def rate_for_games(self, stacked, unstacked):
"""
:param games:
:return:
"""
self.teams = util.get_teams(unstacked)
self._initialize(self.teams)
cols = {name: idx for idx, name in enumerate(stacked.columns)}
for k, row in enumerate(stacked.values):
hteam_id = row[cols['hteam_id']]
ateam_id = row[cols['ateam_id']]
# update winning percentages for teams that don't exist in database
if np.isnan(row[cols['hteam_id']]) or np.isnan(row[cols['ateam_id']]):
if not self.ignore_nan_teams:
self.update_wp(self.team_index[hteam_id], self.team_index[ateam_id])
continue
i, j = self.team_index[hteam_id], self.team_index[ateam_id]
self.update_wins(i, j, row[cols['home_outcome']], row[cols['neutral']])
self.update_played(i, j, row[cols['neutral']])
['UConn', 82, 'Duke', 68],
['Minnesota', 71, 'UConn', 72],
['Kansas', 69, 'UConn', 62],
['Duke', 81, 'Minnesota', 70],
['Minnesota', 52, 'Kansas', 62]]
df = pd.DataFrame(data, columns=['hteam', 'hscore', 'ateam', 'ascore'])
df['home_outcome'] = df.hscore > df.ascore
df['neutral'] = False
df['hteam_id'] = df.hteam.map(lambda x: team_ids.get(x))
df['ateam_id'] = df.ateam.map(lambda x: team_ids.get(x))
return df
if __name__ == "__main__":
# df = rpi_test_data()
games = util.get_games(date(2015, 3, 15))
d1 = pd.read_sql("SELECT * FROM division_one WHERE year=2015", DB.conn)
games = games.merge(d1, left_on='hteam_id', right_on='ncaaid')
games = games.merge(d1, left_on='ateam_id', right_on='ncaaid')
teams = util.get_teams(games)
data = games[['hteam_id', 'ateam_id', 'home_outcome', 'neutral']].values
agg = RPIAggregator(teams)
map(lambda x: agg.update(x), data)
ratings = agg.evaluate()
teams['rpi'] = ratings[0]
teams['sos'] = ratings[1]
teams['w'] = agg.total_won
teams['l'] = agg.total_played - agg.total_won
all_teams = pd.read_sql("SELECT ncaa, ncaaid FROM teams", DB.conn)
df = teams.merge(all_teams, left_on="team_id", right_on="ncaaid")
import csv
import player
import util
from operator import itemgetter
# import read_schedule
path = "../excel/BBM_PlayerRankings"
'''
get zscores
'''
path = "../excel/players.csv"
teams_abbrevs = util.get_teams()
players = []
names = set()
'''
Returns a list of players specified by a list of names
'''
def find_players(names):
with open(path, "rb") as f:
reader = csv.reader(f, delimiter="\t")
for i, line in enumerate(reader):
line = line[0]
number, name, position, age, team, games, games_started, minutes, fgm, \
fga, fgp, threepm, threepa, threepp, twopm, twopa, twopp, \
effective_fgp, ftm, fta, ftp, oreb, drb, trb, ast, stl, blk, tov, \
pf, pts = line.split(',')
