def getAllOdds(year):
df = getDataSet('DataForModel_' + year + '.xlsx')
dates = df.GAME_DATE_EST_x_x.unique()
dfall = getDataSet('Historical_Odds_' + year + '.xlsx')
done = dfall.GAME_DATE_EST_x.unique()
for i in dates:
if i > done[-1]:
x = i
i = i[:10]
i = i.replace("-", "")
print(i)
df = main(i)
# df = getDataSet('Todays_Odds.xlsx')
df['AwayTeam'] = df.apply(getTeams, axis=1)
df['HomeTeam'] = df.apply(getOppTeams, axis=1)
df['key'] = df['key'].astype(str)
df['GAMECODE_x'] = df.apply(getGameCodeODDS, axis=1)
df['VegasLines'] = df.apply(filterOdds, axis=1)
df['TEAM_ABBREVIATION_x_x'] = df['AwayTeam']
df = pd.DataFrame({
'GAMECODE_x':
df['GAMECODE_x'],
'TEAM_ABBREVIATION_x_x':
df['TEAM_ABBREVIATION_x_x'],
'VegasLines':
df['VegasLines'],
'GAME_DATE_EST_x':
x
})
# saveToExcel(df,'Todays_Odds.xlsx','Master')
# dfh = getDataSet('Historical_Odds.xlsx')
dfall = dfall.append(df)
saveToExcel(dfall, 'Historical_Odds_' + year + '.xlsx', 'Master')
def backtest():
# ----Add in ability so select certain models--------------
odds = GetOdds()
df = getDataSet('DataForModel_' + year + '.xlsx')
startDate = '2017-10-31T00:00:00'
df = df.loc[df['GAME_DATE_EST_x'] >= startDate]
actual = getDataSet('AllStats_' + year + '.xlsx')
proj = RunModels(df, odds)
getResults(actual, proj, 'ALL')
def backtest(year, both):
odds = getDataSet('Historical_Odds_' + year + '.xlsx')
if both:
odds1 = getDataSet('Historical_Odds_' + '2015' + '.xlsx')
odds2 = getDataSet('Historical_Odds_' + '2016' + '.xlsx')
frames = [odds1, odds2]
odds = pd.concat(frames)
df = getDataSet('DataForModel_' + year + '.xlsx')
if both:
df1 = getDataSet('DataForModel_' + '2015' + '.xlsx')
df2 = getDataSet('DataForModel_' + '2016' + '.xlsx')
frames = [df1, df2]
df = pd.concat(frames)
actual = getDataSet('AllStats_' + year + '.xlsx')
if both:
actual1 = getDataSet('AllStats_' + '2015' + '.xlsx')
actual2 = getDataSet('AllStats_' + '2016' + '.xlsx')
frames = [actual1, actual2]
actual = pd.concat(frames)
Regression(df)
proj = RunModels(df, odds)
results = getResults(actual, proj, 'Backtest')
# dfr = pd.merge(dfd, results, on=['GAMECODE_x','TEAM_ABBREVIATION_x'],how='left')
# saveToExcel(dfr,'BackTest_Data.xlsx','Master')
dfb = getResultSummary(results)
if both:
saveToExcel(dfb, 'BackTest_Summary.xlsx', 'Both')
if not both:
saveToExcel(dfb, 'BackTest_Summary.xlsx', year)
def GetYesterdaysData():
yesterdaysGames = getGames(yesterday)
df = getADVStats(yesterdaysGames)
saveToExcel(df, 'yesterdaysGames.xlsx', 'Master')
df1 = getDataSet('AllStats_' + year + '.xlsx')
df2 = getDataSet('yesterdaysGames.xlsx')
df4 = df1.tail(1)
x = df4['GAMECODE'].str[:9].values
df5 = df2.head(1)
y = df5['GAMECODE'].str[:9].values
df3 = df1.append(df2)
if x != y:
saveToExcel(df3, 'AllStats_' + year + '.xlsx', 'Master')
return df3
def liveResults():
todaysGames = getGames(today)
df = getADVStats(todaysGames)
df['GAMECODE_x'] = df['GAMECODE']
df['TEAM_ABBREVIATION_x'] = df['TEAM_ABBREVIATION']
actual = df[['GAMECODE_x', 'TEAM_ABBREVIATION_x', 'PTS']]
projected = getDataSet('Projections.xlsx')
getResults(actual, projected, 'Todays')
def CalcStats(year):
# ---------------- Split data out by team and calculate stats ------------------------
dataset = getDataSet('AllStats_'+ year + '.xlsx')
SplitTeams(dataset,year)
# ---------------- Consume team data from tabs to make one dataset and combine both teams onto one line------------------------
d1 = getFirstSplit(year)
# #---------------- Cosolidate split team data, remove first 6 rows without Last 5 calcs, Filter only needed columns------------------------
teamdata4 = trimDF(d1)
print('Stat Calculation Complete')
def GetOdds():
df1 = getDataSet('Historical_Odds_' + '2017' + '.xlsx')
if fetchOdds:
scrapeOdds()
df = getDataSet('Todays_Odds.xlsx')
df['AwayTeam'] = df.apply(getTeams, axis=1)
df['HomeTeam'] = df.apply(getOppTeams, axis=1)
df['key'] = df['key'].astype(str)
df['GAMECODE_x'] = df.apply(getGameCodeODDS, axis=1)
df['VegasLines'] = df.apply(filterOdds, axis=1)
df['TEAM_ABBREVIATION_x_x'] = df['AwayTeam']
df = df[['GAMECODE_x', 'TEAM_ABBREVIATION_x_x', 'VegasLines']]
saveToExcel(df, 'Todays_Odds.xlsx', 'Master')
df1 = df1.append(df)
saveToExcel(df1, 'Season_Odds.xlsx', 'Master')
# df3 = df1.tail(1)
# x = df3['GAMECODE_x'].str[:9].values
# df4 =df.head(1)
# y = df4['GAMECODE_x'].str[:9].values
# if x != y:
# df2 = df1.append(df)
# saveToExcel(df2,'Season_Odds.xlsx','Master')
return df1
def GetTodaysData():
todaysGames = getTodaysGames(today)
game = []
df = getDataSet('DataForModel_' + year + '.xlsx')
# df = df.dropna()
for i in todaysGames:
hometeam = i[12:]
awayteam = i[9:12]
game.append([hometeam, awayteam])
print(game)
dfb = pd.DataFrame(columns=[
'Match', 'GAMECODE_x', 'GAME_DATE_x', 'TEAM_ABBREVIATION_x_x',
'HomeIndex_x_x', 'DaysRest_x', 'AvgPace_x_x', 'AvgORTG_x_x',
'AvgDRTG_x_x', 'AvgORTG_L5_x_x', 'AvgDRTG_L5_x_x', 'std_AvgORTG_x_x',
'std_AvgDRTG_x_x', 'std_AvgORTG_L5_x_x', 'std_AvgDRTG_L5_x_x',
'HomeORTG_x_x', 'HomeDRTG_x_x', 'AwayORTG_x_x', 'AwayDRTG_x_x',
'Location_Avg_ORTG_x_x', 'DaysRest_y', 'AvgPace_x_y', 'AvgORTG_x_y',
'AvgDRTG_x_y', 'AvgORTG_L5_x_y', 'AvgDRTG_L5_x_y', 'std_AvgORTG_x_y',
'std_AvgDRTG_x_y', 'std_AvgORTG_L5_x_y', 'std_AvgDRTG_L5_x_y',
'HomeORTG_x_y', 'HomeDRTG_x_y', 'AwayORTG_x_y', 'AwayDRTG_x_y',
'Location_Avg_ORTG_x_y'
])
for x in game:
match = x[1] + x[0]
df1 = df.loc[df['TEAM_ABBREVIATION_x'] == x[0]]
df2 = df.loc[df['TEAM_ABBREVIATION_x'] == x[1]]
df1 = df1.tail(1)
df2 = df2.tail(1)
df1['Match'] = match
df2['Match'] = match
df1['GAME_DATE'] = pd.to_datetime(df1['GAMECODE'].str[:9])
df2['GAME_DATE'] = pd.to_datetime(df2['GAMECODE'].str[:9])
df1['today'] = pd.to_datetime(today)
df2['today'] = pd.to_datetime(today)
df1['DaysRest'] = (df1['today'] -
df1['GAME_DATE']).astype('timedelta64[D]')
df2['DaysRest'] = (df2['today'] -
df2['GAME_DATE']).astype('timedelta64[D]')
df3 = pd.merge(df1, df2, on='Match', how='outer')
df4 = pd.merge(df2, df1, on='Match', how='outer')
date = today.replace("-", "")
df3['date'] = date
df4['date'] = date
df3['GAMECODE_x'] = df3.apply(getGameCodeToday, axis=1)
df4['GAMECODE_x'] = df4.apply(getGameCodeToday, axis=1)
# print(df4.head())
df3 = df3[[
'Match', 'GAMECODE_x', 'GAME_DATE_x', 'TEAM_ABBREVIATION_x_x',
'HomeIndex_x_x', 'DaysRest_x', 'AvgPace_x_x', 'AvgORTG_x_x',
'AvgDRTG_x_x', 'AvgORTG_L5_x_x', 'AvgDRTG_L5_x_x',
'std_AvgORTG_x_x', 'std_AvgDRTG_x_x', 'std_AvgORTG_L5_x_x',
'std_AvgDRTG_L5_x_x', 'HomeORTG_x_x', 'HomeDRTG_x_x',
'AwayORTG_x_x', 'AwayDRTG_x_x', 'Location_Avg_ORTG_x_x',
'DaysRest_y', 'AvgPace_x_y', 'AvgORTG_x_y', 'AvgDRTG_x_y',
'AvgORTG_L5_x_y', 'AvgDRTG_L5_x_y', 'std_AvgORTG_x_y',
'std_AvgDRTG_x_y', 'std_AvgORTG_L5_x_y', 'std_AvgDRTG_L5_x_y',
'HomeORTG_x_y', 'HomeDRTG_x_y', 'AwayORTG_x_y', 'AwayDRTG_x_y',
'Location_Avg_ORTG_x_y'
]]
df4 = df4[[
'Match', 'GAMECODE_x', 'GAME_DATE_x', 'TEAM_ABBREVIATION_x_x',
'HomeIndex_x_x', 'DaysRest_x', 'AvgPace_x_x', 'AvgORTG_x_x',
'AvgDRTG_x_x', 'AvgORTG_L5_x_x', 'AvgDRTG_L5_x_x',
'std_AvgORTG_x_x', 'std_AvgDRTG_x_x', 'std_AvgORTG_L5_x_x',
'std_AvgDRTG_L5_x_x', 'HomeORTG_x_x', 'HomeDRTG_x_x',
'AwayORTG_x_x', 'AwayDRTG_x_x', 'Location_Avg_ORTG_x_x',
'DaysRest_y', 'AvgPace_x_y', 'AvgORTG_x_y', 'AvgDRTG_x_y',
'AvgORTG_L5_x_y', 'AvgDRTG_L5_x_y', 'std_AvgORTG_x_y',
'std_AvgDRTG_x_y', 'std_AvgORTG_L5_x_y', 'std_AvgDRTG_L5_x_y',
'HomeORTG_x_y', 'HomeDRTG_x_y', 'AwayORTG_x_y', 'AwayDRTG_x_y',
'Location_Avg_ORTG_x_y'
]]
dfb = dfb.append(df3)
dfb = dfb.append(df4)
dfb = dfb.dropna()
# dfb = dfb[['TEAM_ABBREVIATION_x_x','HomeIndex_x_x','ProjectedPace','DaysRest_x','DaysRest_y','std_AvgORTG_x_x','HomeORTG_x_x','AwayORTG_x_x','std_AvgORTG_L5_x_x','AvgDRTG_x_y','HomeDRTG_x_y','AwayDRTG_x_y','std_AvgDRTG_x_y']]
return dfb