def mrscPredict(targetPlayer, allPivotedTableDict, donor, pred_interval,
metric, pred_metrics, threshold, donorSetup, denoiseSetup,
regression_method, verbose):
# create target object
target = Target(targetPlayer, allPivotedTableDict)
# create mrsc model
mrsc = mRSC(donor, target, pred_interval, probObservation=1)
# fit model
mrsc.fit_threshold(metric, threshold, donorSetup, denoiseSetup,
regression_method, verbose)
# predict model for 'pred_metric'
pred = mrsc.predict()
pred = pred[pred.index.isin(pred_metrics)]
return pred
def test():
"""
import data
"""
print("* importing data")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >=
1980] # only choose players who started after 1980
players["player_id"] = range(0, len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("* preparing data")
# transform stats to a dictionary composed of df's for each stat
# the stats are re-calculated to get one stat for each year
metricsPerGameColNames = ["PTS", "AST", "TOV", "TRB", "STL", "BLK", "3P"]
metricsPerGameDict = getMetricsPerGameDict(stats, metricsPerGameColNames)
metricsPerCentColNames = ["FG", "FT"]
metricsPerCentDict = getMetricsPerCentDict(stats, metricsPerCentColNames)
metricsWeightedColNames = ["PER"]
metricsWeightedDict = getMetricsWeightedDict(stats,
metricsWeightedColNames)
allMetricsDict = {
**metricsPerGameDict,
**metricsPerCentDict,
**metricsWeightedDict
}
allPivotedTableDict = getPivotedTableDict(allMetricsDict)
# this matrix will be used to mask the table
df_year = pd.pivot_table(stats,
values="Year",
index="Player",
columns="year_count")
"""
experiment setup
"""
activePlayers = getActivePlayers(stats, 2016, 4)
activePlayers.sort()
activePlayers.remove("Kevin Garnett")
activePlayers.remove("Kobe Bryant")
offMetrics = ["PTS_G", "AST_G", "TOV_G", "3P_G", "PER_w", "FG%", "FT%"]
defMetrics = ["TRB_G", "STL_G", "BLK_G"]
#### uniform weights
# weightsOff = [1.,1.,1.,1.,1.,1.,1.]
# weightsDef = [1.,1.,1.]
#### mean-standardized weights
# weightsOff = [0.12623068620631453, 0.55687314142618904, 0.82115849366536209, 0.080245455622805287, 2.2838580004246301, 1.4304474472757014, 4.7552939398878413]
# weightsDef = [0.28744431242409424, 1.5323016513327052, 2.4985245915220626]
#### variance-standardized weights (1/(x+1))
metrics_list = [offMetrics, defMetrics]
expSetup = ["sliding", "SVD", "all", "pinv", False]
threshold = 0.97
print("* start experiment")
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
for playerName in activePlayers:
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
weights_list = getWeitghts(target,
donor,
metrics_list,
expSetup,
method="mean")
mrsc = mRSC(donor, target, probObservation=1)
mrsc.fit_threshold(offMetrics,
weights_list[0],
2016,
pred_length=1,
threshold=threshold,
setup=expSetup)
predOff = mrsc.predict()
trueOff = mrsc.getTrue()
predOff.columns = [playerName]
trueOff.columns = [playerName]
mrsc.fit_threshold(defMetrics,
weights_list[1],
2016,
pred_length=1,
threshold=threshold,
setup=expSetup)
predDef = mrsc.predict()
trueDef = mrsc.getTrue()
predDef.columns = [playerName]
trueDef.columns = [playerName]
pred = pd.concat([predOff, predDef], axis=0)
true = pd.concat([trueOff, trueDef], axis=0)
pred_all = pd.concat([pred_all, pred], axis=1)
true_all = pd.concat([true_all, true], axis=1)
###################
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print()
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(true_all, pred_all)
print()
print(rmse)
print("RMSE for all: ", rmse.mean())
weirdo = mape.T[mape.T.PTS_G > 100].T
print()
print(weirdo)
print(weirdo.shape)
def test():
"""
import data
"""
print("* importing data")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >=
1980] # only choose players who started after 1980
players["player_id"] = range(0, len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("* preparing data")
# transform stats to a dictionary composed of df's for each stat
# the stats are re-calculated to get one stat for each year
metricsPerGameColNames = ["PTS", "AST", "TOV", "TRB", "STL", "BLK", "3P"]
metricsPerGameDict = getMetricsPerGameDict(stats, metricsPerGameColNames)
metricsPerCentColNames = ["FG", "FT"]
metricsPerCentDict = getMetricsPerCentDict(stats, metricsPerCentColNames)
metricsWeightedColNames = ["PER"]
metricsWeightedDict = getMetricsWeightedDict(stats,
metricsWeightedColNames)
allMetricsDict = {
**metricsPerGameDict,
**metricsPerCentDict,
**metricsWeightedDict
}
allPivotedTableDict = getPivotedTableDict(allMetricsDict)
allMetrics = list(allMetricsDict.keys())
# this matrix will be used to mask the table
df_year = pd.pivot_table(stats,
values="Year",
index="Player",
columns="year_count")
"""
experiment setup
"""
activePlayers = getActivePlayers(stats, 2016, 4)
activePlayers.sort()
activePlayers.remove("Kevin Garnett")
activePlayers.remove("Kobe Bryant")
# offMetrics = ["PTS_G","AST_G","TOV_G","3P_G","PER_w", "FG%","FT%"]
# defMetrics = ["TRB_G","STL_G","BLK_G"]
expSetup = ["sliding", "SVD", "all", "pinv", False]
threshold = 0.97
metrics_to_use = [
"PTS_G", "AST_G", "TOV_G", "3P_G", "PER_w", "FG%", "FT%", "TRB_G",
"STL_G", "BLK_G"
]
print("* start experiment")
print("*******************")
print("uniform weights")
weights = [1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
for playerName in activePlayers:
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
mrsc = mRSC(donor, target, probObservation=1)
mrsc.fit_threshold(metrics_to_use,
weights,
2016,
pred_length=1,
threshold=threshold,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
pred_all = pd.concat([pred_all, pred], axis=1)
true_all = pd.concat([true_all, true], axis=1)
print()
print("*** MAPE ***")
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(true_all, pred_all)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
print("*******************")
print("mean - standardized weights")
metrics_list = [metrics_to_use]
weights = getWeitghts(target, donor, metrics_list, expSetup,
method="mean")[0]
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
for playerName in activePlayers:
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
mrsc = mRSC(donor, target, probObservation=1)
mrsc.fit_threshold(metrics_to_use,
weights,
2016,
pred_length=1,
threshold=threshold,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
pred_all = pd.concat([pred_all, pred], axis=1)
true_all = pd.concat([true_all, true], axis=1)
print()
print("*** MAPE ***")
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(true_all, pred_all)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
print("*******************")
print("var - standardized weights")
metrics_list = [metrics_to_use]
weights = getWeitghts(target, donor, metrics_list, expSetup,
method="var")[0]
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
for playerName in activePlayers:
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
mrsc = mRSC(donor, target, probObservation=1)
mrsc.fit_threshold(metrics_to_use,
weights,
2016,
pred_length=1,
threshold=threshold,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
pred_all = pd.concat([pred_all, pred], axis=1)
true_all = pd.concat([true_all, true], axis=1)
print()
print("*** MAPE ***")
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(true_all, pred_all)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
def test():
"""
import data
"""
print("* importing data")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >=
1980] # only choose players who started after 1980
players["player_id"] = range(0, len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("* preparing data")
# transform stats to a dictionary composed of df's for each stat
# the stats are re-calculated to get one stat for each year
metricsPerGameColNames = ["PTS", "AST", "TOV", "TRB", "STL", "BLK", "3P"]
metricsPerGameDict = getMetricsPerGameDict(stats, metricsPerGameColNames)
metricsPerCentColNames = ["FG", "FT"]
metricsPerCentDict = getMetricsPerCentDict(stats, metricsPerCentColNames)
metricsWeightedColNames = ["PER"]
metricsWeightedDict = getMetricsWeightedDict(stats,
metricsWeightedColNames)
allMetricsDict = {
**metricsPerGameDict,
**metricsPerCentDict,
**metricsWeightedDict
}
allPivotedTableDict = getPivotedTableDict(allMetricsDict)
# this matrix will be used to mask the table
df_year = pd.pivot_table(stats,
values="Year",
index="Player",
columns="year_count")
"""
experiment setup
"""
pred_year = 2016
activePlayers = getActivePlayers(stats, pred_year, 4)
activePlayers.sort()
activePlayers.remove("Kevin Garnett")
activePlayers.remove("Kobe Bryant")
metrics1 = ["PTS_G", "PER_w"]
metrics2 = ["3P_G", "FG%", "FT%"]
metrics3 = ["TOV_G"]
metrics4 = ["TRB_G", "STL_G"]
metrics5 = ["AST_G", "BLK_G"]
metrics_list = [metrics1, metrics2, metrics3, metrics4, metrics5]
print(metrics_list)
#### uniform weights
# weightsOff = [1.,1.,1.,1.,1.,1.,1.]
# weightsDef = [1.,1.,1.]
expSetup = ["sliding", "SVD", "all", "pinv", False]
threshold = 0.97
#### position groups
group1 = [
"C", "SF", "PF", "C-PF", "PF-C", "C-SF", "SF-C", "SF-PF", "PF-SF"
]
group2 = [
"SG", "SF", "PG", "SG-SF", "SF-SG", "SF-PG", "PG-SF", "SG-PG", "PG-SF"
]
group3 = [
"SG", "SF", "PF", "SG-SF", "SF-SG", "SF-PF", "PF-SF", "SG-PF", "PF-SG"
]
print("* start experiment")
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
for playerName in activePlayers:
playerPos = stats.loc[(stats.Player == playerName) &
(stats.Year == pred_year), "Pos"].values[-1]
# print(playerPos)
if playerPos in group1:
players_in_group = stats[stats.Pos.isin(group1)].Player.unique()
# print("group 1")
elif playerPos in group2:
players_in_group = stats[stats.Pos.isin(group2)].Player.unique()
# print("group 2")
elif playerPos in group3:
players_in_group = stats[stats.Pos.isin(group2)].Player.unique()
# print("group 3")
else:
raise Exception("invalid position")
donorPivotedTableDict = filterDonor(allPivotedTableDict,
players_in_group)
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(donorPivotedTableDict, df_year)
# print("***sanitary check***")
# print("players_in_group: ", len(players_in_group))
# print("donor pool size for PTS_G", donorPivotedTableDict["PTS_G"].shape)
weights_list = getWeitghts(target,
donor,
metrics_list,
expSetup,
method="var")
mrsc = mRSC(donor, target, probObservation=1)
player_pred = pd.DataFrame()
player_true = pd.DataFrame()
for i in range(len(metrics_list)):
mrsc.fit_threshold(metrics_list[i],
weights_list[i],
pred_year,
pred_length=1,
threshold=threshold,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
player_pred = pd.concat([player_pred, pred], axis=0)
player_true = pd.concat([player_true, true], axis=0)
pred_all = pd.concat([pred_all, player_pred], axis=1)
true_all = pd.concat([true_all, player_true], axis=1)
###################
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print()
print("******* MAPE *******")
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
def test():
"""
import data
"""
pred_year = 2015 # the year that we are living in
pred_interval = 1 # we are making predictions for pred_year+1 and +2
print("*** importing data ***")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >= 1980] # only choose players who started after 1980
# players["player_id"] = range(0,len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("*** preparing data ***")
########### Donor ##########
# filter stats by the year
stats_donor = stats[stats.Year <= pred_year]
allPivotedTableDict, allMetrics = prepareData(stats_donor)
donor = Donor(allPivotedTableDict)
########### Target ##########
# filter stats by the year
stats_target = stats[stats.Year <= pred_year+pred_interval]
allPivotedTableDict, allMetrics = prepareData(stats_target)
# just to debug
df_year = pd.pivot_table(stats, values="Year", index="Player", columns = "year_count")
"""
experiment setup
"""
# overall setup
donorSetup= [None,"fixed", True]
# weighting = donorSetup[0] # None / "normalize"
# mat_form_method = donorSetup[1] # "fixed"
# skipNan = donorSetup[2] # (Boolean)
denoiseSetup = ["SVD", "all"]
# denoise_method = denoiseSetup[0] # "SVD"
# denoise_mat_method = denoiseSetup[1] # "all"
regression_method = "pinv"
threshold = 0.97
verbose = False
###################################################
offMetrics = ["PTS_G","AST_G","TOV_G","PER_w", "FG%","FT%","3P_G"]
defMetrics = ["TRB_G","STL_G","BLK_G"]
# metrics_list = [offMetrics, defMetrics]
metrics_list = [allMetrics]
###################################################
##############################################################
# test 1
##############################################################
playerNames = getActivePlayers(stats, pred_year, buffer=4)
playerNames.remove("Kevin Garnett")
playerNames.remove("Kobe Bryant")
# playerNames.remove("Jason Kidd")
all_pred = pd.DataFrame()
all_true = pd.DataFrame()
for playerName in playerNames:
# print(playerName)
# print("*** year - year_count matching for this player")
# a = df_year[df_year.index == playerName]
# print(a.dropna(axis=1))
target = Target(playerName, allPivotedTableDict)
# print("*** target - total index: ", target.total_index)
# print(target.concat(metrics_list[1]))
mrsc = mRSC(donor, target, pred_interval, probObservation=1)
player_pred = pd.DataFrame()
player_true = pd.DataFrame()
for i in range(len(metrics_list)):
mrsc.fit_threshold(metrics_list[i], pred_interval, threshold, donorSetup, denoiseSetup,regression_method, verbose)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
player_pred = pd.concat([player_pred, pred], axis=0)
player_true = pd.concat([player_true, true], axis=0)
all_pred = pd.concat([all_pred, player_pred], axis=1)
all_true = pd.concat([all_true, player_true], axis=1)
###################
print(all_pred)
print(all_pred.shape)
mask = (all_true !=0 )
mape = np.abs(all_pred - all_true) / all_true[mask]
print("*** MAPE ***")
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(all_true, all_pred)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
def test():
"""
import data
"""
print("importing data")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >=
1980] # only choose players who started after 1980
players["player_id"] = range(0, len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("preparing data")
# transform stats to a dictionary composed of df's for each stat
# the stats are re-calculated to get one stat for each year
metricsPerGameColNames = ["PTS", "AST", "TOV", "TRB", "STL", "BLK"]
metricsPerGameDict = getMetricsPerGameDict(stats, metricsPerGameColNames)
metricsPerCentColNames = ["FG", "FT", "3P"]
metricsPerCentDict = getMetricsPerCentDict(stats, metricsPerCentColNames)
metricsWeightedColNames = ["PER"]
metricsWeightedDict = getMetricsWeightedDict(stats,
metricsWeightedColNames)
allMetricsDict = {
**metricsPerGameDict,
**metricsPerCentDict,
**metricsWeightedDict
}
allPivotedTableDict = getPivotedTableDict(allMetricsDict)
# this matrix will be used to mask the table
df_year = pd.pivot_table(stats,
values="Year",
index="Player",
columns="year_count")
"""
experiment setup
"""
activePlayers = getActivePlayers(stats, 2016, 5)
activePlayers.sort()
# offMetrics = ["PTS_G","AST_G","TOV_G","PER_w", "FG%","FT%","3P%"]
# defMetrics = ["TRB_G","STL_G","BLK_G"]
metrics_to_use = [
"PTS_G", "AST_G", "TOV_G", "PER_w", "FG%", "FT%", "3P%", "TRB_G",
"STL_G", "BLK_G"
]
weights = [1., 1., 1., 1., 1., 1., 1., 1., 1., 1.]
expSetup = ["fixed", "SVD", "all", "pinv", False]
singvals_list = [1, 2, 4, 8, 16, 32]
print("start experiment")
for singvals in singvals_list:
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
for playerName in activePlayers:
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
mrsc = mRSC(donor, target, probObservation=1)
mrsc.fit(metrics_to_use,
weights,
2016,
pred_length=1,
singvals=singvals,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
pred_all = pd.concat([pred_all, pred], axis=1)
true_all = pd.concat([true_all, true], axis=1)
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print(singvals)
print(mape.mean(axis=1))
def annual_predictions(playerNames, allPivotedTableDict, donor, pred_interval, metrics, pred_metrics,
threshold, donorSetup, denoiseSetup, regression_method, verbose, dir_name, top_players):
all_pred = pd.DataFrame()
all_true = pd.DataFrame()
all_bench = pd.DataFrame()
all_R2 = pd.DataFrame()
for playerName in playerNames:
target = Target(playerName, allPivotedTableDict)
mrsc = mRSC(donor, target, pred_interval, probObservation=1)
player_pred = pd.DataFrame()
player_true = pd.DataFrame()
# benchmark
true, benchmark = getBenchmark(target, pred_metrics, pred_interval)
for metric in metrics:
mrsc.fit_threshold(metric, threshold, donorSetup, denoiseSetup,regression_method, verbose)
pred = mrsc.predict()
pred = pred[pred.index.isin(pred_metrics)]
true = mrsc.getTrue()
# # ARMA
# data = mrsc.target_data.T.ewm(com=0.5).mean().T.values.flatten()
# data = data[:-1]
# ewm = data[-1]
# # if (np.sum(data != 0)==0):
# # pred_arima = 0
# # else:
# # model = ARMA(data, order=(1, 1))
# # model_fit = model.fit(disp=False)
# # pred_arma = model_fit.predict(len(data), len(data))
# pred = 0.5*pred + 0.5*ewm
pred.columns = [playerName+" "+ str(a) for a in range(pred_interval)]
true.columns = [playerName+" "+ str(a) for a in range(pred_interval)]
player_pred = pd.concat([player_pred, pred], axis=0)
player_true = pd.concat([player_true, true], axis=0)
all_pred = pd.concat([all_pred, player_pred], axis=1)
all_true = pd.concat([all_true, player_true], axis=1)
all_bench = pd.concat([all_bench, benchmark], axis=1)
R2 = getR2(player_true, player_pred, benchmark)
all_R2 = pd.concat([all_R2, R2], axis=1)
###################
print("Number of metrics: {}".format(all_pred.shape[0]))
print("Number of players: {}".format(all_pred.shape[1]))
print()
mask = (all_true !=0 )
mape = np.abs(all_pred[mask] - all_true[mask]) / all_true[mask]
print("*** MAPE ***")
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(all_true, all_pred)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
print()
print("*** R2 ***")
print(all_R2.mean(axis=1))
print("R2 for all: ", all_R2.mean(axis=1).mean(axis=0))
edited_R2 = copy.deepcopy(all_R2)
edited_R2[edited_R2 <0] = 0
print()
print("*** edited R2 ***")
print(edited_R2.mean(axis=1))
print("R2 for all: ", edited_R2.mean().mean())
return all_pred, all_true, all_R2, all_bench
def test():
"""
import data
"""
print("* importing data")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >=
1980] # only choose players who started after 1980
players["player_id"] = range(0, len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("* preparing data")
# transform stats to a dictionary composed of df's for each stat
# the stats are re-calculated to get one stat for each year
metricsPerGameColNames = ["PTS", "AST", "TOV", "TRB", "STL", "BLK", "3P"]
metricsPerGameDict = getMetricsPerGameDict(stats, metricsPerGameColNames)
metricsPerCentColNames = ["FG", "FT"]
metricsPerCentDict = getMetricsPerCentDict(stats, metricsPerCentColNames)
metricsWeightedColNames = ["PER"]
metricsWeightedDict = getMetricsWeightedDict(stats,
metricsWeightedColNames)
allMetricsDict = {
**metricsPerGameDict,
**metricsPerCentDict,
**metricsWeightedDict
}
allPivotedTableDict = getPivotedTableDict(allMetricsDict)
allMetrics = list(allMetricsDict.keys())
# this matrix will be used to mask the table
df_year = pd.pivot_table(stats,
values="Year",
index="Player",
columns="year_count")
"""
experiment setup
"""
pred_year = 2016
# targets
activePlayers = getActivePlayers(stats, pred_year, 4)
activePlayers.sort()
activePlayers.remove("Kevin Garnett")
activePlayers.remove("Kobe Bryant")
# overall setup
expSetup = ["sliding", "SVD", "all", "pinv", False]
threshold = 0.97
###################################################
# offMetrics = ["PTS_G","AST_G","TOV_G","PER_w", "FG%","FT%","3P_G"]
# defMetrics = ["TRB_G","STL_G","BLK_G"]
# metrics_list = [offMetrics, defMetrics]
###################################################
print("* start experiment")
pred_all = pd.DataFrame()
true_all = pd.DataFrame()
metrics_all = []
with open('metrics_all.pkl', 'wb') as f:
pickle.dump(metrics_all, f, pickle.HIGHEST_PROTOCOL)
for playerName in activePlayers:
# print()
# print("***********", playerName , "************")
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
metrics_list = getMetrics(target,
donor,
pred_year,
allMetrics,
threshold,
expSetup,
boundary="threshold")
weights_list = getWeitghts(target,
donor,
metrics_list,
expSetup,
method="mean")
metrics_all.append(metrics_list)
# print(metrics_list)
mrsc = mRSC(donor, target, probObservation=1)
player_pred = pd.DataFrame()
player_true = pd.DataFrame()
for i in range(len(metrics_list)):
mrsc.fit_threshold(metrics_list[i],
weights_list[i],
pred_year,
pred_length=1,
threshold=threshold,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
c = metrics_list[i].index(allMetrics[i])
player_pred = pd.concat([player_pred, pred.iloc[c:(c + 1), :]],
axis=0)
player_true = pd.concat([player_true, true.iloc[c:(c + 1), :]],
axis=0)
pred_all = pd.concat([pred_all, player_pred], axis=1)
true_all = pd.concat([true_all, player_true], axis=1)
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
# print(mape.mean(axis=1))
###################
print("******** RESULT ********")
mask = (true_all != 0)
mape = np.abs(pred_all - true_all) / true_all[mask]
print()
print("*** MAPE ***")
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(pred_all, true_all)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
with open('metrics_all.pkl', 'wb') as f:
pickle.dump(metrics_all, f, pickle.HIGHEST_PROTOCOL)
def test():
"""
import data
"""
print("importing data")
players = pd.read_csv("../data/nba-players-stats/player_data.csv")
players = players[players.year_start >=
1980] # only choose players who started after 1980
players["player_id"] = range(0, len(players.name)) # assign id
stats = pd.read_csv("../data/nba-players-stats/Seasons_Stats.csv")
stats = stats[stats.Player.isin(players.name)]
# only after 1980
stats = stats[stats.Year >= 1980]
# without duplicated names --> to do: how to distinguish multiple player with the same name
stats = removeDuplicated(players, stats)
stats.Year = stats.Year.astype(int)
stats.year_count = stats.year_count.astype(int)
print("preparing data")
# transform stats to a dictionary composed of df's for each stat
# the stats are re-calculated to get one stat for each year
metricsPerGameColNames = ["PTS", "AST", "TOV", "TRB", "STL", "BLK", "3P"]
metricsPerGameDict = getMetricsPerGameDict(stats, metricsPerGameColNames)
metricsPerCentColNames = ["FG", "FT"]
metricsPerCentDict = getMetricsPerCentDict(stats, metricsPerCentColNames)
metricsWeightedColNames = ["PER"]
metricsWeightedDict = getMetricsWeightedDict(stats,
metricsWeightedColNames)
allMetricsDict = {
**metricsPerGameDict,
**metricsPerCentDict,
**metricsWeightedDict
}
allPivotedTableDict = getPivotedTableDict(allMetricsDict)
allMetrics = list(allMetricsDict.keys())
# this matrix will be used to mask the table
df_year = pd.pivot_table(stats,
values="Year",
index="Player",
columns="year_count")
"""
experiment setup
"""
# overall setup
expSetup = ["sliding", "SVD", "all", "pinv", False]
threshold = 0.97
metrics1 = ["PTS_G", "PER_w", "TRB_G", "3P_G"]
metrics2 = ["FG%", "FT%"]
metrics3 = ["BLK_G", "AST_G", "TOV_G", "STL_G"]
metrics_list = [metrics1, metrics2, metrics3]
###################################################
# offMetrics = ["PTS_G","AST_G","TOV_G","PER_w", "FG%","FT%","3P%"]
# defMetrics = ["TRB_G","STL_G","BLK_G"]
# metrics_list = [offMetrics, defMetrics]
###################################################
playerName = "Ryan Anderson"
target = Target(playerName, allPivotedTableDict, df_year)
donor = Donor(allPivotedTableDict, df_year)
weights_list = getWeitghts(target,
donor,
metrics_list,
expSetup,
method="var")
mrsc = mRSC(donor, target, probObservation=1)
fig, axs = plt.subplots(3, 5)
player_pred = pd.DataFrame()
player_true = pd.DataFrame()
for i in range(len(metrics_list)):
mrsc.fit_threshold(metrics_list[i],
weights_list[i],
2016,
pred_length=1,
threshold=threshold,
setup=expSetup)
pred = mrsc.predict()
true = mrsc.getTrue()
pred.columns = [playerName]
true.columns = [playerName]
player_pred = pd.concat([player_pred, pred], axis=0)
player_true = pd.concat([player_true, true], axis=0)
# mrsc.plot()
for j in range(len(metrics_list[i])):
metric = metrics_list[i][j]
true_trajectory = target.data[metric].dropna(
axis='columns').iloc[:, :mrsc.total_index]
pred_val = np.dot(
mrsc.model.donor_data.iloc[:, j * mrsc.model.total_index:(
(j + 1) * mrsc.model.total_index)].T, mrsc.model.beta).T
pred_trajectory = pd.DataFrame(pred_val,
columns=true_trajectory.columns,
index=true_trajectory.index)
markers_on = [true_trajectory.shape[1] - 1]
axs[i, j].plot(true_trajectory.T,
marker='o',
color='red',
label='true')
axs[i, j].plot(pred_trajectory.T,
marker='o',
markevery=markers_on,
color='blue',
label='prediction')
axs[i, j].set_title(playerName + ": " + metric)
# axs[i, j].legend()
for ax in axs.flat:
ax.set(xlabel='years played in NBA')
plt.subplots_adjust(wspace=0.5, hspace=0.5)
plt.show()
###################
mask = (player_true != 0)
mape = np.abs(player_pred - player_true) / player_true[mask]
print("*** MAPE ***")
print(mape.mean(axis=1))
print("MAPE for all: ", mape.mean().mean())
rmse = utils.rmse_2d(player_true, player_pred)
print()
print("*** RMSE ***")
print(rmse)
print("RMSE for all: ", rmse.mean())
