Giter Site home page Giter Site logo

roclark / clarktech-ncaab-predictor Goto Github PK

View Code? Open in Web Editor NEW
33.0 9.0 8.0 7.03 MB

A machine learning project to predict NCAA Men's Basketball outcomes

Python 99.09% Dockerfile 0.91%
machine-learning basketball basketball-stats python prediction randomforest

clarktech-ncaab-predictor's People

Contributors

dependabot[bot] avatar roclark avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

clarktech-ncaab-predictor's Issues

Updates?

Hi Clark,

I see that you haven't touched this project in quite some time. I found it interesting and been studying the code. I am curious if you ever got any meaningful results out of it?

Also curious why you kept track of mascots in predictions ?

Thanks,
Sam

Move requests into separate common function

All of the requests should be moved into a separate common function to reduce redundant code and enable more robust error handling in a streamlined manner. Currently, there are still a few requests that don't have error handling and cause issues with various builds.

Handle requests in parallel

Currently, it takes 45 minutes or longer to pull all of the stats. If the requests are run in parallel, it could significantly reduce the time to pull the stats, enabling faster testing.

Additional features to analyze

The following features might be helpful in analyzing the outcome of a game:

  • Where the team falls in the rankings, if at all
  • Which conference the team is in
  • Whether it is a true home game (as opposed to a neutral court game where one team is selected as the home team)
  • The home, away, neutral court record of the team prior to the game
  • What the team's recent performance is (past 3, 5, 10 games)
  • Whether the game is in-conference, out-of-conference, or a tournament
  • If there are any teams that have stand-out players that score most of their points
  • Include data from previous seasons
  • What the team's win percentage is
  • The team's strength of schedule

Wrong URL to pull data

`iMac:~ roneskinder$ docker run --rm -it roclark/clarktech-ncaab-predictor daily-simulation

WARNING: The requested image's platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested

/usr/local/lib/python3.7/site-packages/sklearn/externals/six.py:31: DeprecationWarning: The module is deprecated in version 0.21 and will be removed in version 0.23 since we've dropped support for Python 2.7. Please rely on the official version of six (https://pypi.org/project/six/).
  "(https://pypi.org/project/six/).", DeprecationWarning)
Traceback (most recent call last):
   File "./run-simulator.py", line 789, in <module>
    main()
  File "./run-simulator.py", line 782, in main
teams = Teams()
  File "/usr/local/lib/python3.7/site-packages/sportsreference/ncaab/teams.py", line 997, in __init__
self._conferences_dict = Conferences(year).team_conference
  File "/usr/local/lib/python3.7/site-packages/sportsreference/ncaab/conferences.py", line 142, in __init__
self._find_conferences(year)
  File "/usr/local/lib/python3.7/site-packages/sportsreference/ncaab/conferences.py", line 218, in _find_conferences
raise ValueError(output)

ValueError: Can't pull requested conference page. Ensure the following URL exists: https://www.sports-reference.com/cbb/seasons/2023.html`

Remove warnings

There are a couple of warnings currently being thrown, such as:

  • A deprecation warning for cross_validation

/home/travis/virtualenv/python2.7.13/lib/python2.7/site-packages/sklearn/cross_validation.py:41: DeprecationWarning: This module was deprecated in version 0.18 in favor of the model_selection module into which all the refactored classes and functions are moved. Also note that the interface of the new CV iterators are different from that of this module. This module will be removed in 0.20.
  "This module will be removed in 0.20.", DeprecationWarning)
  • A warning about overwriting copies in a DataFrame
analyze-games.py:70: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy
  stats[field] = float(stats[field]) / num_games
/home/travis/build/clark173/basketball-predictor/predictor.py:49: FutureWarning: '.reindex_axis' is deprecated and will be removed in a future version. Use '.reindex' instead.
  self._test = self._test.reindex_axis(self._filtered_features, axis=1)
  • A deprecation warning about the .reindex_axis method
/home/prometheus/basketball-predictor/predictor.py:45: FutureWarning: '.reindex_axis' is deprecated and will be removed in a future version. Use '.reindex' instead.
  self._test = self._test.reindex_axis(self._filtered_features, axis=1)

These should be removed for a cleaner build and run.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.