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
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():
#horse_parser_98 = HorseParserNoHandicaps('./../Data/born98.csv')
#horse_parser_05 = HorseParserNoHandicaps('./../Data/born05.csv')
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))
jockeys_claim_test(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)
#goings_vs_speed(horses_train_98)
'''
print ''
print 'HorsesBorn05 Training Set:'
print 'No. of horses: ' + str(len(horses_train_05))
jockeys_claim_test(horses_train_05)
'''
def main():
model_file_path = "output" + os.sep + "linear_regression_model_mv.sav"
ignored_columns = ['ZN', 'CHAS', 'NOX', 'RM', 'DIS', 'RAD', 'TAX', 'PIRATIO', 'B', 'LSTAT']
X, Y = load_data('input' + os.sep + 'housing.csv', False, ignored_columns)
X = preprocess(X, "normalize")
X_train, y_train, X_test, y_test = split_dataset(X, Y)
train(X_train, y_train, model_file_path)
y_predicted = predict(X_test, model_file_path)
rmse_ration = calculate_rmse_ration(y_test, y_predicted)
print("rmse ratio:", rmse_ration)
def main(input_path, output_path, ignored_columns, preprocess_type,
training_data_rate, step_length, threshold_rate, max_loop_num,
dynamic_step):
print("input:", input_path)
print("output:", output_path)
print("\n")
if ignored_columns is not None:
print("ignored_columns:", ignored_columns)
print("\n")
print("preprocess_type:", preprocess_type)
print("training_data_rate:", training_data_rate)
print("\n")
print("threshold_rate:", threshold_rate)
print("max_loop_num:", max_loop_num)
print("step_length:", step_length)
if dynamic_step:
print("dynamic stepping ...")
else:
print("static stepping ...")
print("\n")
start_time = datetime.now()
X, Y = load_data(input_path, True, ignored_columns)
X = preprocess(X, preprocess_type)
X_train, y_train, X_test, y_test = split_dataset(X, Y, training_data_rate)
threshold = gen_threshold(Y, threshold_rate)
train(X_train, y_train, output_path, step_length, threshold, max_loop_num,
dynamic_step)
Y_pred = predict(output_path, X_test)
rmse_ration = calculate_rmse_ration(y_test, Y_pred)
print("rmse ratio (rmse / y_mean) is:", rmse_ration, "\n")
end_time = datetime.now()
execution_duration = end_time - start_time
print("execution duration:", execution_duration, "\n")
return
def main():
ignored_columns = [
'ZN', 'CHAS', 'NOX', 'RM', 'DIS', 'RAD', 'TAX', 'PIRATIO', 'B', 'LSTAT'
]
X, Y = load_data('input' + os.sep + 'housing.csv', True, ignored_columns)
X = preprocess(X, "normalize")
X_train, y_train, X_test, y_test = split_dataset(X, Y)
path = 'output' + os.sep + 'lsm_multivariant.csv'
lsm(X_train, y_train, path)
y_predicted = predict(path, X_test)
rmse_ration = calculate_rmse_ration(y_test, y_predicted)
print("rmse ratio:", rmse_ration)
return
def run_experiments_without_cross_validation(model_names, features_to_use):
dataset_features = utilities.load_features('pasokh')
features, targets, labels, documents, all_vec = utilities.split_dataset(dataset_features, features_to_use, 0.40)
X_normal = np.array(all_vec)
utilities.normalize_dataset(X_normal, features_to_use, 'learn')
X_train = np.array(features['train'])
X_test = np.array(features['test'])
y_train = np.array(targets['train'])
y_test = np.array(targets['test'])
labels_train = np.array(labels['train'])
labels_test = np.array(labels['test'])
print("Dataset size: {}".format(len(X_normal)))
#print("Number of True/False labels: {}/{}".format(sum(labels), sum(1 for i in labels if not i)))
(X_balanced, y_balanced, labels_balanced) = (X_train, y_train, labels_train)
#X_balanced, y_balanced, labels_balanced = utilities.balance_dataset(X_train, y_train, labels_train, 3)
print("Train set size: {}".format(len(X_balanced)))
print("Number of True/False labels: {}/{}".format(sum(labels_balanced), sum(1 for i in labels_balanced if not i)))
print("Test set size: {}".format(len(X_test)))
print("Number of True/False labels: {}/{}".format(sum(labels_test), sum(1 for i in labels_test if not i)))
print("Used features: {}".format(len(X_balanced[0])))
dataset_json = json.loads(utilities.read_file('resources/pasokh/all.json'))
is_regressor = True
for model_type in model_names:
print('**********************' + model_type + '**********************')
if model_type == 'dtr':
# max_depth=6
regr = tree.DecisionTreeRegressor()
regr = regr.fit(X_balanced, y_balanced)
export_name = 'dtr'
elif model_type == 'linear':
regr = linear_model.LinearRegression(normalize=True)
# Train the model using the training sets
regr.fit(X_balanced, y_balanced)
# The coefficients
print('Coefficients: \n', regr.coef_)
export_name = 'linear'
elif model_type == 'svm':
regr = SVR(verbose=True, epsilon=0.00001, gamma='auto', tol=.00001)
# Train the model using the training sets
regr.fit(X_balanced, y_balanced)
# The coefficients
print('Coefficients: \n', regr.get_params())
export_name = 'svm'
elif model_type == 'dummy':
regr = RndRegressor()
export_name = 'dummy'
elif model_type == 'ideal':
from IdealRegressor import IdealRegressor
regr = IdealRegressor(X_train, y_train)
regr.fit(X_test, y_test)
export_name = 'ideal'
elif model_type == 'nb':
# from sklearn import svm
# regr = svm.SVC(gamma='scale').fit(X_train, labels_train)
from sklearn.naive_bayes import ComplementNB, GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
regr = ComplementNB(alpha=1)
regr.fit(X_train, labels_train)
is_regressor = False
export_name = 'nb'
else:
print("Regression type is undefined:" + model_type)
continue
# Make predictions using the testing set
model_results = evaluate_model(regr, X_test, X_balanced, y_test, y_balanced, labels_test, labels_balanced, is_regressor)
print('Summarizing dataset and evaluating Rouge...')
rouge_scores = evaluate_summarizer(regr, dataset_json, features_to_use, True)
utilities.print_rouges(rouge_scores)
print('*****************************************************************************')
return rouge_scores, model_results
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 ''
# 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='mean_squared_error', cv=5)
#print regr98.coeff_
# 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 ''
''' ell1 and ell2 metrics computed using actual speeds and those predicted using the training set '''
print 'ell1:'
print ell1(horses_98_y_train, regr98.predict(horses_98_X_train))
print ''
print 'ell2:'
print ell2(horses_98_y_train, regr98.predict(horses_98_X_train))
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='mean_squared_error', 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 ''
''' ell1 and ell2 metrics computed using actual speeds and those predicted using the training set '''
print 'ell1:'
print ell1(horses_05_y_train, regr05.predict(horses_05_X_train))
print ''
print 'ell2:'
print ell2(horses_05_y_train, regr98.predict(horses_05_X_train))
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)
# 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 learn_models(model_names, features_to_use):
"""
This version splits original texts in dataset for evaluating summaries
"""
dataset_features = utilities.load_features('CNN')
features, targets, labels, documents, all_vec = utilities.split_dataset(
dataset_features, features_to_use, 0.28, 'CNN')
#return utilities.write_dataset_csv(dataset_features, '/tmp/test.csv')
'''
cPickle.dump(features, open('features.pkl', 'wb'))
cPickle.dump(targets, open('targets.pkl', 'wb'))
cPickle.dump(labels, open('labels.pkl', 'wb'))
cPickle.dump(documents, open('documents.pkl', 'wb'))
cPickle.dump(all_vec, open('all_vec.pkl', 'wb'))
features = cPickle.load(open('features.pkl', 'rb'))
targets = cPickle.load(open('targets.pkl', 'rb'))
labels = cPickle.load(open('labels.pkl', 'rb'))
documents = cPickle.load(open('documents.pkl', 'rb'))
all_vec = cPickle.load(open('all_vec.pkl', 'rb'))
'''
X_normal = np.array(all_vec)
#X_normal = utilities.select_features(features_to_use, X_normal)
# X_normal = StandardScaler().fit_transform(dataset[0])
utilities.normalize_dataset(X_normal, features_to_use, 'learn')
X_train = np.array(features['train'])
X_test = np.array(features['test'])
y_train = np.array(targets['train'])
y_test = np.array(targets['test'])
labels_train = np.array(labels['train'])
labels_test = np.array(labels['test'])
#X_train = utilities.select_features(features_to_use, X_train)
#utilities.normalize_dataset(X_train, features_to_use)
#X_test = utilities.select_features(features_to_use, X_test)
#utilities.normalize_dataset(X_test, features_to_use)
print("Dataset size: {}".format(len(all_vec)))
#(X_balanced, y_balanced, labels_balanced) = (X_train, y_train, labels_train)
X_balanced, y_balanced, labels_balanced = utilities.balance_dataset(
X_train, y_train, labels_train, 1)
print("Used features: " + ','.join(features_to_use))
print("Train set size: {}".format(len(X_balanced)))
print("Number of True/False labels: {}/{}".format(
sum(labels_balanced), sum(1 for i in labels_balanced if not i)))
print("Test set size: {}".format(len(X_test)))
print("Number of True/False labels: {}/{}".format(
sum(labels_test), sum(1 for i in labels_test if not i)))
print("Used features: {}".format(len(X_balanced[0])))
dataset_json = json.loads(
utilities.read_file('resources/CNN/documents.json'))
test_documents = {int(key): dataset_json[key] for key in documents['test']}
is_regressor = True
for model_type in model_names:
print('**********************' + model_type + '**********************')
if model_type == 'dtr':
# max_depth=6
regr = tree.DecisionTreeRegressor(criterion='friedman_mse')
regr = regr.fit(X_balanced, y_balanced)
print(regr.get_params())
export_name = 'dtr'
elif model_type == 'linear':
regr = linear_model.LinearRegression()
# Train the model using the training sets
regr.fit(X_balanced, y_balanced)
# The coefficients
print('Coefficients: \n', regr.coef_)
export_name = 'linear'
elif model_type == 'svm':
regr = SVR(kernel='rbf',
degree=7,
verbose=False,
epsilon=0.000001,
gamma='scale',
tol=.0000001,
shrinking=True)
# Train the model using the training sets
regr.fit(X_balanced, y_balanced)
# The coefficients
print('Coefficients: \n', regr.get_params())
export_name = 'svm'
elif model_type == 'dummy':
regr = RndRegressor()
export_name = 'dummy'
is_regressor = False
elif model_type == 'ideal':
from IdealRegressor import IdealRegressor
regr = IdealRegressor(X_train, y_train)
#regr.predict(X_train)
regr.fit(X_test, y_test)
#regr.predict(X_test)
export_name = 'ideal'
elif model_type == 'nb':
#from sklearn import svm
#regr = svm.SVC(gamma='scale').fit(X_train, labels_train)
from sklearn.naive_bayes import ComplementNB, GaussianNB
from sklearn.discriminant_analysis import QuadraticDiscriminantAnalysis
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
regr = ComplementNB(alpha=0.015)
regr.fit(X_train, labels_train)
is_regressor = False
export_name = 'nb'
else:
print("Regression type is undefined:" + model_type)
continue
# Make predictions using the testing set
model_results = Learn.evaluate_model(regr, X_test, X_balanced, y_test,
y_balanced, labels_test,
labels_balanced, is_regressor)
print('Summarizing dataset and evaluating Rouge...')
rouge_scores = evaluate_summarizer(regr, test_documents,
features_to_use, True)
utilities.print_rouges(rouge_scores)
utilities.export_model(regr, export_name)
print(
'*****************************************************************************'
)
return rouge_scores, model_results
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 ''
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():
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
''' 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():
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 ''