def get_5v5_df_start_end(**kwargs):
"""
This method retrieves the correct years of the 5v5 player log and concatenates them.
:param kwargs: the relevant ones here are startseason and endseason
:return: dataframe
"""
startdate, enddate = get_startdate_enddate_from_kwargs(**kwargs)
startseason, endseason = (helper.infer_season_from_date(x)
for x in (startdate, enddate))
df = []
for season in range(startseason, endseason + 1):
temp = manip.get_5v5_player_log(season)
sch = schedules.get_season_schedule(season)
temp = temp.merge(sch[['Game', 'Date']], how='left', on='Game')
temp = temp[(temp.Date >= startdate) & (temp.Date <= enddate)]
temp = temp.assign(Season=season)
df.append(temp)
df = pd.concat(df).sort_values(['Date']).drop(
'Date', axis=1) # When games rescheduled, Game ID not in order.
return df
def get_team_schedule(season=None, team=None, startdate=None, enddate=None):
"""
Gets the schedule for given team in given season. Or if startdate and enddate are specified, searches between
those dates. If season and startdate (and/or enddate) are specified, searches that season between those dates.
:param season: int, the season
:param team: int or str, the team
:param startdate: str, YYYY-MM-DD
:param enddate: str, YYYY-MM-DD
:return: dataframe
"""
# TODO handle case when only team and startdate, or only team and enddate, are given
if season is not None:
df = get_season_schedule(season).query('Status != "Scheduled"')
if startdate is not None:
df = df.query('Date >= "{0:s}"'.format(startdate))
if enddate is not None:
df = df.query('Date <= "{0:s}"'.format(enddate))
tid = team_info.team_as_id(team)
return df[(df.Home == tid) | (df.Road == tid)]
if startdate is not None and enddate is not None:
dflst = []
startseason = helpers.infer_season_from_date(startdate)
endseason = helpers.infer_season_from_date(enddate)
for season in range(startseason, endseason + 1):
df = get_team_schedule(season, team) \
.query('Status != "Scheduled"') \
.assign(Season=season)
if season == startseason:
df = df.query('Date >= "{0:s}"'.format(startdate))
if season == endseason:
df = df.query('Date <= "{0:s}"'.format(enddate))
dflst.append(df)
df = pd.concat(dflst)
return df
def get_enddate_from_kwargs(**kwargs):
"""Returns 6/21 of endseason + 1, or enddate"""
if 'enddate' in kwargs:
return kwargs['enddate']
elif 'endseason' in kwargs:
today = datetime.datetime.now().strftime('%Y-%m-%d')
return min('{0:d}-06-21'.format(kwargs['endseason']+1), today)
elif 'startseason' in kwargs:
return get_enddate_from_kwargs(endseason=kwargs['startseason'])
elif 'season' in kwargs:
return get_enddate_from_kwargs(endseason=kwargs['season'])
elif 'startdate' in kwargs:
return get_enddate_from_kwargs(endseason=helper.infer_season_from_date(kwargs['startdate']))
else:
return get_enddate_from_kwargs(endseason=schedules.get_current_season())
def get_fline_shot_rates(team, startdate, enddate):
"""
Gets CF/60 and CA/60 by defenseman duo (5v5 only) for this team between given range of dates
:param team: int or str, team
:param startdate: str, start date
:param enddate: str, end date (inclusive)
:return: dataframe with PlayerID1, PlayerID2, CF, CA, TOI (in secs), CF/60 and CA/60
"""
# TODO this method is so slow
startseason, endseason = [
helper.infer_season_from_date(x) for x in (startdate, enddate)
]
dflst = []
for season in range(startseason, endseason + 1):
games_played = schedules.get_team_games(season, team, startdate,
enddate)
games_played = [g for g in games_played if 20001 <= g <= 30417]
toi = combos.get_team_combo_toi(season, team, games_played, n_players=3) \
.rename(columns={'Secs': 'TOI'})
cfca = combos.get_team_combo_corsi(season,
team,
games_played,
n_players=3)
joined = toi.merge(cfca, how='outer', on=['PlayerID1', 'PlayerID2', 'PlayerID3']) \
.assign(Season=season)
dflst.append(joined)
df = pd.concat(dflst) \
.groupby(['PlayerID1', 'PlayerID2', 'PlayerID3'], as_index=False).sum()
df.loc[:, 'CF60'] = df.CF * 3600 / df.TOI
df.loc[:, 'CA60'] = df.CA * 3600 / df.TOI
forwards = players.get_player_ids_file().query('Pos != "D"')[['ID']]
df = df.merge(forwards.rename(columns={'ID': 'PlayerID1'}), how='inner', on='PlayerID1') \
.merge(forwards.rename(columns={'ID': 'PlayerID2'}), how='inner', on='PlayerID2') \
.merge(forwards.rename(columns={'ID': 'PlayerID3'}), how='inner', on='PlayerID3')
return df
def get_startdate_enddate_from_kwargs(**kwargs):
"""Returns startseason and endseason kwargs. Defaults to current - 3 and current"""
enddate = get_enddate_from_kwargs(**kwargs)
if 'last_n_days' in kwargs:
enddate2 = datetime.datetime(*[int(x) for x in enddate.split('-')])
startdate2 = enddate2 - datetime.timedelta(days=kwargs['last_n_days'])
startdate = startdate2.strftime('%Y-%m-%d')
elif 'startdate' in kwargs:
startdate = kwargs['startdate']
elif 'startseason' in kwargs:
startdate = '{0:d}-09-15'.format(kwargs['startseason'])
elif 'season' in kwargs:
startdate = '{0:d}-09-15'.format(kwargs['season'])
else:
startdate = '{0:d}-09-15'.format(helper.infer_season_from_date(enddate) - 3)
return startdate, enddate
def get_dpair_shot_rates(team, startdate, enddate):
"""
Gets CF/60 and CA/60 by defenseman duo (5v5 only) for this team between given range of dates
:param team: int or str, team
:param startdate: str, start date
:param enddate: str, end date (inclusive)
:return: dataframe with PlayerID1, PlayerID2, CF, CA, TOI (in secs), CF/60 and CA/60
"""
startseason, endseason = [
helper.infer_season_from_date(x) for x in (startdate, enddate)
]
dflst = []
for season in range(startseason, endseason + 1):
games_played = schedules.get_team_games(season, team, startdate,
enddate)
games_played = [g for g in games_played if g >= 20001 and g <= 30417]
toi = manip.get_game_h2h_toi(
season, games_played).rename(columns={'Secs': 'TOI'})
cf = manip.get_game_h2h_corsi(season, games_played,
'cf').rename(columns={'HomeCorsi': 'CF'})
ca = manip.get_game_h2h_corsi(season, games_played,
'ca').rename(columns={'HomeCorsi': 'CA'})
# TOI, CF, and CA have columns designating which team--H or R
# Use schedule to find appropriate ones to filter for
sch = schedules.get_team_schedule(season, team, startdate, enddate)
sch = helper.melt_helper(sch[['Game', 'Home', 'Road']],
id_vars='Game',
var_name='HR',
value_name='Team')
sch = sch.query('Team == {0:d}'.format(int(
team_info.team_as_id(team))))
sch.loc[:, 'HR'] = sch.HR.apply(lambda x: x[0])
sch = sch.assign(Team1=sch.HR, Team2=sch.HR).drop({'Team', 'HR'},
axis=1)
toi = toi.merge(sch, how='inner', on=['Game', 'Team1', 'Team2'])
cf = cf.merge(sch, how='inner', on=['Game', 'Team1', 'Team2'])
ca = ca.merge(sch, how='inner', on=['Game', 'Team1', 'Team2'])
# CF and CA from home perspective, so switch if necessary
cfca = cf.merge(
ca,
how='outer',
on=['Game', 'PlayerID1', 'PlayerID2', 'Team1', 'Team2'])
cfca.loc[:, 'tempcf'] = cfca.CF
cfca.loc[:, 'tempca'] = cfca.CA
cfca.loc[cf.Team1 == 'R', 'CF'] = cfca[cfca.Team1 == 'R'].tempca
cfca.loc[ca.Team1 == 'R', 'CA'] = cfca[cfca.Team1 == 'R'].tempcf
cfca = cfca.drop({'Team1', 'Team2', 'tempcf', 'tempca'}, axis=1)
toi = toi.drop({'Team1', 'Team2', 'Min'}, axis=1)
joined = toi.merge(cfca, how='outer', on=['PlayerID1', 'PlayerID2', 'Game']) \
.assign(Season=season)
dflst.append(joined)
df = pd.concat(dflst) \
.groupby(['PlayerID1', 'PlayerID2'], as_index=False).sum()
df.loc[:, 'CF60'] = df.CF * 3600 / df.TOI
df.loc[:, 'CA60'] = df.CA * 3600 / df.TOI
defensemen = players.get_player_ids_file().query('Pos == "D"')[['ID']]
df = df.merge(defensemen.rename(columns={'ID': 'PlayerID1'}), how='inner', on='PlayerID1') \
.merge(defensemen.rename(columns={'ID': 'PlayerID2'}), how='inner', on='PlayerID2')
return df