A Python implementation of NFL Win Probability (WP)
Project description
Estimate Win Probability (WP) for plays in NFL games:
>>> import pandas as pd
>>> from nflwin.model import WPModel
>>> standard_model = WPModel.load_model()
>>> plays = pd.DataFrame({
... "quarter": ["Q1", "Q2", "Q4"],
... "seconds_elapsed": [0, 0, 600],
... "offense_team": ["NYJ", "NYJ", "NE"],
... "yardline": [-20, 20, 35],
... "down": [1, 3, 3],
... "yards_to_go": [10, 2, 10],
... "home_team": ["NYJ", "NYJ", "NYJ"],
... "away_team": ["NE", "NE", "NE"],
... "curr_home_score": [0, 0, 21],
... "curr_away_score": [0, 0, 10]
... })
>>> standard_model.predict_wp(plays)
array([ 0.58300397, 0.64321796, 0.18195466])
For full documentation, including information about methods and accuracy, click here.
License
MIT. See license file.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nflwin-1.0.1.tar.gz
(17.0 kB
view hashes)