def sim_scheduled_games(sch_game_dicts, n):
"""
"""
# print sch_game_dicts.keys()
# print
prediction_dict = {}
CandP = CombosAndPermuts()
trifs = CandP.get_trifectas()
str_trifs = [str(x[0]) + str(x[1]) + str(x[2]) for x in trifs]
#[x for x in range(1, self.numPlayers +1)]
win = [x[0] for x in trifs] ; place = [x[1] for x in trifs] ; show = [x[2] for x in trifs]
wpsTable = pd.DataFrame(data = {'First':win,'Second':place, 'Third':show}, index = str_trifs)
#print wpsTable.head()
#print wpsTable.columns.values.tolist()
for game_name,game_data in sch_game_dicts.items():
pwin_dict = rds.get_pwin_dict()
point_percentage_data = None
player_list = []
enh_player_list = []
#print game
# for el in game:
# print el
enh_player_list = get_enhanced_player_list(game_data)
#print game_name, enh_player_list
if enh_player_list != None:
#print
#print game_name
for player_dict in enh_player_list:
player_list.append(':'.join(ut.sorted_and_lowered(player_dict['name'])))
# point_percentage_data = sc.runGame_get_WPS_frequencies(player_list, n)
point_percentage_data = sc.runGame_get_WPS_frequencies(player_list, pwin_dict, n)
prediction_dict[game_name] = point_percentage_data
pred_dict_df = pd.DataFrame.from_dict(prediction_dict)
#print pred_dict_df.head()
full_df = pd.merge(wpsTable, pred_dict_df, left_index = True, right_index = True )
#print full_df.head()
#print prediction_dict
fh.write_dict(fh.prediction_dict_file_path,prediction_dict)
for game_name in sch_game_dicts.keys():
try:
# if game_name in full_df.colnames(full_df):
full_df[game_name] = full_df[game_name]/n
except:
pass
#print full_df.columns.values.tolist()
return full_df, prediction_dict
def get_enhanced_player_list(sch_game_dict):
"""
Accepts a scheduled game dictionary such as:
{'ma-01-01-1998_sch_Milford_1':{1: ['Ara', 'Arruti'], 2: ['Douglas', 'Edward'], 3: ['Liam', 'Fitz'], 4: ['Tino', 'Aritz'], 'S/D': 'Doubles', 6: ['Aitor', 'Sergio'], 7: ['Zarandona', 'Wayne'], 8: ['Eggy', 'Richard'], 'GAME': 1, 'DATE': '01/01/1998', 5: ['Aja', 'Alberto'], 'POS-SUB': [52, 11], 6: ['Altuna', 'Guisasola'], 'POINTS': 7, 'DAY': 'Thursday', 'GAME-COUNT': 15, 'POS-4-ID': [36, 17], 'POS-8-ID': [2, 12], 'POS-SUB-ID': [15, 18], 'POS-3-ID': [6, 9], 'POS-7-ID': [38, 20], 'FRONTON': 'Milford', 'POS-5-ID': [34, 13], 'ABSOLUTE-DATE': 35795, 'POS-2-ID': [42, 37], 'POS-1-ID': [4, 28]}}
Looks up the probability of winning and returns a player list formatted like:
playerList = [{'name':['Ara', 'Arruti'],'pwin': 0.56}, {'name':['Douglas', 'Edward'],'pwin': 0.65}, {'name':['Liam', 'Fitz'],'pwin': 0.63}] where position [0] represents start post 1 through to start post # 8
If any player in the scheduled game does not have a probability of winning associated with him then returns None
"""
#print sch_game_dict
real_player_list = []
player_dict = {}
temp_list = []
#print sch_game_dict[sch_game_dict.keys()[0]].get(3) #[sch_game_dict.keys()]
# Some games have 6 players
# Get the names in post position order
# for n in range(1,14):
# if sch_game_dict[sch_game_dict.keys()[0]].get(n) != None:
# temp_list.append(sch_game_dict[sch_game_dict.keys()[0]].get(n))
for n in range(1,14):
#print sch_game_dict.keys()
if sch_game_dict.get(n) != None:
temp_list.append(sch_game_dict.get(n))
#print temp_list
pwin_dict = rds.get_pwin_dict()
#print pwin_dict.keys()
for pos,player in enumerate(temp_list):
player_dict = {}
# break out this comparison as a function
#print player,':'.join(ut.sorted_and_lowered(player)),
if ':'.join(ut.sorted_and_lowered(player)) in pwin_dict.keys():
#print 'in'#,':'.join(ut.sorted_and_lowered(player))
if pwin_dict.get(':'.join(ut.sorted_and_lowered(player))) != None:
player_dict['name'] = player ; player_dict['pwin'] = pwin_dict.get(':'.join(ut.sorted_and_lowered(player)))
real_player_list.append(player_dict)
# If there is no probability of winning for any player
# return None
else:
return None
#print real_player_list
return real_player_list
def simulate_scheduled_games_freq(sch_game_dicts, n = 12):
"""
"""
prediction_dict = {}
for game_name,game_data in sch_game_dicts.items():
pwin_dict = rds.get_pwin_dict()
point_percentage_data = None
player_list = []
enh_player_list = []
#print game
# for el in game:
# print el
enh_player_list = get_enhanced_player_list(game_data)
#print enh_player_list
if enh_player_list != None:
#print
#print game_name
for player_dict in enh_player_list:
player_list.append(':'.join(ut.sorted_and_lowered(player_dict['name'])))
# point_percentage_data = sc.runGame_get_WPS_frequencies(player_list, n)
point_percentage_data = sc.runGame_get_WPS_frequencies(player_list, pwin_dict, n)
prediction_dict[game_name] = point_percentage_data
#print prediction_dict
fh.write_dict(fh.prediction_dict_file_path,prediction_dict)
return prediction_dict
def run_correlations():
start_time = time.time()
dir_list = []
for i in range(1,15):
for j in range(1,5):
dir_list.append(('correl_' + str(i) + 'm', 'correl_' + str(j)+ 'w'))
#print dir_list
dir_list = [('correl_1m', 'correl_1w'),('correl_6m', 'correl_1w'),('correl_14m', 'correl_1w')]
dir_list = [('correl_1m', 'correl_1w'),('correl_1m', 'correl_2w')]
thresholds = [20,40,60,80,100,120,140,160,180,200,220,240, 260, 280, 300, 350, 400, 500]
thresholds = [100, 500]
low_threshold = 20
results_dir = {}
for dir_pair in dir_list:
for threshold in thresholds:
rds.DATA_DIR = dir_pair[0]
fh.set_up_paths(rds.DATA_DIR)
clear_dir(fh.data_summaries_path)
rds.PWIN_DICT_POINTS_PLAYED_THRESHOLD = threshold
pwin_dict_1 = rds.get_pwin_dict()
rds.DATA_DIR = dir_pair[1]
fh.set_up_paths(rds.DATA_DIR)
clear_dir(fh.data_summaries_path)
rds.PWIN_DICT_POINTS_PLAYED_THRESHOLD = low_threshold
pwin_dict_2 = rds.get_pwin_dict()
pwin_dict_3 = dict((pwin_dict_1[key], pwin_dict_2[key]) for key in pwin_dict_1 if key in pwin_dict_2)
#print pwin_dict_3
x = np.array(pwin_dict_3.keys())
y = np.array(pwin_dict_3.values())
# correlation1 = np.corrcoef(x,y)
# print correlation1
# print pearson_def(x, y)
# print pearsonr(x, y)
if len(x) < 5:
res = (0, 0)
else:
res = pearsonr(x, y)
num = len(x)
results_dir[str(dir_pair[0]) + '_' + dir_pair[1] +'_' + str(threshold)] = [res[0], res[1], num, threshold, dir_pair[0].split('_')[1], dir_pair[1].split('_')[1]]
#print [str(dir_pair[0]) + '_' + dir_pair[1] +'_' + str(threshold)], results_dir[str(dir_pair[0]) + '_' + dir_pair[1] +'_' + str(threshold)]
#print
# for k,v in results_dir.items():
# print k, v
df = pd.DataFrame(results_dir)
df = df.transpose()
#curr_path = os.path.dirname(os.path.realpath(__file__))
curr_path = os.path.split(os.path.dirname(os.path.realpath(__file__)))[0]
fh.write_dict(os.path.join(curr_path, 'jaialai','analysis','corr_result.txt'),results_dir)
#print df
df.columns = ['corr', 'p value', 'number players', 'threshold', 'before', 'after']
df.to_excel(os.path.join(curr_path, 'jaialai','analysis','corr_result.xls'))
print "To complete %.0f correlations took %.2f minutes " %(len(results_dir),(time.time() - start_time)/60)
