- nfl_data.csv: The original dataset from which we gathered all the data. Came from Kaggle, can be found here.
- DataViz.ipynb: A Jupyter Notebook containing data visualizations of run/pass trends in the NFL since 2009, made with matplotlib. As suspected, even within this short period of time the NFL as a whole shifted ~3% toward passing.
- nfl_classifiers.py: Python module which has functions to create scikit-learn classifiers and regressors on the NFL data. The classifiers
were used to try to classify a play as either run or pass based on quarter, down, distance, time left in the game, and the point differential
relative to the offensive team (i.e. if the offensive team is winning by 7, it would be 7.0. If they are losing by 7, it would be -7.0.)
The accuracy scores typically range from 65% to 68%, with 68% being the absolute upper bound we got. The regressors were used to
train models to determine the win probability of a team given the time left in the game and the point differential relative to that team.
These worked much better, typically getting around 88% to 95% accuracy. The functions return a tuple of the trained model and its average accuracy
based on test data. An example use of the function could be this:
clf, score = build_sklearn_randforest_classifier('new_run_pass.csv'). This will give you an sklearn RandomForestClassifier trained on data from new_run_pass.csv. - new_run_pass.csv: This is the data used to train the classifiers to determine run or pass based on game situation. This csv was created from the original nfl_data.csv using Pandas DataFrame queries.
- play_year.csv: This is the file the visualizations were created from. This csv was created from the original nfl_data.csv using Pandas DataFrame queries.
- winprob.csv: This is the file the regressors were trained on to determine win probability of a team based on game situation. This csv was created from the original nfl_data.csv using Pandas DataFrame queries.
cs2803-final-project's Introduction
cs2803-final-project's People
Contributors
Watchers
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.