spencer-weston/nbapredict

NBA game prediction model

nbapredict's Issues

Create a script to unify the entire project

One script needs to be capable of performing all functionality in the project. Scrape stats, schedule, and lines. Run predictions on all available data. Store analysis.

• Run scraper through run.run
• Create prediction table setup that works without specifying a game
• Predict_all function which predicts all games and stores the bet result for all games

Make the project run daily and perform all update functions

Project should run automatically each day

• Add handling for missed jobs

Scraping Historical Seasons

Seasons from 2001 forward are correctly written to the database. However, seasons from before then contain errors. The error appears to arise from errant trailing letters after team names. My exploration did not move forward much past that.

Create Handling in run.daily for when computer sleeps

Can't seem to make it work

Hello and thanks for open sourcing your project,

I can seem to make it work, any thoughts?

C:\Users\sergi\AppData\Local\Programs\Python\Python38\lib\site-packages\sklearn\utils\deprecation.py:144: FutureWarning: The sklearn.metrics.classification module is deprecated in version 0.22 and will be removed in version 0.24. The corresponding classes / functions should instead be imported from sklearn.metrics. Anything that cannot be imported from sklearn.metrics is now part of the private API. warnings.warn(message, FutureWarning) Season is up to date; Returning without performing an update. C:\Users\sergi\AppData\Local\Programs\Python\Python38\lib\site-packages\numpy\core\fromnumeric.py:2542: FutureWarning: Method .ptp is deprecated and will be removed in a future version. Use numpy.ptp instead. return ptp(axis=axis, out=out, **kwargs) Traceback (most recent call last): File "C:\Users\sergi\AppData\Local\Programs\Python\Python38\lib\runpy.py", line 193, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\sergi\AppData\Local\Programs\Python\Python38\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "C:\Users\sergi\Desktop\NBApredict-master\run\all.py", line 34, in <module> run_all() File "C:\Users\sergi\Desktop\NBApredict-master\run\all.py", line 26, in run_all predict.predict_all(db, session, year) File "C:\Users\sergi\Desktop\NBApredict-master\predict\predict.py", line 509, in predict_all odds_tbl = database.get_table_mappings("odds_{}".format(league_year)) File "C:\Users\sergi\Desktop\NBApredict-master\database\database.py", line 70, in get_table_mappings self.metadata.reflect(self.engine, only=table_names) File "C:\Users\sergi\AppData\Local\Programs\Python\Python38\lib\site-packages\sqlalchemy\sql\schema.py", line 4259, in reflect raise exc.InvalidRequestError( sqlalchemy.exc.InvalidRequestError: Could not reflect: requested table(s) not available in Engine(sqlite:///outputs//nba_db.db): (odds_2019)

Daily Scheduling Issue

If daily is run during the playoffs, the scheduled run times will not work. This arises because game times in schedule are not always determined ahead of time and default to midnight. Will need an update mechanism to recognize when game times in schedule change and update scheduler accordingly.

Incorrect Table Drop

If a table exists in the database, an error arises when create_table is run even if overwrite = True. If the file is run a second time, it performs without an error. I suspect it indicates there is an issue in the order of operations, or the table is dropped in an incorrect manner.

Running for new season

There are a few issues right now when running for the 2019-2020 NBA season. I am trying to comb through and fix as many as possible.

Tableau/Jupyter to display regression analysis

• Decide on Tableau or Jupyter or Other

Create a useful readme

Season Scraper Broken

Not sure exactly what happened, or where, but the season scraper throws enums to the sql column builder function where it needs to be the enum.value (i.e. a string).