Machine.Learning.for.Hackers

【实例截图】

【核心代码】

Table of Contents
Preface ..................................................................... vii
1. Using R ................................................................ 1
R for Machine Learning 2
Downloading and Installing R 5
IDEs and Text Editors 8
Loading and Installing R Packages 9
R Basics for Machine Learning 12
Further Reading on R 27
2. Data Exploration ....................................................... 29
Exploration versus Confirmation 29
What Is Data? 30
Inferring the Types of Columns in Your Data 34
Inferring Meaning 36
Numeric Summaries 37
Means, Medians, and Modes 37
Quantiles 40
Standard Deviations and Variances 41
Exploratory Data Visualization 44
Visualizing the Relationships Between Columns 61
3. Classification: Spam Filtering ............................................ 73
This or That: Binary Classification 73
Moving Gently into Conditional Probability 77
Writing Our First Bayesian Spam Classifier 78
Defining the Classifier and Testing It with Hard Ham 85
Testing the Classifier Against All Email Types 88
Improving the Results 90
iii
4. Ranking: Priority Inbox ................................................. 93
How Do You Sort Something When You Don’t Know the Order? 93
Ordering Email Messages by Priority 95
Priority Features of Email 95
Writing a Priority Inbox 99
Functions for Extracting the Feature Set 100
Creating a Weighting Scheme for Ranking 108
Weighting from Email Thread Activity 113
Training and Testing the Ranker 117
5. Regression: Predicting Page Views ....................................... 127
Introducing Regression 127
The Baseline Model 127
Regression Using Dummy Variables 132
Linear Regression in a Nutshell 133
Predicting Web Traffic 141
Defining Correlation 152
6. Regularization: Text Regression ......................................... 155
Nonlinear Relationships Between Columns: Beyond Straight Lines 155
Introducing Polynomial Regression 158
Methods for Preventing Overfitting 165
Preventing Overfitting with Regularization 169
Text Regression 174
Logistic Regression to the Rescue 178
7. Optimization: Breaking Codes ........................................... 183
Introduction to Optimization 183
Ridge Regression 190
Code Breaking as Optimization 193
8. PCA: Building a Market Index ........................................... 205
Unsupervised Learning 205
9. MDS: Visually Exploring US Senator Similarity ............................. 215
Clustering Based on Similarity 215
A Brief Introduction to Distance Metrics and Multidirectional Scaling 216
How Do US Senators Cluster? 222
Analyzing US Senator Roll Call Data (101st–111th Congresses) 223
10. kNN: Recommendation Systems ......................................... 233
The k-Nearest Neighbors Algorithm 233
iv | Table of Contents
R Package Installation Data 239
11. Analyzing Social Graphs ................................................ 243
Social Network Analysis 243
Thinking Graphically 246
Hacking Twitter Social Graph Data 248
Working with the Google SocialGraph API 250
Analyzing Twitter Networks 256
Local Community Structure 257
Visualizing the Clustered Twitter Network with Gephi 261
Building Your Own “Who to Follow” Engine 267
12. Model Comparison .................................................... 275
SVMs: The Support Vector Machine 275
Comparing Algorithms 284
Works Cited ................................................................ 293
Index ..................................................................... 295