def logistic(InputFileName):
raw_data = load_data(InputFileName)
all_normalised_data = append_classifications(raw_data)
all_normalised_data = normalise(all_normalised_data)
# all_normalised_data = all_normalised_data
training_data = append_features(all_normalised_data)
expander = FeatureExpander(training_data)
inclusion_list = []
inclusion_list.append(0) # last sv
inclusion_list.append(0) # last change in sv
inclusion_list.append(0) # mean of prev 10 rows sv
inclusion_list.append(0) # std dev of prev 10 rows sv
inclusion_list.append(0) # last sp
inclusion_list.append(0) # last change in sp
inclusion_list.append(0) # mean of prev 10 rows sp
inclusion_list.append(0) # std dev of prev 10 rows sp
expanded = expander.expand_features(inclusion_list)
write_to_file(expanded, fp_out)
[expanded_CV1, expanded_CV2] = split_data(expanded)
THETA_CV1 = regression(expanded_CV1)
THETA_CV2 = regression(expanded_CV2)
print THETA_CV1
print THETA_CV2
return evaluate(expanded_CV1, expanded_CV2, THETA_CV1, THETA_CV2)
def linear(InputFileName):
raw_data = load_data(InputFileName)
training_data = append_features(raw_data)
expander = FeatureExpander(training_data)
inclusion_list = []
inclusion_list.append(2) # last sv
inclusion_list.append(0) # last change in sv
inclusion_list.append(0) # mean of prev 10 rows sv
inclusion_list.append(0) # std dev of prev 10 rows sv
inclusion_list.append(0) # last sp
inclusion_list.append(0) # last change in sp
inclusion_list.append(0) # mean of prev 10 rows sp
inclusion_list.append(0) # std dev of prev 10 rows sp
expanded = expander.expand_features(inclusion_list)
write_to_file(expanded, fp_out)
[expanded_CV1, expanded_CV2] = split_data(expanded)
THETA_CV1 = regression(expanded_CV1)
THETA_CV2 = regression(expanded_CV2)
result = evaluate(expanded_CV1,expanded_CV2,THETA_CV1,THETA_CV2)
print THETA_CV1
print THETA_CV2
return result
def reglogistic(InputFileName, inclusion_list = None):
raw_data = load_data(InputFileName)
all_normalised_data = append_classifications(raw_data)
all_normalised_data = normalise(all_normalised_data)
#all_normalised_data = all_normalised_data
training_data = append_features(all_normalised_data)
expander = FeatureExpander(training_data)
if not inclusion_list:
inclusion_list = []
inclusion_list.append(0) # last sv
inclusion_list.append(0) # last change in sv
inclusion_list.append(0) # mean of prev 10 rows sv
inclusion_list.append(0) # std dev of prev 10 rows sv
inclusion_list.append(0) # last sp
inclusion_list.append(1) # last change in sp
inclusion_list.append(0) # mean of prev 10 rows sp
inclusion_list.append(1) # std dev of prev 10 rows sp
expanded = expander.expand_features(inclusion_list)
write_to_file(expanded, fp_out)
[expanded_CV1, expanded_CV2, expanded_test] = split_data_3_folds(expanded)
results = []
lamb_resolution = 5
for lamb in [i/lamb_resolution for i in range(1,lamb_resolution)]:
print lamb
THETA_CV1 = unflatten_theta(regression(expanded_CV1, lamb))
THETA_CV2 = unflatten_theta(regression(expanded_CV2, lamb))
results.append((THETA_CV1, lamb, percentage_correct_classifications(THETA_CV1, expanded_CV2)))
results.append((THETA_CV2, lamb, percentage_correct_classifications(THETA_CV2, expanded_CV1)))
best_result = results[0]
for result in results:
if result[2] > best_result[2]:
best_result = result
final_score = percentage_correct_classifications(best_result[0], expanded_test)
return (best_result, final_score)
def reglinear(InputFileName, inclusion_list = None):
raw_data = load_data(InputFileName)
training_data = append_features(raw_data)
expander = FeatureExpander(training_data)
if not inclusion_list:
inclusion_list = []
inclusion_list.append(1) # last sv
inclusion_list.append(1) # last change in sv
inclusion_list.append(0) # mean of prev 10 rows sv
inclusion_list.append(1) # std dev of prev 10 rows sv
inclusion_list.append(0) # last sp
inclusion_list.append(0) # last change in sp
inclusion_list.append(2) # mean of prev 10 rows sp
inclusion_list.append(0) # std dev of prev 10 rows sp
expanded = expander.expand_features(inclusion_list)
write_to_file(expanded, fp_out)
[expanded_CV1, expanded_CV2, expanded_test] = split_data_3_folds(expanded)
results = []
lamb_resolution = 100
for lamb in [i/lamb_resolution for i in range(1,lamb_resolution)]:
print lamb
THETA_CV1 = regression(expanded_CV1, lamb)
THETA_CV2 = regression(expanded_CV2, lamb)
results.append((THETA_CV1, lamb, calc_mse(expanded_CV2, THETA_CV1)))
results.append((THETA_CV2, lamb, calc_mse(expanded_CV1, THETA_CV2)))
best_result = results[0]
for result in results:
if result[2] < best_result[2]:
best_result = result
final_score = calc_mse(expanded_test, best_result[0])
return (best_result, final_score)
