def update_player_last_totals(last_range):
print(f"Fetching player stat totals for last {last_range}...")
current_season = get_current_season_full()
date_from = get_date_from_last_range(last_range)
stats_response = leaguedashplayerstats.LeagueDashPlayerStats(
season=current_season, date_from_nullable=date_from)
primary_keys = ["PLAYER_NAME"]
update_data_table_from_stats_response(f"player_last_{last_range}_totals",
stats_response, primary_keys)
def update_player_season(season):
full_season = format_season(season)
print(f"Fetching player stat totals for {full_season}...")
totals_response = leaguedashplayerstats.LeagueDashPlayerStats(
season=full_season)
print(f"Fetching player stats per 100 for {full_season}...")
per_100_response = leaguedashplayerstats.LeagueDashPlayerStats(
season=full_season, per_mode_detailed="Per100Possessions")
primary_keys = ["SEASON", "PLAYER_NAME"]
extra_values = [("SEASON", full_season)]
update_data_table_from_stats_response("player_seasons_totals",
totals_response, primary_keys,
extra_values)
update_data_table_from_stats_response("player_seasons_per_100",
per_100_response, primary_keys,
extra_values)
def by_season(year, debug=False, games_thresh=0, headers=None):
'''
given a year, gets all players in a dataframe
args:
`year`: str: year, like `2019-20`
`debug`: bool: if we want to print out dataframe
`games_thresh`: int: take out players who player <= `games_thresh` games
'''
# given the year, gets all of the players in 1 call
p = leaguedashplayerstats.LeagueDashPlayerStats(
per_mode_detailed='PerGame', season='2019-20', headers=headers)
data = p.league_dash_player_stats.data['data']
# all the columns we want for clustering
columns = np.array([
'PlayerID', 'GP', 'PTS', 'AST', 'REB', 'STL', 'BLK', 'TOV', 'FT_PCT',
'FG_PCT', 'FG3_PCT', 'FTA', 'FGA', 'FG3A', 'MIN', 'PLUS_MINUS'
])
r = len(data)
c = len(columns)
# store players into matrix with r players (rows) and c columns
players_arr = np.zeros((r, c))
# non-empty data
if data != []:
# these are the indices that are used for the columns, this is what stats.nba.com decided
num = np.array(
[0, 5, 29, 22, 21, 24, 25, 23, 18, 12, 15, 17, 11, 14, 9, 30])
for i, player in enumerate(data):
try:
# print if player's name
name = players.find_player_by_id(player[0])['full_name']
print(f'{name} found.')
except:
# name not found
print('Player name not found')
for j, n in enumerate(num):
# populate matrix with data
players_arr[i, j] = player[n]
# convert matrix and cols to df to store in csv on disk
df = pd.DataFrame(players_arr, columns=columns)
to_int = ['PlayerID', 'GP']
# only columns that need to be int
df[to_int] = df[to_int].astype(int)
df_filtered = df[df['GP'] > games_thresh]
if debug:
print(df_filtered)
# also export to csv, so you only have to run it once.
df_filtered.to_csv(f'data/{year}_nba_players.csv')
return df_filtered
def get_columns_for_measure_type(measure_type):
player_stats = leaguedashplayerstats.LeagueDashPlayerStats(
last_n_games=0,
season='2018-19',
measure_type_detailed_defense=measure_type,
month=0,
opponent_team_id=0,
period=0,
date_from_nullable='2018-02-01',
date_to_nullable='2018-02-01')
return player_stats.get_dict()['resultSets'][0]['headers']
def main():
# Get current NBA season
full_season = get_current_season_full()
# Fetch current season stats (totals and per 100)
stats = leaguedashplayerstats.LeagueDashPlayerStats(season=full_season)
stats_totals = stats.get_normalized_dict()["LeagueDashPlayerStats"]
stats = leaguedashplayerstats.LeagueDashPlayerStats(
season=full_season, per_mode_detailed="Per100Possessions")
stats_per_100 = stats.get_normalized_dict()["LeagueDashPlayerStats"]
# Calculate scoring rating for each player
for player_season_totals, player_season_per_100 in zip(
stats_totals, stats_per_100):
inject_scoring_rating(player_season_totals, player_season_per_100)
# Sort players by scoring rating
player_seasons_by_scoring_rtg = order_by(stats_totals, ["-SCORING_RATING"])
# Output data
print_stats(player_seasons_by_scoring_rtg)
def get_ra_fga_percentchange():
centers = leaguedashplayerstats.LeagueDashPlayerStats(
player_position_abbreviation_nullable="C")
teams = teams.get_teams()
# really just centers who play more than an mpg limit
# mpg is calculated here as min / gp
starting_centers = [
center for center in centers.data_sets[0].data['data']
if center[9] / center[5] > MINUTES_THRESHOLD
]
result = {}
# iterate through every combination of starting center and opposing team
for center in starting_centers:
percent_change_sum = 0
for team in teams:
# ignore matchup if center is facing own team (sanity check)
if not team['id'] is center[2]:
matchup_stats = teamvsplayer.TeamVsPlayer(
center[0], team['id'])
#check if there were games played / is data
if len(matchup_stats.shot_area_on_court.data['data']) == 0:
continue
games_played = matchup_stats.overall.data['data'][0][4]
games_played_matchup = matchup_stats.on_off_court.data['data'][
0][7]
fga = matchup_stats.overall.data['data'][0][10] / games_played
fga_oncourt = matchup_stats.on_off_court.data['data'][0][
13] / games_played_matchup
ra_fga = matchup_stats.shot_area_overall.data['data'][0][
6] / games_played
ra_fga_oncourt = matchup_stats.shot_area_on_court.data['data'][
0][9] / games_played_matchup
# percent change of porportion of field goals attempted in
# restricted area with center on the court
percent_change = ((ra_fga_oncourt / fga_oncourt) -
(ra_fga / fga)) / (ra_fga / fga)
percent_change_sum += percent_change
average_rim_intimidation = percent_change_sum / len(teams)
result[center[1]] = average_rim_intimidation
return result
def get_player_stats_df(
date_from='2018-10-16',
date_to=(date.today() - timedelta(1)).strftime('%Y-%m-%d'),
team=0,
opp_team=0,
division=DivisionNullable.default,
vs_division=DivisionNullable.default,
conference=ConferenceNullable.default,
vs_conference=ConferenceNullable.default,
period=0,
game_segment=GameSegmentNullable.default,
home_away=LocationNullable.default,
outcome=OutcomeNullable.default,
player_position=PlayerPositionAbbreviationNullable.default,
player_experience=PlayerExperienceNullable.default,
starter_bench=StarterBenchNullable.default,
shot_clock_range=ShotClockRangeNullable.default):
# Convert team name inputs to ID lists, if applicable
if opp_team != 0:
opp_team = [team_full_name_to_id(tm) for tm in opp_team]
if team != 0:
team = [team_full_name_to_id(tm) for tm in team]
player_stats = leaguedashplayerstats.LeagueDashPlayerStats(
last_n_games=0,
season='2018-19',
measure_type_detailed_defense='Base',
month=0,
opponent_team_id=opp_team,
period=period,
date_from_nullable=date_from,
date_to_nullable=date_to,
team_id_nullable=team,
division_simple_nullable=division,
vs_division_nullable=vs_division,
conference_nullable=conference,
vs_conference_nullable=vs_conference,
game_segment_nullable=game_segment,
location_nullable=home_away,
outcome_nullable=outcome,
player_position_abbreviation_nullable=player_position,
player_experience_nullable=player_experience,
starter_bench_nullable=starter_bench,
shot_clock_range_nullable=shot_clock_range)
header = player_stats.get_dict()['resultSets'][0]['headers']
data = player_stats.get_dict()['resultSets'][0]['rowSet']
return pd.DataFrame(data=data, columns=header)
def _mode_average_stats(self) -> pd.DataFrame:
all_players = leaguedashplayerstats.LeagueDashPlayerStats(last_n_games=self._last_n_games)
all_players = all_players.get_data_frames()[0]
all_players.loc[:, ['PTS', 'REB', 'AST', 'TOV', 'STL', 'BLK']] = (
all_players.loc[:, ['PTS', 'REB', 'AST', 'TOV', 'STL', 'BLK']].div(all_players.GP, axis=0)
)
all_players = all_players.loc[:, ['PLAYER_NAME', 'GP', 'PTS', 'REB', 'AST', 'TOV', 'STL', 'BLK']]
all_players = all_players[all_players.GP > 1].reset_index(drop=True)
all_players['SCR'] = (
all_players['PTS']
+ all_players['REB'] * 1.2
+ all_players['AST'] * 1.5
+ all_players['STL'] * 3
+ all_players['BLK'] * 3
- all_players['TOV']
)
return all_players.round(2)
def get_advanced_stats():
try:
advanced_stats = leaguedashplayerstats.LeagueDashPlayerStats(
team_id_nullable=miami_heat_team_id,
last_n_games=0,
measure_type_detailed_defense='Advanced',
month=0,
opponent_team_id=0,
pace_adjust='N',
per_mode_detailed='PerGame',
period=0,
plus_minus='Y',
rank='Y',
season='2018-19',
season_type_all_star='Regular Season',
)
advanced_stats = advanced_stats.get_dict()
return processnbadict(advanced_stats['resultSets'][0]) #array []
except Exception as e:
return str(e)
def run():
#players = leaguedashplayerstats.LeagueDashPlayerStats(season='2020-21',per_mode_detailed="PerGame",season_type_all_star="Regular Season")
players = leaguedashplayerstats.LeagueDashPlayerStats(
season='2020-21',
per_mode_detailed="PerGame",
season_type_all_star="Regular Season",
player_position_abbreviation_nullable="C")
players = players.get_data_frames()[0]
for i, j in players.iterrows():
print(j.PLAYER_NAME)
"""
g = Game(week = row[0], vteam = row[1], hteam = row[2], temp = row[7], wind_mph = row[8], vdflg = row[9], hdflg = row[10], divgame = row[11], nsite = row[12], hospread = row[14], ouopen = row[15], hcspread = row[17], ouclose= row[18], vTOTALDVOA= row[19], vTOTALRNK= row[20], vOFFRNK= row[21], vOFFDVOA= row[22], vDEFRNK= row[23], vDEFDVOA= row[24], vSTRNK= row[25], vSTDVOA= row[26], hTOTALDVOA= row[27], hTOTALRNK= row[28], hOFFRNK= row[29], hOFFDVOA= row[30], hDEFRNK= row[31], hDEFDVOA= row[32], hSTRNK= row[33], hSTDVOA= row[34], vtsw= row[35], vtsl= row[36], vtst= row[37], htsw= row[38], htsl= row[39], htst= row[40], vtw= row[41], vtl= row[42], vtt= row[43], vts= row[44], htw= row[45], htl= row[46], htt= row[47], hts= row[48])
g.save()
p = Player(PLAYER_ID = j.PLAYER_ID,Player_Name=j.PLAYER_NAME, Team_ID=j.TEAM_ID, Team_Name=j.TEAM_ABBREVIATION, GP=j.GP, MIN=j.MIN, FGM=j.FGM, FGA=j.FGA, FG_PCT=j.FG_PCT, FG3M=j.FG3M, FG3A=j.FG3A, FG3_PCT=j.FG3_PCT, FTM=j.FTM, FTA=j.FTA, FT_PCT=j.FT_PCT, OREB=j.OREB, DREB=j.DREB, REB=j.REB, AST=j.AST, STL=j.STL, BLK=j.BLK, TOV=j.TOV, PF=j.PF, PTS=j.PTS)
obj, created = Player.objects.update_or_create(
Player_Name=j.PLAYER_NAME,
defaults={'PLAYER_ID' : j.PLAYER_ID, 'Team_ID':j.TEAM_ID, 'Team_Name':j.TEAM_ABBREVIATION, 'GP':j.GP, 'MIN':j.MIN, 'FGM':j.FGM, 'FGA':j.FGA, 'FG_PCT':j.FG_PCT, 'FG3M':j.FG3M, 'FG3A':j.FG3A, 'FG3_PCT':j.FG3_PCT, 'FTM':j.FTM, 'FTA':j.FTA, 'FT_PCT':j.FT_PCT, 'OREB':j.OREB, 'DREB':j.DREB, 'REB':j.REB, 'AST':j.AST, 'STL':j.STL, 'BLK':j.BLK, 'TOV':j.TOV, 'PF':j.PF, 'PTS':j.PTS},
)
try:
p = Player.objects.get(PLAYER_ID = j.PLAYER_ID)
except Player.DoesNotExist:
p = False
"""
try:
p = Player.objects.get(PLAYER_ID=j.PLAYER_ID)
except Player.DoesNotExist:
p = False
if p:
p.Pos.add(Positions.objects.get(id=3))
p.save()
teams = []
for teamNum in range(30):
teams.append(teams_dict["data"][teamNum])
#get rosters
rosters = []
for team in teams:
time.sleep(1)
rosters_dict = commonteamroster.CommonTeamRoster(season="2018-19",
team_id=team[1])
rosters_dict = rosters_dict.common_team_roster.get_dict()
rosters.append(rosters_dict["data"])
#get playerstats
leaguestats = leaguedashplayerstats.LeagueDashPlayerStats(
per_mode_detailed="PerGame", season="2018-19")
leaguestats = leaguestats.league_dash_player_stats.get_dict()
leaguestats = leaguestats["data"]
leaguestats.sort(key=lambda x: x[0])
leaguestats_length = len(leaguestats) - 1
sql = "CREATE TABLE IF NOT EXISTS playergamelog (seasonid INT, playerid INT, gameid INT, gamedate DATE, matchup VARCHAR(255), win VARCHAR(255),min INT,"
sql += "fgm INT, fga INT, fg_pct DECIMAL(4,3), fg3m INT, fg3a INT, fg3_pct DECIMAL(4,3), ftm INT, fta INT, ft_pct DECIMAL(4,3), oreb INt, dreb INT, reb INT,"
sql += "ast INT, stl INT, blk INT, tov INT, pf INT, pts INT, plusminus INT, PRIMARY KEY (playerid, gamedate))"
cursor.execute(sql)
for player in leaguestats:
player_stats = playergamelog.PlayerGameLog(player_id=player[0],
season="2018-19")
time.sleep(2)
player_stats = player_stats.player_game_log.get_data_frame()
return teams.find_teams_by_full_name(team_full_name)[0]['id']
"""==================================================================================================================
# Determine list utlization by endpoint
=================================================================================================================="""
team_list = ['Philadelphia 76ers', 'Toronto Raptors']
team_id_list = [team_full_name_to_id(tm) for tm in team_list]
team_id_list
player_stats = leaguedashplayerstats.LeagueDashPlayerStats(
last_n_games=0,
season='2018-19',
measure_type_detailed_defense='Base',
month=0,
opponent_team_id=0,
period=0,
date_from_nullable='2019-01-01',
date_to_nullable='2019-01-31',
team_id_nullable=team_id_list)
header = player_stats.get_dict()['resultSets'][0]['headers']
data = player_stats.get_dict()['resultSets'][0]['rowSet']
pd.DataFrame(data=data, columns=header).sample(10)
# Looks like if list is passed, only first value passed gets pulled from endpoint
"""==================================================================================================================
# Create UDF that returns data given dimensions (to be made available in dashboard)
=================================================================================================================="""
from datetime import date, timedelta
yesterday = (date.today() - timedelta(1)).strftime('%Y-%m-%d')
print(yesterday)
def players_stats_from(end_yr):
return leaguedashplayerstats.LeagueDashPlayerStats(
measure_type_detailed_defense='Advanced',
season=format_year(end_yr)).get_data_frames()[0]
