List of Tables

Chapter 1. The data science process

Table 1.1. Data science project roles and responsibilities

Table 1.2. Loan data attributes

Chapter 3. Exploring data

Table 3.1. Visualizations for one variable

Table 3.2. Visualizations for two variables

Chapter 5. Choosing and evaluating models

Table 5.1. Some common classification methods

Table 5.2. From problem to approach

Table 5.3. Ideal models to calibrate against

Table 5.4. Standard two-by-two confusion matrix

Table 5.5. Example classifier performance measures

Table 5.6. Classifier performance measures business stories

Table 5.7. Common model problems

Chapter 7. Linear and logistic regression

Table 7.1. Some variables in natality dataset

Chapter 8. Unsupervised methods

Table 8.1. A database of library transactions

Table 8.2. The five most confident rules discovered in the data

Chapter 9. Exploring advanced methods

Table 9.1. Some important kernels and their uses

Chapter 10. Documentation and deployment

Table 10.1. Chapter goals

Table 10.2. Buzz data description

Table 10.3. Maintenance tasks made easier by knitr

Table 10.4. Some useful knitr options

Table 10.5. Things not to worry about in comments

Table 10.6. A possible project directory structure

Table 10.7. Methods to demonstrate predictive model operation

Chapter 11. Producing effective presentations

Table 11.1. Entities in the buzz model scenario

Appendix A. Working with R and other tools

Table A.1. Major SQL column themes

Appendix B. Important statistical concepts

Table B.1. Test design parameters