Add dynamic updating record

Source/Build/build.py

@@ -18,10 +18,10 @@ 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. 
-    If you choose to overwrite, it will replace the existing pbp data with the data you pull.
 
     """
     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
@@ -110,10 +110,9 @@ def build_gbg_data(get_seasons=[]):
                 'PointDiff':'mean'
             }
 
-            game = team.groupby('game_id').agg(features).reset_index()
+            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
@@ -161,9 +160,9 @@ def add_odds_data():
     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)
-    odds['Away Team Abbrev'] = odds['Away Team'].map(team_abbreviation_dict)
-    odds = odds[['Date','Home Score','Away Score','Home Team Abbrev','Away Team Abbrev','Home Odds Close','Away Odds Close','Total Score Close']]
+    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']]
@@ -183,6 +182,7 @@ def add_odds_data():
         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)
         
@@ -191,7 +191,7 @@ def add_odds_data():
         else:
             file_path = os.path.join(data_directory, 'gbg_and_odds_this_year.csv')           
         
-        gbg_and_odds.to_csv(file_path, index=False)
+        gbg_and_odds.drop_duplicates(subset='game_id').to_csv(file_path, index=False)
     
 
 

Source/Build/update.py

@@ -1,4 +1,3 @@
-from operator import index
 import nfl_data_py.nfl_data_py as nfl
 import build
 import datetime as dt
@@ -29,10 +28,12 @@ current_season = year if month in [8,9,10,11,12] else year-1
 
 # 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([2023])
+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']]
@@ -48,3 +49,4 @@ 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 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87ac3980c207a257b4a0d006502ce2a79ea40e72107b8ab76f9f6114209bc6ff
+oid sha256:4b03612517c6505adabfc11be02fbd51be8ab8c104361f645401c58c128fd2d7
 size 1613287

Source/Data/gbg_and_odds.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb55eaa75e12c6cffdb65601f2a48b5c09850dd5b42daa0415a2ce9896417eb6
-size 1558685
+oid sha256:d6f1a3ea061ed26a13c2398938efe0a60267d07abfde4baaff82db22ec35e79f
+size 1663814

Source/Data/predictions_this_year.pkl

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:926248e52d1fa532c317e37da24ed652ae64110f8219cb5e061668bd3091f048
-size 5

Source/Data/record.json

@@ -0,0 +1 @@
+{"winners_correct": "5", "winners_incorrect": "11", "over_unders_correct": "7", "over_unders_incorrect": "9"}

Source/Predict/predict.py

@@ -5,6 +5,8 @@ import pickle as pkl
 import os
 import requests
 from bs4 import BeautifulSoup
+import warnings
+warnings.filterwarnings("ignore")
 
 # set dirs for other files
 current_directory = os.path.dirname(os.path.abspath(__file__))
@@ -64,27 +66,26 @@ def get_games(week):
 def get_one_week(home,away,season,week):
     try:
         home_df = gbg.loc[((gbg['away_team']==home) | (gbg['home_team']==home)) & (gbg['Season']==season) & (gbg['GP']==week-1)]
-        print(home_df)
         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']==week-1)]
-        print(away_df)
         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.merge(away_df, left_on='GP', right_on='GP.Away')
-        print(df.columns)
         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]
@@ -149,5 +150,4 @@ def predict(home,away,season,week,total):
                       'Probability': ['N/A'],
                       'Result': over_under_result}
     
-    print(moneyline)
     return game_id, moneyline, over_under

get_record.py

@@ -0,0 +1,52 @@
+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
+from Source.Predict.predict import predict
+
+# get team abbreviations
+with open('Source/Pickles/team_abbreviation_to_name.pkl', 'rb') as f:
+    team_abbreviation_to_name = pkl.load(f)
+
+# get this year's odds and results
+gbg_and_odds_this_year = pd.read_csv('Source/Data/gbg_and_odds_this_year.csv')
+results = pd.read_csv('Source/Data/results.csv')
+
+# make predictions
+from tqdm import tqdm
+print("Predicting games and getting record")
+predictions = {}
+for game_id,home,away,season,week,total in tqdm(gbg_and_odds_this_year[['game_id','home_team','away_team','Season','GP','Total Score Close']].values):
+    if week!=1:
+        predictions[game_id] = predict(home,away,season,week,total)
+
+# get record and save it
+predictions_df = pd.DataFrame(predictions).T
+predictions_df['predicted_winner'] = [i['Winner'][0] if type(i['Winner'])==list else None for i in predictions_df[1]]
+predictions_df['predicted_winner'] = predictions_df['predicted_winner'].map(team_abbreviation_to_name)
+predictions_df['predicted_over_under'] = [i['Over/Under'][0] if type(i['Over/Under'])==list else None for i in predictions_df[2]]
+predictions_df = predictions_df.merge(results, left_index=True, right_on='game_id').merge(gbg_and_odds_this_year[['game_id','Total Score Close']]).dropna(subset=['predicted_winner'])
+predictions_df['over_under'] = ['Over' if t>tsc else 'Under' if t<tsc else 'Push' for t,tsc in predictions_df[['total','Total Score Close']].values]
+
+predictions_df['winner_correct'] = (predictions_df['predicted_winner']==predictions_df['winner']).astype(int)
+predictions_df['winner_incorrect'] = (predictions_df['predicted_winner']!=predictions_df['winner']).astype(int)
+predictions_df['over_under_correct'] = (predictions_df['predicted_over_under']==predictions_df['over_under']).astype(int)
+predictions_df['over_under_incorrect'] = (predictions_df['predicted_over_under']!=predictions_df['over_under']).astype(int)
+
+winners_correct = predictions_df['winner_correct'].sum()
+winners_incorrect = predictions_df['winner_incorrect'].sum()
+over_unders_correct = predictions_df['over_under_correct'].sum()
+over_unders_incorrect = predictions_df['over_under_incorrect'].sum()
+
+record = {"winners_correct":str(winners_correct),
+        "winners_incorrect":str(winners_incorrect),
+        "over_unders_correct":str(over_unders_correct),
+        "over_unders_incorrect":str(over_unders_incorrect)}
+
+import json
+with open('Source/Data/record.json', 'w') as f:
+    json.dump(record,f)
+

main.py

@@ -9,6 +9,8 @@ pd.set_option('display.expand_frame_repr', False)
 
 import os
 import json
+with open('Source/Data/record.json','r') as f:
+    record = json.load(f)
 
 # input the over/under lines here for quicker predictions!
 lines = [44.5,
@@ -38,7 +40,7 @@ games = predict.get_games(week)[['Date','Away Team','Home Team']]
 
 @app.route('/')
 def index():
-    return render_template('index.html')
+    return render_template('index.html', **record)
 
 @app.route('/get_lines')
 def get_lines():