are much shaggier, with a long fringe hanging from their throats to their hindquarters and a mane of thick black hair along their spines. Females weigh about 130 pounds, while males can weigh as much as 275 pounds.
Nyalas are native to the woodlands of southeastern Africa, with a range that includes Malawi, Mozambique, South Africa, Eswatini, Zambia, and Zimbabwe. They are shy creatures, preferring to graze in the early morning, late afternoon, or nighttime, and spending most of the hot part of the day resting among cover. Nyalas form loose herds of up to ten animals, though older males are solitary. They are not territorial, though males will fight over dominance during mating.
Nyalas are considered a species of least concern, though cattle grazing, agriculture, and habitat loss pose a threat to them.
购买选项
定价：109.00元
书号：978-7-5766-0588-4
出版社：东南大学出版社
联系出版社邮购

© 2024，奥莱利技术咨询(北京)有限公司。版权所有。
传真: +86-10-88097463
 京ICP备05003502号