Introduction
This project and the data explores the relationship between Social Media, Salary, Influence, Performance and Team Valuation in the NBA. This is covered in Chapter 6 of Pragmatic AI
Pragmatic AI Labs
This project was produced by Pragmatic AI Labs. You can continue learning about these topics by:
- Buying a copy of Pragmatic AI: An Introduction to Cloud-Based Machine Learning
- Viewing more content at noahgift.com
- Viewing more content at Pragmatic AI Labs
- Hear more about the some of the topics covered in TWIML podcast
Strata 2018 Talk
-
What is the relationship between social influence and the NBA
-
Slides on What is the relationship between social influence and the NBA
IBM Developerworks Articles on Project
-
Explore valuation and attendance using data science and machine learning: https://www.ibm.com/developerworks/library/ba-social-influence-python-pandas-machine-learning-r-1/
-
Exploring the individual NBA players: https://www.ibm.com/developerworks/analytics/library/ba-social-influence-python-pandas-machine-learning-r-2/
Kaggle Version of Project
You can also see Kaggle Notebooks here:
Data Legend
Exploring Team Valuation Notebook
This notebook has the following data legend:
Exploring Team Valuation Dataset created
- TEAM: Name of the NBA Team
- GMS: Games Played
- PCT_ATTENDANCE: Average % Attendance of capacity (note some teams were over capacity as an averag)
- WINNING_SEASON: If the team won over 50% of their games, it was 1, otherwise 0.
- TOTAL_ATTENDANCE_MILLIONS: Total season attendance in the millions.
- VALUE_MILLIONS: Valuation of the team in millions
- ELO: https://en.wikipedia.org/wiki/Elo_rating_system
- CONF: Eastern or Western Conference
- COUNTY: The county where the team is located
- MEDIAN_HOME_PRICE_COUNTY_MILLIONS: Median Home Price
- COUNTY_POPULATION_MILLIONS: The Population of the county in Millions
- cluster: A cluster created by KMeans clustering (shown in notebook)
Exploring Team Valuation Notebook
Exploring Team Valuation Dataset created
- PLAYER: NBA Player Name
- TEAM: NBA Team
- SALARY_MILLIONS: Salary paid to player in Millions
- ENDORSEMENT_MILLIONS: Endorsements paid to player in Millions
- PCT_ATTENDANCE_STADIUM: Average % attendance in stadium
- ATTENDANCE_TOTAL_BY_10K
- FRANCHISE_VALUE_100_MILLION
- ELO_100X: https://en.wikipedia.org/wiki/Elo_rating_system/100
- CONF: Eastern or Western Conference (Even split between all teams between both conferences)
- POSITION: Position of the player
- AGE
- MP: Minutes/Games Average
- GP: Games played
- MPG: Minutes/Games Average
- WINS_RPM: Wins attributed to individual player performance. One of the best metrics of overall impact on team.
- PLAYER_TEAM_WINS: Wins for the team the playes is on.
- WIKIPEDIA_PAGEVIEWS_10K: Pageviews of player divided by 10 thousand TWITTER_FAVORITE_COUNT_1K: Twitter favorites of player profile divided by 1 thousand.
Social Power, Influence and Performance in the NBA
Social Power in the NBA (Comparing on the court performance with Social Influence)
Data Exploration
Player Impact Estimation
Social Power, Performance and Salary
Valuation vs Attendance
ELO vs Attendance
ELO Correlation Heatmap
REAL PLUS MINUS Wins, POINTS and SALARY
3D Plot
ALL Data Correlation Heatmap
Explore Juypter Notebooks
Juypter Noteboooks Social Power
Social Money
Social Power and Performance
Explore Raw Data Here
-
NBA 2016-2017 REAL PLUS MINUS Wins, POINTS, SALARY, Wikipedia, Twitter
- This data was collected from multiple sources: ESPN, Basketball-Reference, Twitter, Wikipedia, and Forbes
Additional Related Topics from Noah Gift
His most recent books are:
- Pragmatic A.I.: An introduction to Cloud-Based Machine Learning (Pearson, 2018)
- Python for DevOps (O'Reilly, 2020).
His most recent video courses are:
- Essential Machine Learning and A.I. with Python and Jupyter Notebook LiveLessons (Pearson, 2018)
- AWS Certified Machine Learning-Specialty (ML-S) (Pearson, 2019)
- Python for Data Science Complete Video Course Video Training (Pearson, 2019)
- AWS Certified Big Data - Specialty Complete Video Course and Practice Test Video Training (Pearson, 2019)
- Building A.I. Applications on Google Cloud Platform (Pearson, 2019)
- Pragmatic AI and Machine Learning Core Principles (Pearson, 2019)
- Data Engineering with Python and AWS Lambda (Pearson, 2019)
His most recent online courses are: