Spaces:
Running
Running
| import xgboost as xgb | |
| import numpy as np | |
| import pandas as pd | |
| import pickle as pkl | |
| import os | |
| import requests | |
| from bs4 import BeautifulSoup | |
| # 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) | |
| # 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) | |
| def get_week(): | |
| headers = { | |
| 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7', | |
| 'Accept-Encoding': 'gzip, deflate', | |
| 'Accept-Language': 'en-US,en;q=0.9', | |
| 'Cache-Control': 'max-age=0', | |
| 'Connection': 'keep-alive', | |
| 'Dnt': '1', | |
| 'Upgrade-Insecure-Requests': '1', | |
| 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/116.0.0.0 Safari/537.36' | |
| } | |
| url = 'https://www.nfl.com/schedules/' | |
| resp = requests.get(url,headers=headers) | |
| soup = BeautifulSoup(resp.text, 'html.parser') | |
| h2_tags = soup.find_all('h2') | |
| year = h2_tags[0].getText().split(' ')[0] | |
| week = h2_tags[0].getText().split(' ')[-1] | |
| return int(week), int(year) | |
| def get_games(): | |
| # pull from NBC | |
| url = 'https://www.nbcsports.com/nfl/schedule' | |
| df = pd.read_html(url)[0] | |
| 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: | |
| home_df = gbg.loc[((gbg['away_team']==home) | (gbg['home_team']==home)) & (gbg['Season']==season) & (gbg['GP']==week-1)] | |
| home_df = home_df[[i for i in home_df.columns if '.Away' not in i] if home_df['home_team'].item()==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)] | |
| away_df = away_df[[i for i in away_df.columns if '.Away' not in i] if away_df['home_team'].item()==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] | |
| drop_columns = ['game_id', 'Season', 'home_team', 'away_team', 'game_date'] | |
| df = home_df.merge(away_df, left_on='GP', right_on='GP.Away').drop(columns=drop_columns) | |
| return df | |
| except ValueError: | |
| return pd.DataFrame() | |
| def predict(home,away,season,week,total): | |
| # finish preparing data | |
| home_abbrev = team_name_to_abbreviation[home] | |
| away_abbrev = team_name_to_abbreviation[away] | |
| data = get_one_week(home_abbrev,away_abbrev,season,week) | |
| data['Total Score Close'] = total | |
| matrix = xgb.DMatrix(data.astype(float).values) | |
| # moneyline | |
| model = 'xgboost_ML_no_odds_69.8%' | |
| file_path = os.path.join(model_directory, f'{model}.json') | |
| xgb_ml = xgb.Booster() | |
| xgb_ml.load_model(file_path) | |
| try: | |
| ml_predicted_proba = xgb_ml.predict(matrix)[0][1] | |
| print(xgb_ml.predict(matrix)) | |
| winner_proba = max([ml_predicted_proba, 1-ml_predicted_proba]).item() | |
| moneyline = {'Winner': [home if ml_predicted_proba>0.6 else away if ml_predicted_proba<0.4 else 'Toss-Up'], | |
| 'Probabilities':[winner_proba]} | |
| except: | |
| moneyline = {'Winner': 'NA', | |
| 'Probabilities':['N/A']} | |
| # over/under | |
| model = 'xgboost_OU_no_odds_60.8%' | |
| file_path = os.path.join(model_directory, f'{model}.json') | |
| xgb_ou = xgb.Booster() | |
| xgb_ou.load_model(file_path) | |
| 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]} | |
| except: | |
| over_under = {'Over/Under': 'N/A', | |
| 'Probability': ['N/A']} | |
| # create game id to save predictions | |
| game_id = str(season) + '_' + str(week) + '_' + away_abbrev + '_' + home_abbrev | |
| return game_id, moneyline, over_under | |