def get_GA_nums(schedule_data, individual,
team_data1, team_data2, team_cols1, team_cols2,
player_data1, player_data2, player_cols1, player_cols2, health_data):
num_games_loop = len(schedule_data)
print('Num games to predict: ' + str(num_games_loop))
home_ga_nums = []
visitor_ga_nums = []
home_pts = []
visitor_pts = []
for i in range(num_games_loop):
team_home = schedule_data.loc[i, 'home']
team_visitor = schedule_data.loc[i, 'visitor']
game_date = schedule_data.loc[i, 'date']
[team_nums_home1] = np.array(team_data1[team_data1['team'] == team_home])
[team_nums_home2] = np.array(team_data2[team_data2['team'] == team_home])
[team_nums_visitor1] = np.array(team_data1[team_data1['team'] == team_visitor])
[team_nums_visitor2] = np.array(team_data2[team_data2['team'] == team_visitor])
team_nums_home = np.hstack((team_nums_home1[team_cols1], team_nums_home2[team_cols2]))
team_nums_visitor = np.hstack((team_nums_visitor1[team_cols1], team_nums_visitor2[team_cols2]))
player_nums_home1 = np.array(player_data1[player_data1['team'] == team_home])
player_nums_home2 = np.array(player_data2[player_data2['team'] == team_home])
player_nums_visitor1 = np.array(player_data1[player_data1['team'] == team_visitor])
player_nums_visitor2 = np.array(player_data2[player_data2['team'] == team_visitor])
player_nums_home = np.hstack((player_nums_home1[:,player_cols1], player_nums_home2[:,player_cols2]))
player_nums_visitor = np.hstack((player_nums_visitor1[:,player_cols1], player_nums_visitor2[:,player_cols2]))
schedule_stats_home = GA_Funs.get_schedule_stats(schedule_data, schedule_data,
game_date, team_home, future_logical=False)
schedule_stats_visitor = GA_Funs.get_schedule_stats(schedule_data, schedule_data,
game_date, team_visitor, future_logical=False)
player_indices = range(len(player_cols1) + len(player_cols2))
team_indices = range(len(player_indices), len(team_cols1) + len(team_cols2) + len(player_indices))
schedule_indices = range(len(team_indices) + len(player_indices), len(individual))
health_mod_home = []
for x in player_data1['name'][player_data1['team'] == team_home]:
if x in list(health_data['name']):
health_mod_home.extend(health_data.loc[health_data['name']==x,'health_mod'])
else:
health_mod_home.extend([1.0])
health_mod_visitor = []
for x in player_data1['name'][player_data1['team'] == team_visitor]:
if x in list(health_data['name']):
health_mod_visitor.extend(health_data.loc[health_data['name']==x,'health_mod'])
else:
health_mod_visitor.extend([1.0])
home_num = np.mean(np.array(player_nums_home).dot(individual[player_indices]) * health_mod_home) + \
np.array(team_nums_home).dot(individual[team_indices]) + \
np.array(schedule_stats_home).dot(individual[schedule_indices])
visitor_num = np.mean(np.array(player_nums_visitor).dot(individual[player_indices]) * health_mod_visitor) + \
np.array(team_nums_visitor).dot(individual[team_indices]) + \
np.array(schedule_stats_visitor).dot(individual[schedule_indices])
home_ga_nums.extend([home_num])
visitor_ga_nums.extend([visitor_num])
home_pts.extend([schedule_data.loc[i, 'home_pts']])
visitor_pts.extend([schedule_data.loc[i, 'visitor_pts']])
point_num_data = pd.DataFrame({'home_score': home_pts, 'visitor_score': visitor_pts,
'home_ga_num': home_ga_nums, 'visitor_ga_num': visitor_ga_nums})
return point_num_data
def get_prediction(schedule_data, historic_schedule, individual, days_predict,
team_data1, team_data2, team_cols1, team_cols2,
player_data1, player_data2, player_cols1, player_cols2,
health_data, slope, intercept):
# future_schedule
predict_schedule = schedule_data[(schedule_data['days_ago'] <= 0) & (schedule_data['days_ago'] >= -days_predict)]
num_games_loop = len(predict_schedule)
print('Num games to predict: ' + str(num_games_loop))
pred_winner_list = []
home_score_pred = []
visitor_score_pred = []
for i in range(num_games_loop):
team_home = predict_schedule.loc[i, 'home']
team_visitor = predict_schedule.loc[i, 'visitor']
game_date = predict_schedule.loc[i, 'date']
[team_nums_home1] = np.array(team_data1[team_data1['team'] == team_home])
[team_nums_home2] = np.array(team_data2[team_data2['team'] == team_home])
[team_nums_visitor1] = np.array(team_data1[team_data1['team'] == team_visitor])
[team_nums_visitor2] = np.array(team_data2[team_data2['team'] == team_visitor])
team_nums_home = np.hstack((team_nums_home1[team_cols1], team_nums_home2[team_cols2]))
team_nums_visitor = np.hstack((team_nums_visitor1[team_cols1], team_nums_visitor2[team_cols2]))
player_nums_home1 = np.array(player_data1[player_data1['team'] == team_home])
player_nums_home2 = np.array(player_data2[player_data2['team'] == team_home])
player_nums_visitor1 = np.array(player_data1[player_data1['team'] == team_visitor])
player_nums_visitor2 = np.array(player_data2[player_data2['team'] == team_visitor])
player_nums_home = np.hstack((player_nums_home1[:,player_cols1], player_nums_home2[:,player_cols2]))
player_nums_visitor = np.hstack((player_nums_visitor1[:,player_cols1], player_nums_visitor2[:,player_cols2]))
schedule_stats_home = GA_Funs.get_schedule_stats(predict_schedule, historic_schedule,
game_date, team_home, future_logical=True)
schedule_stats_visitor = GA_Funs.get_schedule_stats(predict_schedule, historic_schedule,
game_date, team_visitor, future_logical=True)
player_indices = range(len(player_cols1) + len(player_cols2))
team_indices = range(len(player_indices), len(team_cols1) + len(team_cols2) + len(player_indices))
schedule_indices = range(len(team_indices) + len(player_indices), len(individual))
health_mod_home = []
for x in player_data1['name'][player_data1['team'] == team_home]:
if x in list(health_data['name']):
health_mod_home.extend(health_data.loc[health_data['name']==x,'health_mod'])
else:
health_mod_home.extend([1.0])
health_mod_visitor = []
for x in player_data1['name'][player_data1['team'] == team_visitor]:
if x in list(health_data['name']):
health_mod_visitor.extend(health_data.loc[health_data['name']==x,'health_mod'])
else:
health_mod_visitor.extend([1.0])
home_num = np.mean(np.array(player_nums_home).dot(individual[player_indices]) * health_mod_home) + \
np.array(team_nums_home).dot(individual[team_indices]) + \
np.array(schedule_stats_home).dot(individual[schedule_indices])
visitor_num = np.mean(np.array(player_nums_visitor).dot(individual[player_indices]) * health_mod_visitor) + \
np.array(team_nums_visitor).dot(individual[team_indices]) + \
np.array(schedule_stats_visitor).dot(individual[schedule_indices])
if visitor_num > home_num:
pred_winner = team_visitor
else:
pred_winner = team_home
pred_winner_list.append(pred_winner)
temp_home_score = slope * home_num + intercept
temp_visitor_score = slope * visitor_num + intercept
home_score_pred.append(temp_home_score)
visitor_score_pred.append(temp_visitor_score)
pred_frame = pd.DataFrame({'winner': pred_winner_list, 'home_score_pred': home_score_pred,
'visitor_score_pred': visitor_score_pred})
return pred_frame
schedule_data['winner'] = schedule_data.apply(get_winner, axis=1)
logging.info('Saving Game Data to Database')
saveFrameToTable(dataFrame=schedule_data, tableName='schedule_data', sqldbName='NBA_data', dbFolder=data_folder, e_option='replace')
######
# Create population parameters
upper_bounds = np.repeat(1, player_char_num + team_char_num + schedule_char_num)
lower_bounds = np.repeat(-1, player_char_num + team_char_num + schedule_char_num)
######
# Create initial population
logging.info('Initializing Population')
population = GA_Funs.create_population(lower_bounds, upper_bounds, n=N_pop, type_fill='random')
######
# Assess initial fitness
fitness = np.repeat(0.0, N_pop)
for n in range(N_pop):
fitness[n] = GA_Funs.get_fitness(population[n,], schedule_data,
team_data1, team_data2, team_cols1, team_cols2,
player_data1, player_data2, player_cols1, player_cols2, health_data)
######
# Start Genetic Algorithm
def get_GA_nums(schedule_data, individual, team_data1, team_data2, team_cols1,
team_cols2, player_data1, player_data2, player_cols1,
player_cols2, health_data):
num_games_loop = len(schedule_data)
print('Num games to predict: ' + str(num_games_loop))
home_ga_nums = []
visitor_ga_nums = []
home_pts = []
visitor_pts = []
for i in range(num_games_loop):
team_home = schedule_data.loc[i, 'home']
team_visitor = schedule_data.loc[i, 'visitor']
game_date = schedule_data.loc[i, 'date']
[team_nums_home1
] = np.array(team_data1[team_data1['team'] == team_home])
[team_nums_home2
] = np.array(team_data2[team_data2['team'] == team_home])
[team_nums_visitor1
] = np.array(team_data1[team_data1['team'] == team_visitor])
[team_nums_visitor2
] = np.array(team_data2[team_data2['team'] == team_visitor])
team_nums_home = np.hstack(
(team_nums_home1[team_cols1], team_nums_home2[team_cols2]))
team_nums_visitor = np.hstack(
(team_nums_visitor1[team_cols1], team_nums_visitor2[team_cols2]))
player_nums_home1 = np.array(
player_data1[player_data1['team'] == team_home])
player_nums_home2 = np.array(
player_data2[player_data2['team'] == team_home])
player_nums_visitor1 = np.array(
player_data1[player_data1['team'] == team_visitor])
player_nums_visitor2 = np.array(
player_data2[player_data2['team'] == team_visitor])
player_nums_home = np.hstack(
(player_nums_home1[:,
player_cols1], player_nums_home2[:,
player_cols2]))
player_nums_visitor = np.hstack((player_nums_visitor1[:, player_cols1],
player_nums_visitor2[:,
player_cols2]))
schedule_stats_home = GA_Funs.get_schedule_stats(schedule_data,
schedule_data,
game_date,
team_home,
future_logical=False)
schedule_stats_visitor = GA_Funs.get_schedule_stats(
schedule_data,
schedule_data,
game_date,
team_visitor,
future_logical=False)
player_indices = range(len(player_cols1) + len(player_cols2))
team_indices = range(
len(player_indices),
len(team_cols1) + len(team_cols2) + len(player_indices))
schedule_indices = range(
len(team_indices) + len(player_indices), len(individual))
health_mod_home = []
for x in player_data1['name'][player_data1['team'] == team_home]:
if x in list(health_data['name']):
health_mod_home.extend(
health_data.loc[health_data['name'] == x, 'health_mod'])
else:
health_mod_home.extend([1.0])
health_mod_visitor = []
for x in player_data1['name'][player_data1['team'] == team_visitor]:
if x in list(health_data['name']):
health_mod_visitor.extend(
health_data.loc[health_data['name'] == x, 'health_mod'])
else:
health_mod_visitor.extend([1.0])
home_num = np.mean(np.array(player_nums_home).dot(individual[player_indices]) * health_mod_home) + \
np.array(team_nums_home).dot(individual[team_indices]) + \
np.array(schedule_stats_home).dot(individual[schedule_indices])
visitor_num = np.mean(np.array(player_nums_visitor).dot(individual[player_indices]) * health_mod_visitor) + \
np.array(team_nums_visitor).dot(individual[team_indices]) + \
np.array(schedule_stats_visitor).dot(individual[schedule_indices])
home_ga_nums.extend([home_num])
visitor_ga_nums.extend([visitor_num])
home_pts.extend([schedule_data.loc[i, 'home_pts']])
visitor_pts.extend([schedule_data.loc[i, 'visitor_pts']])
point_num_data = pd.DataFrame({
'home_score': home_pts,
'visitor_score': visitor_pts,
'home_ga_num': home_ga_nums,
'visitor_ga_num': visitor_ga_nums
})
return point_num_data
def get_prediction(schedule_data, historic_schedule, individual, days_predict,
team_data1, team_data2, team_cols1, team_cols2,
player_data1, player_data2, player_cols1, player_cols2,
health_data, slope, intercept):
# future_schedule
predict_schedule = schedule_data[(schedule_data['days_ago'] <= 0) & (
schedule_data['days_ago'] >= -days_predict)]
num_games_loop = len(predict_schedule)
print('Num games to predict: ' + str(num_games_loop))
pred_winner_list = []
home_score_pred = []
visitor_score_pred = []
for i in range(num_games_loop):
team_home = predict_schedule.loc[i, 'home']
team_visitor = predict_schedule.loc[i, 'visitor']
game_date = predict_schedule.loc[i, 'date']
[team_nums_home1
] = np.array(team_data1[team_data1['team'] == team_home])
[team_nums_home2
] = np.array(team_data2[team_data2['team'] == team_home])
[team_nums_visitor1
] = np.array(team_data1[team_data1['team'] == team_visitor])
[team_nums_visitor2
] = np.array(team_data2[team_data2['team'] == team_visitor])
team_nums_home = np.hstack(
(team_nums_home1[team_cols1], team_nums_home2[team_cols2]))
team_nums_visitor = np.hstack(
(team_nums_visitor1[team_cols1], team_nums_visitor2[team_cols2]))
player_nums_home1 = np.array(
player_data1[player_data1['team'] == team_home])
player_nums_home2 = np.array(
player_data2[player_data2['team'] == team_home])
player_nums_visitor1 = np.array(
player_data1[player_data1['team'] == team_visitor])
player_nums_visitor2 = np.array(
player_data2[player_data2['team'] == team_visitor])
player_nums_home = np.hstack(
(player_nums_home1[:,
player_cols1], player_nums_home2[:,
player_cols2]))
player_nums_visitor = np.hstack((player_nums_visitor1[:, player_cols1],
player_nums_visitor2[:,
player_cols2]))
schedule_stats_home = GA_Funs.get_schedule_stats(predict_schedule,
historic_schedule,
game_date,
team_home,
future_logical=True)
schedule_stats_visitor = GA_Funs.get_schedule_stats(
predict_schedule,
historic_schedule,
game_date,
team_visitor,
future_logical=True)
player_indices = range(len(player_cols1) + len(player_cols2))
team_indices = range(
len(player_indices),
len(team_cols1) + len(team_cols2) + len(player_indices))
schedule_indices = range(
len(team_indices) + len(player_indices), len(individual))
health_mod_home = []
for x in player_data1['name'][player_data1['team'] == team_home]:
if x in list(health_data['name']):
health_mod_home.extend(
health_data.loc[health_data['name'] == x, 'health_mod'])
else:
health_mod_home.extend([1.0])
health_mod_visitor = []
for x in player_data1['name'][player_data1['team'] == team_visitor]:
if x in list(health_data['name']):
health_mod_visitor.extend(
health_data.loc[health_data['name'] == x, 'health_mod'])
else:
health_mod_visitor.extend([1.0])
home_num = np.mean(np.array(player_nums_home).dot(individual[player_indices]) * health_mod_home) + \
np.array(team_nums_home).dot(individual[team_indices]) + \
np.array(schedule_stats_home).dot(individual[schedule_indices])
visitor_num = np.mean(np.array(player_nums_visitor).dot(individual[player_indices]) * health_mod_visitor) + \
np.array(team_nums_visitor).dot(individual[team_indices]) + \
np.array(schedule_stats_visitor).dot(individual[schedule_indices])
if visitor_num > home_num:
pred_winner = team_visitor
else:
pred_winner = team_home
pred_winner_list.append(pred_winner)
temp_home_score = slope * home_num + intercept
temp_visitor_score = slope * visitor_num + intercept
home_score_pred.append(temp_home_score)
visitor_score_pred.append(temp_visitor_score)
pred_frame = pd.DataFrame({
'winner': pred_winner_list,
'home_score_pred': home_score_pred,
'visitor_score_pred': visitor_score_pred
})
return pred_frame
dbFolder=data_folder,
e_option='replace')
######
# Create population parameters
upper_bounds = np.repeat(1,
player_char_num + team_char_num + schedule_char_num)
lower_bounds = np.repeat(-1,
player_char_num + team_char_num + schedule_char_num)
######
# Create initial population
logging.info('Initializing Population')
population = GA_Funs.create_population(lower_bounds,
upper_bounds,
n=N_pop,
type_fill='random')
######
# Assess initial fitness
fitness = np.repeat(0.0, N_pop)
for n in range(N_pop):
fitness[n] = GA_Funs.get_fitness(population[n, ], schedule_data,
team_data1, team_data2, team_cols1,
team_cols2, player_data1, player_data2,
player_cols1, player_cols2, health_data)
######
# Start Genetic Algorithm
