Update with up to date data

.gitattributes

@@ -1,36 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
-*.csv filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -1,31 +0,0 @@
-
-# Use the official lightweight Python image.
-# https://hub.docker.com/_/python
-FROM python:3.11-slim
-
-# Allow statements and log messages to immediately appear in the logs
-ENV PYTHONUNBUFFERED True
-
-# Copy local code to the container image.
-ENV APP_HOME /app
-WORKDIR $APP_HOME
-COPY . ./
-
-# Install production dependencies.
-RUN pip install -r requirements.txt
-
-RUN useradd -m -u 1000 user
-USER user
-ENV HOME=/home/user \
-	PATH=/home/user/.local/bin:$PATH
-
-WORKDIR $APP_HOME
-
-COPY --chown=user . $HOME/app
-
-# Run the web service on container startup. Here we use the gunicorn
-# webserver, with one worker process and 8 threads.
-# For environments with multiple CPU cores, increase the number of workers
-# to be equal to the cores available.
-# Timeout is set to 0 to disable the timeouts of the workers to allow Cloud Run to handle instance scaling.
-CMD exec gunicorn --bind 0.0.0.0:7860 --workers 4 --threads 8 --timeout 0 main:app

README.md

@@ -1,10 +0,0 @@
----
-title: MARCI (NFL Betting)
-emoji: 🏈
-colorFrom: red
-colorTo: blue
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

Source/Build/build.py

@@ -1,197 +0,0 @@
-from nfl_data_py import nfl_data_py as nfl
-from tqdm import tqdm
-import numpy as np
-import pandas as pd
-pd.set_option('chained_assignment',None)
-pd.set_option('display.max_columns',None)
-import os
-import datetime as dt
-
-current_directory = os.path.dirname(os.path.abspath(__file__))
-parent_directory = os.path.dirname(current_directory)
-data_directory = os.path.join(parent_directory, 'Data')
-
-year = dt.datetime.now().year
-month = dt.datetime.now().month
-current_season = year if month in [8,9,10,11,12] else year-1
-
-def get_pbp_data(get_seasons=[]):
-    """
-    Pull data from nflFastR's Github repo. 
-
-    """
-    pbp = nfl.import_pbp_data(get_seasons)
-    #pbp = pd.read_csv(r"C:\Users\brayd\Downloads\play_by_play_2023.csv")
-    pbp['TOP_seconds'] = pbp['drive_time_of_possession'].apply(lambda x: int(x.split(':')[0]) * 60 + int(x.split(':')[1]) if pd.notnull(x) else 0)
-
-    return pbp
-
-
-def build_gbg_data(get_seasons=[]):
-    """
-    Build a game-by-game dataset to use for prediction models.
-
-    """
-    print('Loading play-by-play data.')
-    pbp = get_pbp_data(get_seasons)
-    game_date_dict = dict(pbp[['game_id','game_date']].values)
-    teams = list(set(list(pbp['home_team'].unique()) + list(pbp['away_team'].unique())))
-    seasons = pbp['season'].unique()
-    
-    print('Building game-by-game data.')
-    data = pd.DataFrame()
-    for season in seasons:
-        print(season)
-        for team_name in tqdm(teams):
-            # create features
-            team = pbp.loc[((pbp['home_team']==team_name) | (pbp['away_team']==team_name)) & (pbp['season']==season)] 
-            team['GP'] = team['week']
-            team['W'] = [1 if r>0 and team_name==h else 1 if r<0 and team_name==a else 0 for r,a,h in team[['result','away_team','home_team']].values]
-            team['L'] = [0 if r>0 and team_name==h else 0 if r<0 and team_name==a else 1 for r,a,h in team[['result','away_team','home_team']].values]
-            team['W_PCT'] = team['W']/team['GP']
-            team['TOP'] = [t if team_name==p else 0 for t,p in team[['TOP_seconds','posteam']].values]
-            team['FGA'] = [1 if team_name==p and f==1 else 0 for p,f in team[['posteam','field_goal_attempt']].values]
-            team['FGM'] = [1 if team_name==p and f=='made' else 0 for p,f in team[['posteam','field_goal_result']].values]
-            team['FG_PCT'] = team['FGM']/team['FGA']
-            team['PassTD'] = np.where((team['posteam'] == team_name) & (team['pass_touchdown'] == 1), 1, 0)
-            team['RushTD'] = np.where((team['posteam'] == team_name) & (team['rush_touchdown'] == 1), 1, 0)
-            team['PassTD_Allowed'] = np.where((team['defteam'] == team_name) & (team['pass_touchdown'] == 1), 1, 0)
-            team['RushTD_Allowed'] = np.where((team['defteam'] == team_name) & (team['rush_touchdown'] == 1), 1, 0)
-            team['PassYds'] = [y if p==team_name else 0 for p,y in team[['posteam','passing_yards']].values]
-            team['RushYds'] = [y if p==team_name else 0 for p,y in team[['posteam','rushing_yards']].values]
-            team['PassYds_Allowed'] = [y if d==team_name else 0 for d,y in team[['defteam','passing_yards']].values]
-            team['RushYds_Allowed'] = [y if d==team_name else 0 for d,y in team[['defteam','rushing_yards']].values]
-            team['Fum'] = np.where((team['defteam'] == team_name) & (team['fumble_lost'] == 1), 1, 0)
-            team['Fum_Allowed'] = np.where((team['posteam'] == team_name) & (team['fumble_lost'] == 1), 1, 0)
-            team['INT'] = np.where((team['defteam'] == team_name) & (team['interception'] == 1), 1, 0)
-            team['INT_Allowed'] = np.where((team['posteam'] == team_name) & (team['interception'] == 1), 1, 0)
-            team['Sacks'] = np.where((team['defteam'] == team_name) & (team['sack'] == 1), 1, 0)
-            team['Sacks_Allowed'] = np.where((team['posteam'] == team_name) & (team['sack'] == 1), 1, 0)
-            team['Penalties'] = np.where((team['penalty_team'] == team_name), 1, 0)
-            team['FirstDowns'] = [1 if team_name==p and f==1 else 0 for p,f in team[['posteam','first_down']].values]
-            team['3rdDownConverted'] = [1 if p==team_name and t==1 else 0 for p,t in team[['posteam','third_down_converted']].values]
-            team['3rdDownFailed'] = [1 if p==team_name and t==1 else 0 for p,t in team[['posteam','third_down_failed']].values]
-            team['3rdDownAllowed'] = [1 if d==team_name and t==1 else 0 for d,t in team[['defteam','third_down_converted']].values]
-            team['3rdDownDefended'] = [1 if d==team_name and t==1 else 0 for d,t in team[['defteam','third_down_failed']].values]
-            team['PTS'] = [ap if at==team_name else hp if ht==team_name else None for ht,at,hp,ap in team[['home_team','away_team','home_score','away_score']].values]
-            team['PointDiff'] = [r if team_name==h else -r if team_name==a else 0 for r,a,h in team[['result','away_team','home_team']].values]
-
-            # aggregate from play-by-play to game-by-game
-            features = {
-                'GP':'mean',
-                'W':'mean',
-                'L':'mean',
-                'W_PCT':'mean',
-                'TOP':'sum',
-                'FGA':'sum',
-                'FGM':'sum',
-                'FG_PCT':'mean',
-                'PassTD':'sum',
-                'RushTD':'sum',
-                'PassTD_Allowed':'sum',
-                'RushTD_Allowed':'sum',
-                'PassYds':'sum',
-                'RushYds':'sum',
-                'PassYds_Allowed':'sum',
-                'RushYds_Allowed':'sum',
-                'Fum':'sum',
-                'Fum_Allowed':'sum',
-                'INT':'sum',
-                'INT_Allowed':'sum',
-                'Sacks':'sum',
-                'Sacks_Allowed':'sum',
-                'Penalties':'sum',
-                'FirstDowns':'sum',
-                '3rdDownConverted':'sum',
-                '3rdDownFailed':'sum',
-                '3rdDownAllowed':'sum',
-                '3rdDownDefended':'sum',
-                'PTS':'mean',
-                'PointDiff':'mean'
-            }
-
-            game = team.groupby('game_id').agg(features).reset_index().sort_values('GP')
-            game[['W','L']] = game[['W','L']].expanding().sum()
-            game[game.columns[4:]] = game[game.columns[4:]].expanding().mean()
-            if season != current_season:
-                game[game.columns[1:]] = game[game.columns[1:]].shift()
-                game['TEAM'] = team_name
-                game['Season'] = season
-            else:
-                game['TEAM'] = team_name
-                game['Season'] = season
-
-            data = pd.concat([data,game])
-
-    # separate home and away data and merge
-    data = data.merge(pbp[['game_id','home_team','away_team']].drop_duplicates())
-    home = data.loc[data['home_team']==data['TEAM']]
-    away = data.loc[data['away_team']==data['TEAM']]
-    away.columns = [f'{i}.Away' for i in away.columns]
-    gbg = home.merge(away,left_on='game_id',right_on='game_id.Away')
-    gbg.drop(columns=['TEAM','TEAM.Away','home_team.Away','away_team.Away','Season.Away','game_id.Away'], inplace=True)
-    gbg['game_date'] = gbg['game_id'].map(game_date_dict)
-
-    # save current data 
-    if current_season in get_seasons:
-        gbg_this_year = gbg.loc[gbg['Season']==current_season]
-        file_path = os.path.join(data_directory, 'gbg_this_year.csv')
-        gbg_this_year.to_csv(file_path, index=False)
-
-    # save historical data 
-    if get_seasons != [current_season]:
-        gbg = gbg.loc[gbg['Season']!=current_season]
-        file_path = os.path.join(data_directory, 'gbg.csv')
-        gbg.to_csv(file_path, index=False)
-
-
-def add_odds_data():
-    """
-    Get odds from Australian Sports Betting's free online dataset and merge it with game-by-game data.
-
-    """
-    
-    # get team abbreviations
-    team_descriptions = nfl.import_team_desc()
-    team_abbreviation_dict = dict(team_descriptions[['team_name','team_abbr']].values)
-    
-    # get odds
-    odds = pd.read_excel('https://www.aussportsbetting.com/historical_data/nfl.xlsx')
-    odds['Home Team'] = odds['Home Team'].str.replace('Washington Redskins','Washington Commanders').str.replace('Washington Football Team','Washington Commanders')
-    odds['Away Team'] = odds['Away Team'].str.replace('Washington Redskins','Washington Commanders').str.replace('Washington Football Team','Washington Commanders')
-    odds['Season'] = [i.year if i.month in [8,9,10,11,12] else i.year-1 for i in odds['Date']]
-    odds['Home Team Abbrev'] = odds['Home Team'].map(team_abbreviation_dict).str.replace('LAR','LA')
-    odds['Away Team Abbrev'] = odds['Away Team'].map(team_abbreviation_dict).str.replace('LAR','LA')
-    odds = odds[['Date','Home Score','Away Score','Home Team Abbrev','Away Team Abbrev','Home Odds Close','Away Odds Close','Total Score Close','Home Line Close']]
-    odds['Key'] = odds['Date'].astype(str) + odds['Home Team Abbrev'] + odds['Away Team Abbrev']
-    odds = odds.drop(columns=['Date','Home Team Abbrev','Away Team Abbrev']).dropna()
-    odds['Home Odds'] = [round((i-1)*100) if i>= 2 else round(-100/(i-1)) for i in odds['Home Odds Close']]
-    odds['Away Odds'] = [round((i-1)*100) if i>= 2 else round(-100/(i-1)) for i in odds['Away Odds Close']]
-    odds['Home Winnings'] = [ho-1 if h>a else -1 if a>h else 0 for ho,h,a in odds[['Home Odds Close','Home Score','Away Score']].values]
-    odds['Away Winnings'] = [ao-1 if a>h else -1 if h>a else 0 for ao,h,a in odds[['Away Odds Close','Home Score','Away Score']].values]
-
-    # load gbg data
-    file_path = os.path.join(data_directory, 'gbg.csv')
-    gbg = pd.read_csv(file_path)
-    file_path = os.path.join(data_directory, 'gbg_this_year.csv')
-    gbg_this_year = pd.read_csv(file_path)
-
-    # merge and save
-    dataframes = [gbg, gbg_this_year]
-    for idx in range(2):
-        i = dataframes[idx]
-        i['Key'] = i['game_date'].astype(str) + i['home_team'] + i['away_team']
-        gbg_and_odds = i.merge(odds, left_on='Key', right_on='Key')
-        gbg_and_odds['Home-Team-Cover'] = [1 if (h-a)>-l else 0 if (h-a)<-l else 2 for h,a,l in gbg_and_odds[['Home Score','Away Score','Home Line Close']].values] 
-        gbg_and_odds['Home-Team-Win'] = (gbg_and_odds['Home Score']>gbg_and_odds['Away Score']).astype(int)
-        gbg_and_odds['Over'] = ((gbg_and_odds['Home Score'] + gbg_and_odds['Away Score'])>gbg_and_odds['Total Score Close']).astype(int)
-        
-        if idx==0:
-            file_path = os.path.join(data_directory, 'gbg_and_odds.csv')
-        else:
-            file_path = os.path.join(data_directory, 'gbg_and_odds_this_year.csv')           
-        
-        gbg_and_odds.drop_duplicates(subset='game_id').to_csv(file_path, index=False)
-    
-
-

Source/Build/nfl_data_py

@@ -1 +0,0 @@
-Subproject commit e4988dc303bc441108dd11f4ae93a8200aab10e1

Source/Build/update.py

@@ -1,59 +0,0 @@
-import nfl_data_py.nfl_data_py as nfl
-import build
-import datetime as dt
-import numpy as np
-import pandas as pd
-pd.set_option('chained_assignment',None)
-pd.set_option('display.max_columns',None)
-import os
-import pickle as pkl
-
-current_directory = os.path.dirname(os.path.abspath(__file__))
-parent_directory = os.path.dirname(current_directory)
-data_directory = os.path.join(parent_directory, 'Data')
-pickle_directory = os.path.join(parent_directory, 'Pickles')
-
-# get team abbreviations
-file_path = os.path.join(pickle_directory, 'team_name_to_abbreviation.pkl')
-with open(file_path, 'rb') as f:
-    team_name_to_abbreviation = pkl.load(f)
-file_path = os.path.join(pickle_directory, 'team_abbreviation_to_name.pkl')
-with open(file_path, 'rb') as f:
-    team_abbreviation_to_name = pkl.load(f)
-
-# get current season
-year = dt.datetime.now().year
-month = dt.datetime.now().month
-current_season = year if month in [8,9,10,11,12] else year-1
-
-# get schedule
-print('Getting schedule.\n')
-url = 'https://www.nbcsports.com/nfl/schedule'
-df = pd.read_html(url)
-file_path = os.path.join(pickle_directory, 'schedule.pkl')
-with open(file_path, 'wb') as f:
-    pkl.dump(df, f)
-
-# update current season
-build.build_gbg_data(get_seasons=[current_season])
-#build.build_gbg_data(get_seasons=range(2014,2024))
-build.add_odds_data()
-
-# get winners
-pbp = build.get_pbp_data([current_season])
-pbp = pbp.drop_duplicates(subset='game_id')
-pbp[['season','week','away','home']] = pbp['game_id'].str.split('_', expand=True)
-games = pbp[['game_id','away_score','home_score','season','week','away','home']]
-games[['away_score','home_score','season','week']] = games[['away_score','home_score','season','week']].astype(int)
-
-games['away_team'] = games['away'].map(team_abbreviation_to_name)
-games['home_team'] = games['home'].map(team_abbreviation_to_name)
-
-games['total'] = games['away_score'] + games['home_score']
-games['winner'] = [a if a_s>h_s else h if h_s>a_s else 'Tie' for a,h,a_s,h_s in games[['away_team','home_team','away_score','home_score']].values]
-
-file_path = os.path.join(data_directory, 'results.csv')
-games[['game_id','total','winner']].to_csv(file_path, index=False)
-
-
-

Source/Data/gbg.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4b03612517c6505adabfc11be02fbd51be8ab8c104361f645401c58c128fd2d7
-size 1613287

Source/Data/gbg_and_odds.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d6f1a3ea061ed26a13c2398938efe0a60267d07abfde4baaff82db22ec35e79f
-size 1663814

Source/Data/gbg_and_odds_this_year-Thinkpad.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ffb812ba82afc8e124ea3186f8bcc04e66a10b15e9507e6fa8e6eba18463c5f7
-size 276

Source/Data/predictions.csv

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c67a5b32fca86661a44a993df5b8001073ab8e99fc0a588d050bfc04bb4f0c3
-size 20000

Source/Data/record.json

@@ -1 +1 @@
-{"winners_correct": "74", "winners_incorrect": "38", "winners_tie": "", "winners_return": "66.1% accuracy, -3.0x return", "over_unders_correct": "68", "over_unders_incorrect": "76", "over_unders_push": "-2", "over_unders_return": "46.6% accuracy, -14.1x return", "latest_game": "Monday, 12/25", "over_unders_binom": "72.0% chance of equal or better performance by flipping a coin.", "winners_binom": "<1% chance of equal or better performance by flipping a coin."}
+{"winners_correct": "74", "winners_incorrect": "38", "winners_tie": "", "winners_return": "66.1% accuracy, -3.0x return", "over_unders_correct": "68", "over_unders_incorrect": "76", "over_unders_push": "-2", "over_unders_return": "46.6% accuracy, -14.1x return", "latest_game": "Monday, 12/25", "over_unders_binom": "72.0% chance of equal or better performance by flipping a coin.", "winners_binom": "0.0% chance of equal or better performance by flipping a coin."}

Source/Predict/predict.py

@@ -1,156 +0,0 @@
-import xgboost as xgb
-import numpy as np
-import pandas as pd
-import pickle as pkl
-import os
-import requests
-from bs4 import BeautifulSoup
-import warnings
-warnings.filterwarnings("ignore")
-from datetime import datetime
-
-# set dirs for other files
-current_directory = os.path.dirname(os.path.abspath(__file__))
-parent_directory = os.path.dirname(current_directory)
-data_directory = os.path.join(parent_directory, 'Data')
-model_directory = os.path.join(parent_directory, 'Models')
-pickle_directory = os.path.join(parent_directory, 'Pickles')
-
-file_path = os.path.join(data_directory, 'gbg_this_year.csv')
-gbg = pd.read_csv(file_path, low_memory=False)
-
-file_path = os.path.join(data_directory, 'results.csv')
-results = pd.read_csv(file_path, low_memory=False)
-
-# get team abbreviations
-file_path = os.path.join(pickle_directory, 'team_name_to_abbreviation.pkl')
-with open(file_path, 'rb') as f:
-    team_name_to_abbreviation = pkl.load(f)
-
-file_path = os.path.join(pickle_directory, 'team_abbreviation_to_name.pkl')
-with open(file_path, 'rb') as f:
-    team_abbreviation_to_name = pkl.load(f)
-
-# get schedule
-file_path = os.path.join(pickle_directory, 'schedule.pkl')
-with open(file_path, 'rb') as f:
-    schedule = pkl.load(f)
-
-# get current week
-file_path = os.path.join(pickle_directory, 'the_week.pkl')
-with open(file_path, 'rb') as f:
-    the_week = pkl.load(f)
-
-# load models
-# moneyline
-model = 'xgboost_ML_no_odds_71.4%'
-file_path = os.path.join(model_directory, f'{model}.json')
-xgb_ml = xgb.Booster()
-xgb_ml.load_model(file_path)
-
-# over/under
-model = 'xgboost_OU_no_odds_59.8%'
-file_path = os.path.join(model_directory, f'{model}.json')
-xgb_ou = xgb.Booster()
-xgb_ou.load_model(file_path)
-
-
-def get_week():
-    week = the_week['week']
-    year = the_week['year']
-    return int(week), int(year)
-
-
-def get_games(week):
-    df = schedule[week-1]
-    df['Away Team'] = [' '.join(i.split('\xa0')[1:]) for i in df['Away TeamAway Team']]
-    df['Home Team'] = [' '.join(i.split('\xa0')[1:]) for i in df['Home TeamHome Team']]
-    df['Date'] = pd.to_datetime(df['Game TimeGame Time'])
-    df['Date'] = df['Date'].dt.strftime('%A %d/%m %I:%M %p')
-    df['Date'] = df['Date'].apply(lambda x: f"{x.split()[0]} {int(x.split()[1].split('/')[1])}/{int(x.split()[1].split('/')[0])} {x.split()[2]}".capitalize())
-    return df[['Away Team','Home Team','Date']]
-
-
-def get_one_week(home,away,season,week):
-    try:
-        max_GP_home = gbg.loc[((gbg['home_team'] == home) | (gbg['away_team'] == home)) & (gbg['GP'] < week)]['GP'].max()
-        max_GP_away = gbg.loc[((gbg['home_team'] == away) | (gbg['away_team'] == away)) & (gbg['GP'] < week)]['GP'].max()
-
-        home_df = gbg.loc[((gbg['away_team']==home) | (gbg['home_team']==home)) & (gbg['Season']==season) & (gbg['GP']==max_GP_home)]
-        gbg_home_team = home_df['home_team'].item()
-        home_df.drop(columns=['game_id','home_team','away_team','Season','game_date'], inplace=True)
-        home_df = home_df[[i for i in home_df.columns if '.Away' not in i] if gbg_home_team==home else [i for i in home_df.columns if '.Away' in i]]
-        home_df.columns = [i.replace('.Away','') for i in home_df.columns]
-
-        away_df = gbg.loc[((gbg['away_team']==away) | (gbg['home_team']==away)) & (gbg['Season']==season) & (gbg['GP']==max_GP_away)]
-        gbg_home_team = away_df['home_team'].item()
-        away_df.drop(columns=['game_id','home_team','away_team','Season','game_date'], inplace=True)
-        away_df = away_df[[i for i in away_df.columns if '.Away' not in i] if gbg_home_team==away else [i for i in away_df.columns if '.Away' in i]]
-        away_df.columns = [i.replace('.Away','') + '.Away' for i in away_df.columns]
-
-        df = home_df.reset_index(drop=True).merge(away_df.reset_index(drop=True), left_index=True, right_index=True)
-        return df
-    except ValueError:
-        return pd.DataFrame()
-
-
-def predict(home,away,season,week,total):
-    global results
-
-    # finish preparing data
-    if len(home)>4:
-        home_abbrev = team_name_to_abbreviation[home]
-    else:
-        home_abbrev = home
-
-    if len(away)>4:
-        away_abbrev = team_name_to_abbreviation[away]
-    else:
-        away_abbrev = away
-
-    data = get_one_week(home_abbrev,away_abbrev,season,week)
-    data['Total Score Close'] = total
-    matrix = xgb.DMatrix(data.astype(float).values)
-
-    # create game id 
-    if week < 10:
-        game_id = str(season) + '_0' + str(int(week)) + '_' + away_abbrev + '_' + home_abbrev
-    else:
-        game_id = str(season) + '_' + str(int(week)) + '_' + away_abbrev + '_' + home_abbrev
-
-    try:
-        moneyline_result = results.loc[results['game_id']==game_id, 'winner'].item()
-    except:
-        moneyline_result = 'N/A'
-
-    try:
-        ml_predicted_proba = xgb_ml.predict(matrix)[0][1]
-        winner_proba = max([ml_predicted_proba, 1-ml_predicted_proba]).item()
-        moneyline = {'Winner': [home if ml_predicted_proba>0.5 else away if ml_predicted_proba<0.5 else 'Toss-Up'],
-                     'Probabilities':[winner_proba],
-                     'Result': moneyline_result}
-    except:
-        moneyline = {'Winner': 'NA',
-                     'Probabilities':['N/A'],
-                     'Result': moneyline_result}
-    
-    try:
-        result = results.loc[results['game_id']==game_id, 'total'].item()
-        over_under_result = 'Over' if float(result)>float(total) else 'Push' if float(result)==float(total) else 'Under'
-
-    except:
-        over_under_result = 'N/A'
-    
-    try:
-        ou_predicted_proba = xgb_ou.predict(matrix)[0][1]
-        ou_proba = max([ou_predicted_proba, 1-ou_predicted_proba]).item()
-
-        over_under = {'Over/Under': ['Over' if ou_predicted_proba>0.5 else 'Under'],
-                      'Probability': [ou_proba],
-                      'Result': over_under_result}
-    except:
-        over_under = {'Over/Under': 'N/A',
-                      'Probability': ['N/A'],
-                      'Result': over_under_result}
-    
-    return game_id, moneyline, over_under

Source/Test/xgboost_ATS.py

@@ -1,73 +0,0 @@
-from cgi import test
-import xgboost as xgb
-import pandas as pd
-import pickle as pkl
-import numpy as np
-import os
-
-model = 'xgboost_ATS_no_odds_57.3%'
-
-current_directory = os.path.dirname(os.path.abspath(__file__))
-parent_directory = os.path.dirname(current_directory)
-data_directory = os.path.join(parent_directory, 'Data')
-model_directory = os.path.join(parent_directory, 'Models')
-pickle_directory = os.path.join(parent_directory, 'Pickles')
-
-file_path = os.path.join(model_directory, f'{model}.json')
-xgb_ml = xgb.Booster()
-xgb_ml.load_model(file_path)
-
-file_path = os.path.join(pickle_directory, 'test_games_ATS_no_odds.pkl')
-with open(file_path,'rb') as f:
-    test_games = pkl.load(f).tolist()
-
-file_path = os.path.join(data_directory, 'gbg_and_odds.csv')
-gbg_and_odds = pd.read_csv(file_path)
-test_data = gbg_and_odds.loc[gbg_and_odds['game_id'].isin(test_games)]
-test_data_matrix = xgb.DMatrix(test_data.drop(columns=['game_id','Home-Team-Win','Home-Team-Cover','Over','Season','home_team','away_team','game_date','Key','Home Score','Away Score','Home Odds Close','Away Odds Close','Home Winnings','Away Winnings','Away Odds','Home Odds']).astype(float).values)
-
-predicted_probas = xgb_ml.predict(test_data_matrix)
-predictions = np.argmax(predicted_probas, axis=1)
-test_data['predicted_proba'] = [i[1] for i in predicted_probas]
-test_data['prediction'] = predictions
-test_data['correct'] = test_data['Home-Team-Cover']==test_data['prediction']
-print(test_data['predicted_proba'])
-print(test_data['correct'].mean())
-
-bets = test_data.loc[(test_data['predicted_proba']>0.5) | (test_data['predicted_proba']<0.5)]
-bets['winnings'] = [0.91 if c==1 else -1 for c in bets['correct']]
-
-print('Actual')
-print(bets.loc[bets['Home-Team-Cover']==1].shape)
-print(bets.loc[bets['Home-Team-Cover']==0].shape)
-print(bets.loc[bets['Home-Team-Cover']==2].shape)
-
-print('Predicted')
-print(bets.loc[bets['prediction']==1].shape)
-print(bets.loc[bets['prediction']==0].shape)
-print(bets.loc[bets['prediction']==2].shape)
-
-
-import matplotlib.pyplot as plt
-fig = plt.figure(facecolor='black')
-ax = fig.add_subplot(1, 1, 1, facecolor='black')
-
-# Plot data with line color as RGB(0, 128, 0)
-ax.plot(bets['winnings'].cumsum().values*100, linewidth=3, color=(0/255, 128/255, 0/255))
-
-# Set title and labels
-ax.set_title('MARCI 3.0 - Against the Spread', color='white')
-ax.set_xlabel('Games Bet On', color='white')
-ax.set_ylabel('Return (%)', color='white')
-
-# Change tick colors to white
-ax.tick_params(axis='x', colors='white')
-ax.tick_params(axis='y', colors='white')
-
-# Change axis edge colors
-ax.spines['bottom'].set_color('white')
-ax.spines['top'].set_color('white')
-ax.spines['left'].set_color('white')
-ax.spines['right'].set_color('white')
-
-plt.savefig(f'{model}_dark.png', facecolor='black')

Source/Test/xgboost_ML.py

@@ -1,59 +0,0 @@
-import xgboost as xgb
-import pandas as pd
-import pickle as pkl
-import numpy as np
-import os
-
-model = 'xgboost_ML_no_odds_71.4%'
-
-current_directory = os.path.dirname(os.path.abspath(__file__))
-parent_directory = os.path.dirname(current_directory)
-data_directory = os.path.join(parent_directory, 'Data')
-model_directory = os.path.join(parent_directory, 'Models')
-pickle_directory = os.path.join(parent_directory, 'Pickles')
-
-file_path = os.path.join(model_directory, f'{model}.json')
-xgb_ml = xgb.Booster()
-xgb_ml.load_model(file_path)
-
-file_path = os.path.join(pickle_directory, 'test_games_ML_no_odds.pkl')
-with open(file_path,'rb') as f:
-    test_games = pkl.load(f).tolist()
-
-file_path = os.path.join(data_directory, 'gbg_and_odds.csv')
-gbg_and_odds = pd.read_csv(file_path)
-test_data = gbg_and_odds.loc[gbg_and_odds['game_id'].isin(test_games)]
-test_data_matrix = xgb.DMatrix(test_data.drop(columns=['game_id','Over','Home-Team-Win','Season','home_team','away_team','game_date','Key','Home Score','Away Score','Home Odds Close','Away Odds Close','Home Winnings','Away Winnings','Away Odds','Home Odds']).astype(float).values)
-
-predicted_probas = xgb_ml.predict(test_data_matrix)
-predictions = np.argmax(predicted_probas, axis=1)
-test_data['predicted_proba'] = [i[1] for i in predicted_probas]
-test_data['prediction'] = (test_data['predicted_proba']>0.5).astype(int)
-test_data['correct'] = test_data['Home-Team-Win']==test_data['prediction']
-
-bets = test_data.loc[(test_data['predicted_proba']>0.6) | (test_data['predicted_proba']<0.4)]
-bets['winnings'] = [h if p==1 else a for h,a,p in bets[['Home Winnings','Away Winnings','prediction']].values]
-
-import matplotlib.pyplot as plt
-fig = plt.figure(facecolor='black')
-ax = fig.add_subplot(1, 1, 1, facecolor='black')
-
-# Plot data with line color as RGB(0, 128, 0)
-ax.plot(bets['winnings'].cumsum().values*100, linewidth=3, color=(0/255, 128/255, 0/255))
-
-# Set title and labels
-ax.set_title('MARCI 3.0 - MoneyLine w/ 60% Confidence Threshold', color='white')
-ax.set_xlabel('Games Bet On', color='white')
-ax.set_ylabel('Return (%)', color='white')
-
-# Change tick colors to white
-ax.tick_params(axis='x', colors='white')
-ax.tick_params(axis='y', colors='white')
-
-# Change axis edge colors
-ax.spines['bottom'].set_color('white')
-ax.spines['top'].set_color('white')
-ax.spines['left'].set_color('white')
-ax.spines['right'].set_color('white')
-
-plt.savefig(f'{model}_dark.png', facecolor='black')