For basketball project team winter 2023
Contents:
- main.py: Runs the model on a given .csv file
- project_marchmadness_scraping.py: Scrapes data from the given year on basketball reference
- CSV_Merger.ipynb: Merges two .csv files if their 'Team' column is identical
- Json_format.ipynb: Converts a .csv into a .json file
- merger.py: Merges two .csv files using 'Team' column with an outer join
- Module1.bas: Implements a function that finds and changes many names in an Excel file, creating a column with the changed values
- A variety of other data files and versions
Download main.py and call it on an ranked .csv file formatted with combined data in the same directory to train the model. Then input an unranked combined .csv of teams in a March Madness bracket to rank those teams on how well it believes they will do in the tournament.
.csv Input Indexes
- Num
- Rk
- Team
- Conf
- W/L
- AdjEM
- AdjO
- AdjD
- AdjT
- Luck
- AdjEM.1
- OppO
- OppD
- AdjEM.2
- FG
- FGA
- FGpct
- 2PT
- 2PTA
- 2PTpct
- 3PT
- 3PTA
- 3PTpct
- FT
- FTA
- FTpct
- ORB
- DRB
- TRB
- AST
- STL
- BLK
- TOV
- PF
- PTS
- FG_RANK
- FGA_RANK
- FGpct_RANK
- 2PT_RANK
- 2PTA_RANK
- 2PTpct_RANK
- 3PT_RANK
- 3PTA_RANK
- 3PTpct_RANK
- FT_RANK
- FTA_RANK
- FTpct_RANK
- ORB_RANK
- DRB_RANK
- TRB_RANK
- AST_RANK
- STL_RANK
- BLK_RANK
- TOV_RANK
- PF_RANK
- PTS_RANK
- OPP_FG
- OPP_FGA
- OPP_FGpct
- OPP_2PT
- OPP_2PTA
- OPP_2PTpct
- OPP_3PT
- OPP_3PTA
- OPP_3PTpct
- OPP_FT
- OPP_FTA
- OPP_FTpct
- OPP_ORB
- OPP_DRB
- OPP_TRB
- OPP_AST
- OPP_STL
- OPP_BLK
- OPP_TOV
- OPP_PF
- OPP_PTS
- OPP_FG_RANK
- OPP_FGA_RANK
- OPP_FGpct_RANK
- OPP_2PT_RANK
- OPP_2PTA_RANK
- OPP_2PTpct_RANK
- OPP_3PT_RANK
- OPP_3PTA_RANK
- OPP_3PTpct_RANK
- OPP_FT_RANK
- OPP_FTA_RANK
- OPP_FTpct_RANK
- OPP_ORB_RANK
- OPP_DRB_RANK
- OPP_TRB_RANK
- OPP_AST_RANK
- OPP_STL_RANK
- OPP_BLK_RANK
- OPP_TOV_RANK
- OPP_PF_RANK
- OPP_PTS_RANK
- Rank (only in ranked datasets)
- Round (only in ranked datasets)
And easily scalable to more data.