DOCSLIB.ORG

Going Long on Machine Learning

Total Page：16

File Type：pdf, Size：1020Kb

Download full-text PDF Read full-text
Going Long on Machine Learning machine learning GOING LONG ON MACHINE LEARNING How AWS and the NFL teamed up to transform a 100-year-old league TABLE OF CONTENTS Introduction 03 Letter from Michelle McKenna, SVP and CIO of the NFL What are the odds? 04 Opening story What happened? 05 The data behind the stat The factors 06 How is Completion Probability calculated? The mechanics 08 How does Next Gen Stats calculate Completion Probability? The formula 09 How the machine learning models are trained The journey 11 The NFL’s machine learning journey The problem 13 Why machine learning? The end results 14 Measuring the impact Ready for more? 15 Taking machine learning beyond the end zones Get in the game 16 Resources Glossary 17 More stats 2 INTRODUCTION If you grew up in a Web Services. Working with AWS just made sense because of their football family like I did, flexibility, security, and ability to scale. you might already know that the AWS has the broadest offering of NFL is America’s largest sports cloud services for our builders to We’re excited to share organization, with over 188 million build upon—giving us the ideal this portion of our fans worldwide. We’re a big content platform to grow. “ creator—NFL games accounted for journey with you and For me, getting started with machine 38 of last year’s top 50 telecasts. learning was not a question of “why” help you see a little bit We’re also a big data creator— but of “how.” I knew machine learning every week our league generates of what we’ve been up would transform our company. I also 3terabytes, equivalent to 1,500 knew our technology projects needed to at the NFL. hours, of data. to be supported at the top level of As CIO of the NFL, I’m responsible the organization to get both the for ensuring we leverage our data to business and technical teams We’re working to build a better create the best and most efficient working together and sharing playing, coaching, and viewing technology solutions that will evolve the same priorities. experience. Thanks to AWS machine our game, engage our fans, and learning, we’re revolutionizing a Implementing machine learning protect and develop our players. 100-year-old league. benefits the entire company, not just the technology department. Machine learning has made the NFL’s production teams more efficient— transforming previously tedious roles Transforming a like video labeling into an automated, 100-year-old league streamlined process. Coaches can use “ the technology to officiate playbook is not an easy job. formations and automatically draw Likewise, the NFL’s out plays, saving them time on the sidelines. With the power of machine machine learning learning on AWS, we can better journey has not been a understand fan engagement, how a game is presented, the potential straightforward path. impact of adjusting the rules of play, how the game is called, and player performance and safety. Next Gen Michelle McKenna Next Gen Stats, one of our machine Stats allows us to use this real-time Senior Vice President and CIO, NFL learning projects—is the product of data to engage, inform, and empower our working partnership with Amazon fans in new and unique ways. 3 WHAT ARE THE ODDS? It was Sunday night, week one in the 2018 season, fourth quarter. The Green Bay Packers were down 3 to 20 against longtime rival the Chicago Bears. Aaron Rodgers, who sat out much of the first half from a knee injury, was back in the game, but things weren’t looking good. Second and 2, and Corey Linsley snaps to Rodgers. Man-to-man coverage. All eyes are on Rodgers, who appears to have time, except nobody down the field looks open. Rodgers steps back and launches. FPO Not all passes are created equal. When players defy the odds, we are exposed to how talented they truly are. But this often doesn’t get represented by traditional box score stats, which would score Rodgers the same whether his pass traveled three yards behind the line of scrimmage to an open running back or whether his pass did what happened next. The ball sails 39 yards down the field toward the back-right corner of the Bears’ end zone, and the Bears’ Kyle Fuller is all over Geronimo Allison, the target of the last several of Rodgers’ first-down throws. Everyone can see it’s an unlikely catch as it arcs toward the pylon. But how unlikely? Next Gen Stats, powered by machine learning models built on Amazon SageMaker from AWS, had just launched another new metric for the 2018 season called Completion Probability, which leverages tracking data to improve upon the limitations of raw box score stats and add context to each passing play. Next Gen Stats calculated the pass had just a 14.7% Completion Probability—the most improbable completion that week. Allison leaps with Fuller on his back, in full reach, fingers wide to swat the ball, and misses by what seems like inches. The ball lands right in the pocket as Allison cradles it close and plants two feet with full control before sliding out of bounds for a touchdown. This is the beginning of the end for the Bears, who ultimately lose the game 23-24 to a significant fourth-quarter comeback for the Packers. 4 WHAT HAPPENED? The data behind the stat By Matt Swensson, Vice President of Emerging Products and Technology of the NFL Completion Probability is measured All of those factors, among several using more than 10 different in-play others, had a direct relationship with factors starting with data transmitted the likelihood Rodgers’ pass would by RFID chips in the football and on be complete or incomplete. We players’ shoulder pads all collected by can evaluate these relationships by RF receivers around the stadium. plotting each in-play factor against the actual completion percentage In the case of Rodgers, the data to better understand each factor’s shows the pass traveling 60.3 yards in effect on the outcome of a play and the air from the location of Rodgers contextualize the difficulty of a throw. at the time of the throw to Allison at the time of the catch. Rodgers Let’s review some of these factors had 2.1 yards of separation from and examine how the predictive Jonathan Bullard when he released models were trained. the ball, and Allison had 0.9 yards of separation from Kyle Fuller at the moment of the catch. 5 MLUNDERSTANDING DIFFERENCE THE FACTORS Completion Probability’s top factors 1.0 Air Distance 0.8 The further the ball has to travel, the lower the likelihood of completion. This 1 is measured by the air distance – the true 0.6 distance from the location the ball is thrown to where it is caught. Passes traveling xComp 0.4 more than 40 air distance yards have approximately 20% chance of completion. 0.2 1.0 0.0 0 10 20 30 40 50 60 70 Air distance 0.8 0.6 Target Separation xComp As the distance between the receiver and 0.4 nearest defender increases, the likelihood 2 of a completion also increases. The larger 0.2 circles at lower target separation show that it’s more common for receivers to have close defenders. 0.0 0 2 4 6 8 10 12 14 Target separation at pass arried Sideline Separation As the distance between the receiver and the sideline decreases, the likelihood of a 3 completion also decreases. The probability of a completed pass decreases rapidly at five yards of sideline separation. Controlling for all other factors, passes to the sideline xComp just inside the white paint have a roughly 30% chance of a completion. After about 10 yards, we see diminishing returns. Separation from sideline 6 MLUNDERSTANDING DIFFERENCE THE FACTORS 1.0 Pass Rush Separation 0.8 As the distance between the quarterback and nearest pass rusher at the time of 4 the throw decreases, the likelihood of a 0.6 completion also decreases. A quarterback xComp throwing with no defenders around has 0.4 a higher probability of a completed pass compared to a quarterback with a pass 0.2 rusher within a few yards at the time of the throw. 0.0 0 1 2 3 4 5 Closest to b 1.0 0.8 Passer Speed As the speed of the quarterback at the time 0.6 of the throw increases, the likelihood of a 5 completed pass decreases. Speeds below xComp 8 MPH have little effect on the probability 0.4 of a completion. However, as the speed of the quarterback increases above 8 MPH, the 0.2 chance of a completion decreases. 0.0 0 2 4 6 8 10 12 14 16 18 1.0 Passer speed at pass forward 0.8 Time to Throw 0.6 Most passes occur between 2 and 3 seconds after the snap. As the duration xComp 6 of time increases from snap to throw, the 0.4 likelihood of a completed pass decreases. The probability of a completion declines 0.2 significantly after 3 seconds. 0.0 0 1 2 3 4 5 6 Time to throw These are just a few of the data points measured and fed into machine learning model to develop the Next Gen Stats Completion Probability metric. Next we’ll explore why the NFL decided to use machine learning. 7 THE MECHANICS How does Next Gen Stats calculate Completion Probability? Amazon SageMaker Building and training machine learning models used to be By Jarvis Lee, AWS Data Scientist and Tyler Mullenbach, AWS Practice Manager locked in the ivory towers of elite developers and data By leveraging AWS’ broad range Stats team to reflect the trends and scientists.
Load more

Recommended publications
  • The Wild Bunch a Side Order of Football
    THE WILD BUNCH A SIDE ORDER OF FOOTBALL AN OFFENSIVE MANUAL AND INSTALLATION GUIDE BY TED SEAY THIRD EDITION January 2006 TABLE OF CONTENTS INTRODUCTION p. 3 1. WHY RUN THE WILD BUNCH? 4 2. THE TAO OF DECEPTION 10 3. CHOOSING PERSONNEL 12 4. SETTING UP THE SYSTEM 14 5. FORGING THE LINE 20 6. BACKS AND RECEIVERS 33 7. QUARTERBACK BASICS 35 8. THE PLAYS 47 THE RUNS 48 THE PASSES 86 THE SPECIALS 124 9. INSTALLATION 132 10. SITUATIONAL WILD BUNCH 139 11. A PHILOSOPHY OF ATTACK 146 Dedication: THIS BOOK IS FOR PATSY, WHOSE PATIENCE DURING THE YEARS I WAS DEVELOPING THE WILD BUNCH WAS MATCHED ONLY BY HER GOOD HUMOR. Copyright © 2006 Edmond E. Seay III - 2 - INTRODUCTION The Wild Bunch celebrates its sixth birthday in 2006. This revised playbook reflects the lessons learned during that period by Wild Bunch coaches on three continents operating at every level from coaching 8-year-olds to semi-professionals. The biggest change so far in the offense has been the addition in 2004 of the Rocket Sweep series (pp. 62-72). A public high school in Chicago and a semi-pro team in New Jersey both reached their championship game using the new Rocket-fueled Wild Bunch. A youth team in Utah won its state championship running the offense practically verbatim from the playbook. A number of coaches have requested video resources on the Wild Bunch, and I am happy to say a DVD project is taking shape which will feature not only game footage but extensive whiteboard analysis of the offense, as well as information on its installation.
    [Show full text]
  • Nflfastr: Functions to Efficiently Access NFL Play by Play Data
    Package ‘nflfastR’ August 3, 2021 Type Package Title Functions to Efficiently Access NFL Play by Play Data Version 4.2.0 Description A set of functions to access National Football League play-by-play data from <https://www.nfl.com/>. License MIT + file LICENSE URL https://www.nflfastr.com/, https://github.com/nflverse/nflfastR BugReports https://github.com/nflverse/nflfastR/issues Depends R (>= 3.5.0) Imports cli (>= 3.0.0), curl, dplyr, fastrmodels (>= 1.0.1), furrr, future, glue, janitor, lubridate, lifecycle (>= 0.2.0), magrittr, mgcv, progressr (>= 0.6.0), rlang, stringr (>= 1.3.0), tibble (>= 3.0), tidyr (>= 1.0.0), tidyselect (>= 1.1.0), xgboost (>= 1.1) Suggests crayon (>= 1.3.4), DBI, DT, gsisdecoder, httr, jsonlite, purrr (>= 0.3.0), qs (>= 0.25.1), rmarkdown, RSQLite, testthat Encoding UTF-8 LazyData true RoxygenNote 7.1.1 NeedsCompilation no Author Sebastian Carl [aut], Ben Baldwin [cre, aut], Lee Sharpe [ctb], Maksim Horowitz [ctb], Ron Yurko [ctb], Samuel Ventura [ctb], Tan Ho [ctb] Maintainer Ben Baldwin <[email protected]> Repository CRAN Date/Publication 2021-08-03 15:10:02 UTC 1 2 nflfastR-package R topics documented: nflfastR-package . .2 add_qb_epa . .4 add_xpass . .5 add_xyac . .5 build_nflfastR_pbp . .6 calculate_expected_points . .7 calculate_player_stats . .9 calculate_win_probability . 11 clean_pbp . 13 decode_player_ids . 14 fast_scraper . 15 fast_scraper_roster . 27 fast_scraper_schedules . 29 field_descriptions . 30 load_pbp . 31 load_player_stats . 31 stat_ids . 32 teams_colors_logos . 33 update_db . 34 Index 36 nflfastR-package nflfastR: Functions to Efficiently Access NFL Play by Play Data Description A set of functions to access National Football League play-by-play data from <https://www.nfl.com/>.
    [Show full text]
  • Washington Redskins at Dallas Cowboys Week 13 / November 30
    2017 SEASON WEEKLY GUIDE WASHINGTON REDSKINS AT DALLAS COWBOYS WEEK 13 / NOVEMBER 30 GAME RELEASE 21300 Redskin Park Drive | Ashburn, VA 20147 | 703.726.7000 @Redskins | www.Redskins.com | media.Redskins.com REGULAR SEASON - WEEK 13 WASHINGTON REDSKINS (5-6) AT DALLAS COWBOYS (5-6) Thursday, Nov. 30 | 8:25 p.m. ET AT&T Stadium (80,000) | Arlington, Texas REDSKINS READY FOR SECOND GAME CENTER STRAIGHT THURSDAY NIGHT GAME SERIES HISTORY: Redskins trail all-time series, 44-69-2 Redskins trail regular season series, 42-69-2 The Washington Redskins will once again play in front of a national Last meeting: Oct. 29, 2017 (33-19, DAL) Thursday night audience when the team faces the Dallas Cowboys in Week 13. Kickoff at AT&T Stadium is scheduled for 8:25 p.m. ET. TELEVISION: NBC/NFL Network/Amazon The game will be broadcast on NBC, NFL Network, and for the first Mike Tirico (play-by-play) time in Redskins history, on Amazon. In addition to the NBC broadcast, Cris Collinsworth (color) Amazon viewers will have access to British English commentary (Derek Heather Cox (sidelines) Rae and Tommy Smyth), Spanish commentary (Armando Quintero and << See left for international crews Oscar Benítez) and Portuguese commentary (Flavio Pereira and Nilton Batata). RADIO: Redskins Radio Network Last week, the Redskins hosted their first Thanksgiving home game Larry Michael (play-by-play) in team history, earning a 20-10 victory against the New York Giants. Chris Cooley (analysis) With back-to-back Thursday contests in Weeks 12-13, the Redskins are Rick “Doc” Walker (sidelines) in the midst of a season in which they play multiple Thursday contests Westwood One Sports for the first time in team history.
    [Show full text]
  • Axiomatic Design of a Football Play-Calling Strategy
    Axiomatic Design of a Football Play-Calling Strategy A Major Qualifying Project Report Submitted to the Faculty of the WORCESTER POLYTECHNIC INSTITUTE in partial fulfillment of the requirements for the Degree of Bachelor of Science in Mechanical Engineering by _____________________________________________________________ Liam Koenen _____________________________________________________________ Camden Lariviere April 28th, 2016 Approved By: Prof. Christopher A. Brown, Advisor _____________________________________________________________ 1 Abstract The purpose of this MQP was to design an effective play-calling strategy for a football game. An Axiomatic Design approach was used to establish a list of functional requirements and corresponding design parameters and functional metrics. The two axioms to maintain independence and minimize information content were used to generate a final design in the form of a football play card. The primary focus was to develop a successful play-calling strategy that could be consistently repeatable by any user, while also being adaptable over time. Testing of the design solution was conducted using a statistical-based computer simulator. 2 Acknowledgements We would like to extend our sincere gratitude to the following people, as they were influential in the successful completion of our project. We would like to thank Professor Christopher A. Brown for his advice and guidance throughout the yearlong project and Richard Henley for sharing his intellect and thought process about Axiomatic Design and the role
    [Show full text]
  • Wide Receiver Drill Catalog University of Missouri-Rolla
    Wide Receiver Drill Catalog University of Missouri-Rolla As you review the following receiver drills, it is important to remember these key points: 1. Proper Wide Receiver Stance: This is especially important for the outside receivers or any receiver which may be on the LOS. You want to have your inside foot forward, slight bend in the knees, shoulders low, and your hands held high. The inside foot should be forward so that you have a closed stance and your chest is not exposed to any press defender. The vast majority of times you get a pressed defender they will play inside leverage and if you have your inside foot back, then your chest is exposed to an inside leverage press defender. The knees should be bent and the shoulders low so that you again limit the amount of space which is available to be hit right on the snap as well as helping to make the WR quicker off of the ball. The hands should be high so that you can attack a press defender right away without first accepting a blow from him. If you hands are not held high, then on the snap the first thing you must do is bring your hands up so you can either defender yourself against the press defensive back or bring them up to start running. 2. Proper Way To Catch A Football: One of the biggest problems receivers have is trying to make a backhanded catch. A backhanded catch is when the ball is low and away and the receiver opens his palms to the ground.
    [Show full text]
  • NFL Season Launch Kit 2015 PLAY FOOTBALL VIGNETTES
    NFL Season Launch Kit 2015 PLAY FOOTBALL VIGNETTES C.J. MOSLEY FILLING THE SHOES OF RAY LEWIS IS NO EASY TASK BUT C.J. MOSLEY STEPPED RIGHT IN TO LEAD THE RAVENS IN TACKLES AND WAS NAMED TO THE PRO BOWL IN HIS FIRST SEASON. RADIO - MOSLEY'S 2 INTERCEPTIONS, 7 PASSES DEFENSED, A FORCED FUMBLE AND A FUMBLE RECOVERY. HE'S GOT A COMPLETE SET OF STATS. COMING DOWN WITH THE INTERCEPTION, WHO ELSE BY C.J. MOSLEY! WITH A YEAR UNDER HIS BELT, MOSLEY HOPES TO HAVE A SENSATIONAL SOPHOMORE SEASON IN 2015. JAMAAL CHARLES THERE WASN'T A BETTER BIG PLAY THREAT IN THE NFL THAN JAMAAL CHARLES IN 2014. HE LED THE AFC WITH 14 TOUCHDOWNS. RADIO - CHARLES DIVES FOR THE TOUCHDOWN! CHARLES IS A DANGEROUS BACK WHO CAN HURT OPPOSING TEAMS LINING UP AS A RECEIVER OR GETTING THE BALL OUT OF THE BACKFIELD. DON'T LET HIM GET IN THE OPEN FIELD, OTHERWISE YOU'LL SEE HIS WORLD CLASS SPEED THAT LEAVES OPPONENTS IN THE DUST. RADIO - JAMAAL CHARLES IS JUST A LIGHTNING BOLT WHEN HE GETS OUTSIDE. DEREK CARR DEREK CARR WAS THE 4TH QUARTERBACK DRAFTED IN 2014 BUT LED ALL ROOKIE PASSERS IN COMPLETIONS, PASSING YARDS AND TOUCHDOWNS. RADIO - CARR LETS IT FLY DEEP DOWNFIELD. CAUGHT! LOOK OUT! WHAT A PLAY THERE! DEREK CARR OVER THE TOP! CARR'S ABILITY TO READ DEFENSES AND USE HIS STRONG RIGHT ARM MAKES HIM ONE OF THE LEAGUE'S BEST YOUNG PROSPECTS. LOOK FOR CARR TO IMPROVE ON HIS IMPRESSIVE ROOKIE SEASON AND PUT UP MORE BIG NUMBERS IN 2015.
    [Show full text]
  • University of Colorado Buffaloes / Sports Information Service Game 3 2019 Colorado Buffalo Football Weekly Release, Notes &
    0 FARI UNIVERSITY OF COLORADO BUFFALOES / SPORTS INFORMATION SERVICE www.CUBuffs.com 2150 Stadium Drive (574 Champions Center), 357 UCB, Boulder, CO 80309-0357 © 2019 CU Athletics Telephone 303/492-5626 (E-mail/FB contacts: [email protected]; [email protected]) David Plati (Associate AD/SID), Curtis Snyder (Assistant AD), Troy Andre (Associate SID/+CUBuffs.com Managing Editor), Linda Sprouse (Associate SID), COLORADO Seth Pringle (Assistant SID), Shaun Wicen (Assistant SID), Neill Woelk (Contributing Editor/CUBuffs.com), Rob Livingston (Graduate Assistant) GAME 3 2019 COLORADO BUFFALO FOOTBALL WEEKLY RELEASE, NOTES & STATISTICS SCHOOLS 75 MILES APART TO MEET FOR THE FIRST TIME SINCE 1974 SATURDAY, SEPTEMBER 14, 2019 11:01 a.m. MDT Folsom Field (50,183) Boulder, Colo. RELEASE NUMBER 3 (September 9, 2019) PAC-12 NETWORK (National) | KOA-RADIO | CUBUFFS.COM (Live Stats) BUFFALO BITS … The Colorado Buffaloes (2-0, 0-0 Pac-12) remain at home (and in the year history; Mel Tucker is the 10th CU head coach to win his two games at state) for their third game of the season, hosting the Air Force Falcons (1- the reins of the Buffaloes ... The Buffaloes are coming off a wild 34-31 0, 0-0 MW) in an 11:01 a.m. MDT kickoff at Folsom Field in Boulder ... It will overtime win over No. 25 Nebraska in Boulder, rallying from down 17-0 late be the first meeting between the schools just 75 miles apart for the first time in the third quarter in overpowering the Cornhuskers (outgaining them 335- since 1974 (yes, just two months after President Nixon resigned) ..
    [Show full text]
  • A Five-Time Amazon Bestseller - Now Available at Early Bird Discount
    CLICK TO BUY WARREN'S 400+ PAGE, 2021 FOOTBALL PREVIEW "Simply the best analytical 2021 football preview you can buy" A FIVE-TIME AMAZON BESTSELLER - NOW AVAILABLE AT EARLY BIRD DISCOUNT Written by Warren Sharp Edited by Dan Pizzuta Featuring contributions from Rich Hribar, Dan Pizzuta, TA Cleveland and Ryan McCrystal TEAM CHAPTER LAYOUT AND DEFINITIONS PAGE 1: Schedule strength based on opponent Vegas win totals // asterisk next to draft indicates comp pick // Lineup & Cap Hits lists projected starting roster shaded based on cap to analyze where cap $ is being spent // Key players lost if null shows unsigned players to date PAGE 2: Advanced stats including EPA (Expected Points Added), which is a metric that looks at the Expected Points (EP) of the down, distance, and field position situation at the start of a play and contrasting it with the situation at the end of the play. Thus, the difference, or “added” points are considered EPA, and could be positive or negative), and Success Rate are calculated on a per-play basis. Success rate is defined as frequency a play gains required yardage to stay ahead of sticks, and is a rate stat // EDSR is a custom metric Warren created to measure early down success and measures efficiency on early downs and ability to bypass third down offensively or force opponents into third downs defensively // INT = interceptions, FUM = fumbles // Weekly EDSR chart bottom left looks at whether team won the EDSR battle (comparing both sides of the ball vs opponent) each week, green bar = EDSR win, red bar = EDSR loss PAGE 3: logo in Strength of Schedule graphic is the 2020 forecast, the shaded target is 2019 actual based on 2019 season through week 17 // Schedule Variance analyzes ease in schedule as compared to the rest of teams.
    [Show full text]
  • Strat-O-Matic Football Rules
    Strat-O-Matic Football Rules 2015 Card Season Revised 01-04-2017 01/04/2016 Page 1 01/04/2016 Page 2 2015 Season Cards This set of rules encompasses all rules previously found in the rule booklet and on the roster sheets, as well as the newly introduced rules and optional rules adopted by the League Rules Committee. In addition some rules found within the official Strat-O-Matic Computer rules have been deleted or modified to better suit play within this league. INTRODUCTION First and foremost all rules of football apply. If a conflict occurs concerning a particular aspect of the game use common sense to resolve the dispute applying the rules of the NFL. If the exact rule is not known at that time try to find the answer in a timely manner and if a solution is not reached resolve the dispute by a die roll and continue play. It is after all just a game. TABLE OF CONTENTS 2015 Season Cards ..................................................................................................................................................................................... 3 INTRODUCTION ..................................................................................................................................................................................... 3 TABLE OF CONTENTS ........................................................................................................................................................................... 3 IMPORTANT CHANGES TO THE RULES FROM THE PAST SEASONS.........................................................................................
    [Show full text]
  • Nflwar: a Reproducible Method for Offensive Player
    nflWAR: A Reproducible Method for Offensive Player Evaluation in Football Ron Yurko Sam Ventura Max Horowitz Department of Statistics Carnegie Mellon University NESSIS, 2017 Ron Yurko (@Stat Ron) nflWAR NESSIS, 2017 1 / 36 nflscrapR: R package created by Maksim Horowitz to enable easy data access and promote reproducible NFL research Collects play-by-play data from NFL.com and formats into R data frames Data is available for all games starting in 2009 Available on Github, install with: devtools::install github(repo=maksimhorowitz/nflscrapR) Reproducible Research with nflscrapR Recent work in football analytics is not easily reproducible: Reliance on proprietary and costly data sources Data quality relies on potentially biased human judgement Ron Yurko (@Stat Ron) nflWAR NESSIS, 2017 2 / 36 Reproducible Research with nflscrapR Recent work in football analytics is not easily reproducible: Reliance on proprietary and costly data sources Data quality relies on potentially biased human judgement nflscrapR: R package created by Maksim Horowitz to enable easy data access and promote reproducible NFL research Collects play-by-play data from NFL.com and formats into R data frames Data is available for all games starting in 2009 Available on Github, install with: devtools::install github(repo=maksimhorowitz/nflscrapR) Ron Yurko (@Stat Ron) nflWAR NESSIS, 2017 2 / 36 And the comments... Pittsburgh Fans React Pittsburgh Post-Gazette article by Liz Bloom covered recent nflscrapR research and status of statistics in football Ron Yurko (@Stat Ron) nflWAR NESSIS, 2017 3 / 36 Pittsburgh Fans React Pittsburgh Post-Gazette article by Liz Bloom covered recent nflscrapR research and status of statistics in football And the comments..
    [Show full text]
  • London Junior Mustangs Football Club Football
    LONDON JUNIOR MUSTANGS FOOTBALL CLUB FOOTBALL TERMINOLOGY GUIDE Text courtesy of Kevin Holmes, HB Sport Management Services 1 Table of Contents STATEMENT .................................................................................................................................................................. 3 OFFENSE ....................................................................................................................................................................... 3 POSITIONS ................................................................................................................................................................ 3 Offensive Line ...................................................................................................................................................... 3 Backfield ............................................................................................................................................................... 3 Receivers .............................................................................................................................................................. 4 NUMBERING/LETTER SYSTEM .............................................................................................................................. 4 FORMATIONS ....................................................................................................................................................... 4 HOLES ..................................................................................................................................................................
    [Show full text]
  • Strat-O-Matic Football Rules
    Strat-O-Matic Football Rules 2014 Card Season Revised 12-17-2015 01/10/2015 Page 1 01/10/2015 Page 2 2014 Season Cards This set of rules encompasses all rules previously found in the rule booklet and on the roster sheets, as well as the newly introduced rules and optional rules adopted by the League Rules Committee. In addition some rules found within the official Strat-O-Matic Computer rules have been deleted or modified to better suit play within this league. INTRODUCTION First and foremost all rules of football apply. If a conflict occurs concerning a particular aspect of the game use common sense to resolve the dispute applying the rules of the NFL. If the exact rule is not known at that time try to find the answer in a timely manner and if a solution is not reached resolve the dispute by a die roll and continue play. It is after all just a game. TABLE OF CONTENTS 2013 Season Cards ..................................................................................................................................................................................... 3 INTRODUCTION ..................................................................................................................................................................................... 3 TABLE OF CONTENTS ........................................................................................................................................................................... 3 IMPORTANT CHANGES TO THE RULES FROM THE PAST SEASONS.........................................................................................
    [Show full text]