def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
races98 = RaceParserNoHandicaps('./../Data/born98.csv').races
races05 = RaceParserNoHandicaps('./../Data/born05.csv').races
horses_train_98, horses_test_98 = split_dataset(horses98)
horses_train_05, horses_test_05 = split_dataset(horses05)
going_class(horses_train_05)
going_class(horses_train_98)
def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
horses_train_98, horses_test_98 = split_dataset(horses98)
horses_train_05, horses_test_05 = split_dataset(horses05)
print 'HorsesBorn98 Training Set:'
print 'No. of horses: ' + str(len(horses_train_98))
rating_vs_speed(horses_train_98)
prize_money_vs_speed(horses_train_98)
odds_vs_speed(horses_train_98)
age_vs_speed(horses_train_98)
no_of_runners_vs_speed(horses_train_98)
race_class_vs_speed(horses_train_98)
weight_vs_speed(horses_train_98)
jockeys_claim_vs_speed(horses_train_98)
place_vs_speed(horses_train_98)
distance_vs_speed(horses_train_98)
comptime_vs_speed(horses_train_98)
stall_vs_speed(horses_train_98)
rating_vs_odds(horses_train_98)
#goings_vs_speed(horses_train_98)
print ''
print 'HorsesBorn05 Training Set:'
print 'No. of horses: ' + str(len(horses_train_05))
rating_vs_speed(horses_train_05)
prize_money_vs_speed(horses_train_05)
odds_vs_speed(horses_train_05)
age_vs_speed(horses_train_05)
no_of_runners_vs_speed(horses_train_05)
race_class_vs_speed(horses_train_05)
weight_vs_speed(horses_train_05)
jockeys_claim_vs_speed(horses_train_05)
place_vs_speed(horses_train_05)
distance_vs_speed(horses_train_05)
comptime_vs_speed(horses_train_05)
stall_vs_speed(horses_train_05)
rating_vs_odds(horses_train_05)
def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
races98 = RaceParserNoHandicaps('./../Data/born98.csv').races
races05 = RaceParserNoHandicaps('./../Data/born05.csv').races
print 'HorsesBorn98 Training Set:'
print 'No. of horses: ' + str(len(horses98))
print 'No. of races: ' + str(len(races98))
print 'HorsesBorn05 Training Set:'
print 'No. of horses: ' + str(len(horses05))
print 'No. of races: ' + str(len(races05))
#average_race_speeds(races98, races05)
#average_horse_speeds(horses98, horses05)
#horses_age_record_no(horses98, horses05)
#race_distances(races98, races05)
#race_records_per_horse(horses98, horses05)
race_class_records(races98, races05)
'''
rating_vs_speed(horses98)
prize_money_vs_speed(horses98)
odds_vs_speed(horses98)
age_vs_speed(horses98)
no_of_runners_vs_speed(horses98)
race_class_vs_speed(horses98)
weight_vs_speed(horses98)
jockeys_claim_vs_speed(horses98)
place_vs_speed(horses98)
distance_vs_speed(horses98)
comptime_vs_speed(horses98)
stall_vs_speed(horses98)
#goings_vs_speed(horses98)
'''
print ''
#average_race_speeds(races05)
#average_horse_speeds(horses05)
'''
def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
races98 = RaceParserNoHandicaps('./../Data/born98.csv').races
races05 = RaceParserNoHandicaps('./../Data/born05.csv').races
''' HorsesBorn98 Dataset '''
horses_train_98, horses_test_98 = split_dataset(horses98)
horses_98_X_train = []
horses_98_y_train = []
for h in horses_train_98:
v,s = compute_vector(h)
horses_98_X_train.append(v)
horses_98_y_train .append(s)
print 'No. of instances in training set:'
print len(horses_98_X_train)
print len(horses_98_y_train)
print ''
horses_98_X_test = []
horses_98_y_test = []
for h in horses_test_98:
v,s = compute_vector(h)
horses_98_X_test.append(v)
horses_98_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_98_X_test)
print len(horses_98_y_test)
print ''
# Create linear regression object
regr98 = linear_model.LinearRegression()
# Train the model using the training sets
regr98.fit(horses_98_X_train, horses_98_y_train)
# Coefficients
print 'Coefficients:'
print regr98.coef_
print ''
# Explained variance score: 1 is perfect prediction
print 'Variance score:'
print regr98.score(horses_98_X_test, horses_98_y_test)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_98_y_test, (regr98.predict(horses_98_X_test)))
print ''
print 'Explained variance:'
print explained_variance_score(horses_98_y_test, (regr98.predict(horses_98_X_test)))
print ''
print 'Mean squared error:'
print mean_squared_error(horses_98_y_test, (regr98.predict(horses_98_X_test)))
print ''
print 'R2 score:'
print r2_score(horses_98_y_test, (regr98.predict(horses_98_X_test)))
print ''
''' HorsesBorn05 Dataset '''
horses_train_05, horses_test_05 = split_dataset(horses05)
horses_05_X_train = []
horses_05_y_train = []
for h in horses_train_05:
v,s = compute_vector(h)
horses_05_X_train.append(v)
horses_05_y_train .append(s)
print 'No. of instances in training set:'
print len(horses_05_X_train)
print len(horses_05_y_train)
print ''
horses_05_X_test = []
horses_05_y_test = []
for h in horses_test_05:
v,s = compute_vector(h)
horses_05_X_test.append(v)
horses_05_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_05_X_test)
print len(horses_05_y_test)
print ''
# Create linear regression object
regr05 = linear_model.LinearRegression()
# Train the model using the training sets
regr05.fit(horses_05_X_train, horses_05_y_train)
# Coefficients
print 'Coefficients:'
print regr05.coef_
print ''
# Explained variance score: 1 is perfect prediction
print 'Variance score:'
print regr05.score(horses_05_X_test, horses_05_y_test)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_05_y_test, (regr05.predict(horses_05_X_test)))
print ''
print 'Explained variance:'
print explained_variance_score(horses_05_y_test, (regr05.predict(horses_05_X_test)))
print ''
print 'Mean squared error:'
print mean_squared_error(horses_05_y_test, (regr05.predict(horses_05_X_test)))
print ''
print 'R2 score:'
print r2_score(horses_05_y_test, (regr05.predict(horses_05_X_test)))
print ''
def main():
horse_parser_98 = HorseParserNoHandicaps('./../Data/born98.csv')
horse_parser_05 = HorseParserNoHandicaps('./../Data/born05.csv')
race_parser_98 = RaceParserNoHandicaps('./../Data/born98.csv')
race_parser_05 = RaceParserNoHandicaps('./../Data/born05.csv')
horses98 = horse_parser_98.horses
horses05 = horse_parser_05.horses
races98 = race_parser_98.races
races05 = race_parser_05.races
full_races_98 = get_full_races(races98)
full_races_05 = get_full_races(races05)
total_races_with_all_horses_98 = no_of_races_with_all_horses(races98)
total_races_with_winners_98 = races_with_winning_horse(races98)
total_races_with_all_horses_05 = no_of_races_with_all_horses(races05)
total_races_with_winners_05 = races_with_winning_horse(races05)
average_races_per_horse_98 = average_no_of_races_per_horse(horses98)
average_races_per_horse_05 = average_no_of_races_per_horse(horses05)
ages98 = get_ages(full_races_98)
ages05 = get_ages(full_races_05)
no_of_races_per_age_98 = races_at_each_age(full_races_98, ages98)
no_of_races_per_age_05 = races_at_each_age(full_races_05, ages05)
races_with_k_missing_horses_98 = races_with_k_missing_runners(races98)
races_with_k_missing_horses_05 = races_with_k_missing_runners(races05)
print 'born98.csv file statistics - without handicap races:'
print 'No. of horses: ' + str(len(horses98))
print 'No. of races: ' + str(len(races98))
print 'No. of races for which we have all the horses: ' + str(total_races_with_all_horses_98)
print 'No. of races for which we have the winner: ' + str(total_races_with_winners_98)
print 'Fraction of races for which we have all the horses: ' + str(float(total_races_with_all_horses_98)/len(races98))
print 'Fraction of races for which we have the winner: ' + str(float(total_races_with_winners_98)/len(races98))
print 'Average no. of races per horse: ' + str(average_races_per_horse_98)
print 'No. of races for horses at each age: ' + str(no_of_races_per_age_98)
print 'No. of races with k-missing horse records: ' + str(races_with_k_missing_horses_98)
print 'No. of different trainers: ' + str(no_of_trainers(horses98))
print 'No. of different jockeys: ' + str(no_of_jockeys(horses98))
print 'Going and Speed: '
going_average_speeds(races98)
print 'Race Class and Speed:'
class_average_speeds(races98)
print 'Race Class and Distance:'
class_average_distances(races98)
print 'Race Class and Prize:'
class_average_prizes(races98)
print ''
print 'born05.csv file statistics - without handicap races:'
print 'No. of horses: ' + str(len(horses05))
print 'No. of races: ' + str(len(races05))
print 'No. of races for which we have all the horses: ' + str(total_races_with_all_horses_05)
print 'No. of races for which we have the winner: ' + str(total_races_with_winners_05)
print 'Fraction of races for which we have all the horses: ' + str(float(total_races_with_all_horses_05)/len(races05))
print 'Fraction of races for which we have the winner: ' + str(float(total_races_with_winners_05)/len(races05))
print 'Average no. of races per horse: ' + str(average_races_per_horse_05)
print 'No. of races for horses at each age: ' + str(no_of_races_per_age_05)
print 'No. of races with k-missing horse records: ' + str(races_with_k_missing_horses_05)
print 'No. of different trainers: ' + str(no_of_trainers(horses05))
print 'No. of different jockeys: ' + str(no_of_jockeys(horses05))
print 'Going and Speed: '
going_average_speeds(races05)
print 'Race Class and Speed:'
class_average_speeds(races05)
print 'Race Class and Distance:'
class_average_distances(races05)
print 'Race Class and Prize:'
class_average_prizes(races05)
def main():
horse_parser_98 = HorseParser('./../Data/born98.csv')
horse_parser_05 = HorseParser('./../Data/born05.csv')
race_parser_98 = RaceParser('./../Data/born98.csv')
race_parser_05 = RaceParser('./../Data/born05.csv')
horse_parser_no_handicaps_98 = HorseParserNoHandicaps('./../Data/born98.csv')
horse_parser_no_handicaps_05 = HorseParserNoHandicaps('./../Data/born05.csv')
race_parser_no_handicaps_98 = RaceParserNoHandicaps('./../Data/born98.csv')
race_parser_no_handicaps_05 = RaceParserNoHandicaps('./../Data/born05.csv')
horses98 = horse_parser_98.horses
horses05 = horse_parser_05.horses
races98 = race_parser_98.races
races05 = race_parser_05.races
full_races_98 = get_full_races(races98)
full_races_05 = get_full_races(races05)
total_races_with_all_horses_98 = no_of_races_with_all_horses(races98)
total_races_with_winners_98 = no_of_races_with_winner(races98, horses98)
total_races_with_all_horses_05 = no_of_races_with_all_horses(races05)
total_races_with_winners_05 = no_of_races_with_winner(races05, horses05)
average_races_per_horse_98 = average_no_of_races_per_horse(horses98)
average_races_per_horse_05 = average_no_of_races_per_horse(horses05)
ages98 = get_ages(full_races_98)
ages05 = get_ages(full_races_05)
no_of_races_per_age_98 = races_at_each_age(full_races_98, ages98)
no_of_races_per_age_05 = races_at_each_age(full_races_05, ages05)
races_with_k_missing_horses_98 = races_with_k_missing_runners(races98)
races_with_k_missing_horses_05 = races_with_k_missing_runners(races05)
print 'born98.csv file statistics:'
print 'No. of horses: ' + str(len(horses98))
print 'No. of races: ' + str(len(races98))
print 'No. of races for which we have all the horses: ' + str(total_races_with_all_horses_98)
print 'No. of races for which we have the winner: ' + str(total_races_with_winners_98)
print 'Fraction of races for which we have all the horses: ' + str(float(total_races_with_all_horses_98)/len(races98))
print 'Fraction of races for which we have the winner: ' + str(float(total_races_with_winners_98)/len(races98))
print 'Average no. of races per horse: ' + str(average_races_per_horse_98)
print 'No. of races for horses at each age: ' + str(no_of_races_per_age_98)
print 'No. of races with k-missing horse records: ' + str(races_with_k_missing_horses_98)
print 'No. of horse records with comptime missing: ' + str(horse_parser_98.comptime_missing)
print 'No. of race records with comptime missing: ' + str(race_parser_98.comptime_missing)
print 'No. of horse records with Irish race class: ' + str(horse_parser_98.irish_races)
print 'No. of race records with Irish race class ' + str(race_parser_98.irish_races)
print 'No. of races without handicap races:' + str()
print ''
print 'born05.csv file statistics:'
print 'No. of horses: ' + str(len(horses05))
print 'No. of races: ' + str(len(races05))
print 'No. of races for which we have all the horses: ' + str(total_races_with_all_horses_05)
print 'No. of races for which we have the winner: ' + str(total_races_with_winners_05)
print 'Fraction of races for which we have all the horses: ' + str(float(total_races_with_all_horses_05)/len(races05))
print 'Fraction of races for which we have the winner: ' + str(float(total_races_with_winners_05)/len(races05))
print 'Average no. of races per horse: ' + str(average_races_per_horse_05)
print 'No. of races for horses at each age: ' + str(no_of_races_per_age_05)
print 'No. of races with k-missing horse records: ' + str(races_with_k_missing_horses_05)
print 'No. of horse records with comptime missing: ' + str(horse_parser_05.comptime_missing)
print 'No. of race records with comptime missing: ' + str(race_parser_05.comptime_missing)
print 'No. of horse records with Irish race class: ' + str(horse_parser_05.irish_races)
print 'No. of race records with Irish race class ' + str(race_parser_05.irish_races)
def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
print ''' HorsesBorn98 Dataset '''
horses_train_98, horses_test_98 = split_dataset(horses98)
horses_98_X_train = []
horses_98_y_train = []
for h in horses_train_98:
v, s = compute_vector(h)
horses_98_X_train.append(v)
horses_98_y_train.append(s)
print 'No. of instances in training set:'
print len(horses_98_X_train)
print len(horses_98_y_train)
print ''
horses_98_X_test = []
horses_98_y_test = []
for h in horses_test_98:
v, s = compute_vector(h)
horses_98_X_test.append(v)
horses_98_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_98_X_test)
print len(horses_98_y_test)
print ''
# Create linear regression object
regr98 = linear_model.LinearRegression(fit_intercept=True)
# Cross-validation
cv_scores_98 = cross_validation.cross_val_score(
regr98,
np.array(horses_98_X_train),
np.array(horses_98_y_train),
scoring='r2',
cv=5)
# Print CV scores
print '5-fold CV scores using MSE:'
print cv_scores_98
print ''
# Mean and SD of estimate score
print 'Mean of scores: ' + str(cv_scores_98.mean())
print 'SD of scores: ' + str(cv_scores_98.std() * 2)
print ''
# Train the model using the training sets
regr98.fit(np.array(horses_98_X_train), np.array(horses_98_y_train))
# Coefficients
print 'Coefficients:'
print regr98.coef_
print ''
print 'Intercept: '
print regr98.intercept_
print ''
# Predict using the testing set
horses_98_y_pred = regr98.predict(horses_98_X_test)
print 'Mean squared error:'
print mean_squared_error(horses_98_y_test, horses_98_y_pred)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_98_y_test, horses_98_y_pred)
print ''
print 'R2 Score:'
print r2_score(horses_98_y_test, horses_98_y_pred)
print ''
print '1-R1 Score:'
print r1(horses_98_y_test, horses_98_y_pred)
print ''
print ''' HorsesBorn05 Dataset '''
horses_train_05, horses_test_05 = split_dataset(horses05)
horses_05_X_train = []
horses_05_y_train = []
for h in horses_train_05:
v, s = compute_vector(h)
horses_05_X_train.append(v)
horses_05_y_train.append(s)
print 'No. of instances in training set:'
print len(horses_05_X_train)
print len(horses_05_y_train)
print ''
horses_05_X_test = []
horses_05_y_test = []
for h in horses_test_05:
v, s = compute_vector(h)
horses_05_X_test.append(v)
horses_05_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_05_X_test)
print len(horses_05_y_test)
print ''
# Create linear regression object
regr05 = linear_model.LinearRegression(fit_intercept=True)
# Cross-validation
cv_scores_05 = cross_validation.cross_val_score(
regr05,
np.array(horses_05_X_train),
np.array(horses_05_y_train),
scoring='r2',
cv=5)
# Print CV scores
print '5-fold CV scores using MSE:'
print cv_scores_05
print ''
# Mean and SD of estimate score
print 'Mean of scores: ' + str(cv_scores_05.mean())
print 'SD of scores: ' + str(cv_scores_05.std() * 2)
print ''
# Train the model using the training sets
regr05.fit(np.array(horses_05_X_train), np.array(horses_05_y_train))
# Coefficients
print 'Coefficients:'
print regr05.coef_
print ''
print 'Intercept: '
print regr05.intercept_
print ''
# Predict using the testing set
horses_05_y_pred = regr05.predict(horses_05_X_test)
print 'Mean squared error:'
print mean_squared_error(horses_05_y_test, horses_05_y_pred)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_05_y_test, horses_05_y_pred)
print ''
print 'R2 Score:'
print r2_score(horses_05_y_test, horses_05_y_pred)
print ''
print '1-R1 Score:'
print r1(horses_05_y_pred, horses_05_y_test)
print ''
def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
print ''' HorsesBorn98 Dataset '''
horses_train_98, horses_test_98 = split_dataset(horses98)
horses_98_X_train = []
horses_98_y_train = []
for h in horses_train_98:
v, s = compute_vector(h)
horses_98_X_train.append(v)
horses_98_y_train.append(s)
print 'No. of instances in training set:'
print len(horses_98_X_train)
print len(horses_98_y_train)
print ''
horses_98_X_test = []
horses_98_y_test = []
for h in horses_test_98:
v, s = compute_vector(h)
horses_98_X_test.append(v)
horses_98_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_98_X_test)
print len(horses_98_y_test)
print ''
# Create linear regression object
regr98 = linear_model.LinearRegression(fit_intercept=True)
# Train the model using the training sets
regr98.fit(np.array(horses_98_X_train), np.array(horses_98_y_train))
# Coefficients
print 'Coefficients:'
print regr98.coef_
print ''
print 'Intercept: '
print regr98.intercept_
print ''
# Predict using the testing set
horses_98_y_pred = regr98.predict(horses_98_X_test)
print 'Mean squared error:'
print mean_squared_error(horses_98_y_test, horses_98_y_pred)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_98_y_test, horses_98_y_pred)
print ''
print 'R2 Score:'
print r2_score(horses_98_y_test, horses_98_y_pred)
print ''
print '1-R1 Score:'
print r1(horses_98_y_test, horses_98_y_pred)
print ''
print ''' HorsesBorn05 Dataset '''
horses_train_05, horses_test_05 = split_dataset(horses05)
horses_05_X_train = []
horses_05_y_train = []
for h in horses_train_05:
v, s = compute_vector(h)
horses_05_X_train.append(v)
horses_05_y_train.append(s)
print 'No. of instances in training set:'
print len(horses_05_X_train)
print len(horses_05_y_train)
print ''
horses_05_X_test = []
horses_05_y_test = []
for h in horses_test_05:
v, s = compute_vector(h)
horses_05_X_test.append(v)
horses_05_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_05_X_test)
print len(horses_05_y_test)
print ''
# Create linear regression object
regr05 = linear_model.LinearRegression(fit_intercept=True)
# Train the model using the training sets
regr05.fit(np.array(horses_05_X_train), np.array(horses_05_y_train))
# Coefficients
print 'Coefficients:'
print regr05.coef_
print ''
print 'Intercept: '
print regr05.intercept_
print ''
# Predict using the testing set
horses_05_y_pred = regr05.predict(horses_05_X_test)
print 'Mean squared error:'
print mean_squared_error(horses_05_y_test, horses_05_y_pred)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_05_y_test, horses_05_y_pred)
print ''
print 'R2 Score:'
print r2_score(horses_05_y_test, horses_05_y_pred)
print ''
print '1-R1 Score:'
print r1(horses_05_y_pred, horses_05_y_test)
print ''
def main():
horses98 = HorseParserNoHandicaps('./../Data/born98.csv').horses
horses05 = HorseParserNoHandicaps('./../Data/born05.csv').horses
races98 = RaceParserNoHandicaps('./../Data/born98.csv').races
races05 = RaceParserNoHandicaps('./../Data/born05.csv').races
print 'HorsesBorn98 Dataset'
horses_train_98, horses_test_98 = split_dataset(horses98)
horses_98_X_train = []
horses_98_y_train = []
for h in horses_train_98:
v, s = compute_vector(h)
horses_98_X_train.append(v)
horses_98_y_train.append(s)
print 'No. of instances in training set:'
print len(horses_98_X_train)
print len(horses_98_y_train)
print ''
horses_98_X_test = []
horses_98_y_test = []
for h in horses_test_98:
v, s = compute_vector(h)
horses_98_X_test.append(v)
horses_98_y_test.append(s)
print 'No. of instances in testing set:'
print len(horses_98_X_test)
print len(horses_98_y_test)
print ''
print 'Create SVR object'
# Create svr object
svr98 = SVR(kernel='linear', C=1e3) #, gamma=0.1)
print 'Training SVR'
# Train the model using the training sets
svr98.fit(horses_98_X_train, horses_98_y_train)
print 'Predicting'
horses_98_y_pred = svr98.predict(horses_98_X_test)
# Explained variance score: 1 is perfect prediction
print 'Variance score:'
print svr98.score(horses_98_X_test, horses_98_y_test)
print ''
print 'Mean absolute error:'
print mean_absolute_error(horses_98_y_test, horses_98_y_pred)
print ''
print 'Explained variance:'
print explained_variance_score(horses_98_y_test, horses_98_y_pred)
print ''
print 'Mean squared error:'
print mean_squared_error(horses_98_y_test, horses_98_y_pred)
print ''
print 'R2 score:'
print r2_score(horses_98_y_test, horses_98_y_pred)
print ''