Football Analytics with Python & R. Early Release

Preface

    Who This Book Is For
    Who This Book Is Not For
    How We Think About Data and How to Use This Book
    A Football Example
    What You Will Learn from Our Book
    Conventions Used in This Book
    Using Code Examples
    O’Reilly Online Learning
    How to Contact Us
    Acknowledgments

1. Football Analytics

    Baseball Has the Three True Outcomes: Does Football?
    Do Running Backs Matter?
    How Data Can Help Us Contextualize Passing Statistics
    Can You Beat the Odds?
    Do Teams Beat the Draft?
    Tools for Football Analytics
    First Steps in Python and R
    Example Data: Who Throws Deep?
        nflfastR in R
        nfl_data_py in Python
    Data Science Tools Used in This Chapter
    Suggested Readings

2. Exploring Data Analysis: Stable Versus Unstable Quarterback Statistics

    Defining Questions
    Obtaining and Filtering Data
    Summarizing Data
    Plotting Data
        Histograms
        Boxplots
    Player-Level Stability of Passing Yards per Attempt
        Deep Passes vs Short Passes
        So, What Should We Do with This Insight?
    Data Science Tools Used in This Chapter
    Exercises with Your Data
    Suggested Readings

3. Simple Linear Regression: Rushing Yards Over Expected

    Exploratory Data Analysis
    Simple Linear Regression
    Who Was the Best in RYOE?
    Is RYOE a Better Metric?
    Data Science Tools Used in This Chapter
    Exercises
    Suggested Readings

4. Multiple Regression: Rushing Yards Over Expected

    Definition of Multiple Linear Regression
    Exploratory Data Analysis
    Applying Multiple Linear Regression
    Analyzing RYOE
    So, Do Running Backs Matter?
    Assumption of Linearity
    Data Science Tools Used in This Chapter
    Exercises
    Suggested Readings

5. Generalized Linear Models: Completion Percentage Over Expected

    General Linear Models
    Building a GLM
    GLM Application to Completion Percentage
    Is CPOE More Stable Than Completion Percentage?
    A Question About Residual Metrics
    A Brief Primer on Odds Ratios
    Data Science Tools Used in This Chapter
    Exercises
    Suggested Readings

6. Using Data Science for Sports Betting: Poisson Regression and Passing

    The Main Markets in Football
    Application of Poisson Regression: Prop Markets
    The Poisson Distribution
    Individual Player Markets and Modeling
    Understanding Poisson Regression Coefficients
    Closing Thoughts on GLMS
    Data Science Tools Used in This Chapter
    Exercises
    Suggested Readings

7. Webscraping: Obtaining and Analyzing Draft Picks

    for Loops
    Web Scraping with Python
    Webscraping in R
    Analyzing the NFL Draft
    The Jets/Colts 2018 Trade Evaluated
    Are Some Teams Better at Drafting Players than Others?
    Data Science Tools Used in This Chapter
    Suggested Reading
    Exercises

8. Principal Component Analysis and Clustering: Player Attributes

    Web Scrapping and Visualizing NFL Combine Data
    Introduction to PCA
    PCA on All Data
    Clustering Combine Data
        Clustering Combine Data in Python
        Clustering Combine Data in R
        Closing Thoughts on Clustering
    Data Science Tools Used in This Chapter
    Exercises
    Suggested Reading

9. Advanced Tools and Next Steps

    Advanced Modeling Tools
        Time Series Analysis
        Multivariate Statistics Beyond PCA
        Quantile Regression
        Bayesian Statistics and Hierarchical Models
        Survival Analysis/Time-to-event
        Bayesian Networks/Structural Equation Modeling
        Machine Learning
    Command Line Tools
        Bash Example
        Suggested Reading for bash
    Version Control
        Git
        GitHub and GitLab
        GitHub Webpages and Resumes
    Suggested Reading for Git
    Style Guides and Linting
    Packages
        Suggested Reading for Packages
    Computer Environments
    Interactives and Report Tools to Share Data
    Artificial Intelligence Tools
    Conclusion

A. Python and R Basics

    Obtaining Python and R
        Local Installation
        Cloud-based Options
    Scripts
    Packages in Python and R
    nlffastR and nfl_py_data Tips
    Integrated Development Environments
    Basic Python Data Types

B. Summary Statistics and Data Wrangling: Passing the Ball

    Basic Statistics
        Averages
        Variability and Distribution
        Uncertainty Around Estimates
    Filtering and Selecting Columns
    Calculating Summary Statistics with Python and R
    A Note about Presenting Summary Statistics
    Improving your presentation
    Exercises
    Future readings

C. Data Wrangling Fundamentals

    Logic Operators
    Filtering and Sorting Data
    Cleaning
    Piping in R
    Checking and Cleaning Data for Outliers
    Merging Multiple Datasets

Glossary
About the Authors