def do_cross_validation():
summaries = []
for pipeline in pipelines:
for (classifier, classifier_name) in classifiers:
print 'Using pipeline %s with classifier %s' % (pipeline.get_name(), classifier_name)
scores = []
for target in targets:
print 'Processing %s (classifier %s)' % (target, classifier_name)
task_core = TaskCore(cached_data_loader=cached_data_loader, data_dir=data_dir,
target=target, pipeline=pipeline,
# target=target, pipeline=pipeline,
classifier_name=classifier_name, classifier=classifier,
normalize=should_normalize(classifier), gen_preictal=pipeline.gen_preictal,
cv_ratio=cv_ratio)
data = CrossValidationScoreTask(task_core).run()
score = data.score
scores.append(score)
print '%.3f' % score
if len(scores) > 0:
name = pipeline.get_name() + '_' + classifier_name
summary = get_score_summary(name, scores)
summaries.append((summary, np.mean(scores)))
print summary
print_results(summaries)
def train_full_model(make_predictions):
for pipeline in pipelines:
for (classifier, classifier_name) in classifiers:
print 'Using pipeline %s with classifier %s' % (pipeline.get_name(), classifier_name)
guesses = ['clip,seizure,early']
classifier_filenames = []
for target in targets:
task_core = TaskCore(cached_data_loader=cached_data_loader, data_dir=data_dir,
target=target, pipeline=pipeline,
classifier_name=classifier_name, classifier=classifier,
normalize=should_normalize(classifier), gen_ictal=pipeline.gen_ictal,
cv_ratio=cv_ratio)
if make_predictions:
predictions = MakePredictionsTask(task_core).run()
guesses.append(predictions.data)
else:
task = TrainClassifierTask(task_core)
task.run()
classifier_filenames.append(task.filename())
if make_predictions:
filename = 'submission%d-%s_%s.csv' % (ts, classifier_name, pipeline.get_name())
filename = os.path.join(submission_dir, filename)
with open(filename, 'w') as f:
print >> f, '\n'.join(guesses)
print 'wrote', filename
else:
print 'Trained classifiers ready in %s' % cache_dir
for filename in classifier_filenames:
print os.path.join(cache_dir, filename + '.pickle')
def do_cross_validation():
for pipeline in pipelines:
for (classifier, classifier_name) in classifiers:
print 'Using pipeline %s with classifier %s' % (
pipeline.get_name(), classifier_name)
scores = []
for target in targets:
print 'Processing %s (classifier %s)' % (target,
classifier_name)
task_core = TaskCore(
cached_data_loader=cached_data_loader,
data_dir=data_dir,
target=target,
pipeline=pipeline,
classifier_name=classifier_name,
classifier=classifier,
normalize=should_normalize(classifier),
gen_ictal=pipeline.gen_ictal,
cv_ratio=cv_ratio)
data = CrossValidationScoreTask(task_core).run()
score = data.score
scores.append(score)
print target, 'Seizure_AUC=', data.S_auc, 'Early_AUC=', data.E_auc
def do_cross_validation():
summaries = []
for pipeline in pipelines:
for (classifier, classifier_name) in classifiers:
print('Using pipeline %s with classifier %s' %
(pipeline.get_name(), classifier_name))
scores = []
S_scores = []
E_scores = []
for target in targets:
print('Processing %s (classifier %s)' %
(target, classifier_name))
task_core = TaskCore(
cached_data_loader=cached_data_loader,
data_dir=data_dir,
target=target,
pipeline=pipeline,
classifier_name=classifier_name,
classifier=classifier,
normalize=should_normalize(classifier),
gen_ictal=pipeline.gen_ictal,
cv_ratio=cv_ratio)
data = CrossValidationScoreTask(task_core).run()
score = data.score
scores.append(score)
print('%.3f' % score, 'S=%.4f' % data.S_auc,
'E=%.4f' % data.E_auc)
S_scores.append(data.S_auc)
E_scores.append(data.E_auc)
if len(scores) > 0:
name = pipeline.get_name() + '_' + classifier_name
summary = get_score_summary(name, scores)
summaries.append((summary, np.mean(scores)))
print(summary)
if len(S_scores) > 0:
name = pipeline.get_name() + '_' + classifier_name
summary = get_score_summary(name, S_scores)
print('S', summary)
if len(E_scores) > 0:
name = pipeline.get_name() + '_' + classifier_name
summary = get_score_summary(name, E_scores)
print('E', summary)
print_results(summaries)
def train_full_model(make_predictions):
for pipeline in pipelines:
for (classifier, classifier_name) in classifiers:
print('Using pipeline %s with classifier %s' %
(pipeline.get_name(), classifier_name))
guesses = ['clip,preictal']
classifier_filenames = []
plot2file = PdfPages(
os.path.join(figure_dir,
('figure%d-_%s_%s_.pdf' %
(ts, classifier_name, pipeline.get_name()))))
for target in targets:
task_core = TaskCore(
cached_data_loader=cached_data_loader,
data_dir=data_dir,
target=target,
pipeline=pipeline,
classifier_name=classifier_name,
classifier=classifier,
normalize=should_normalize(classifier),
gen_preictal=pipeline.gen_preictal,
cv_ratio=cv_ratio,
plot2file=plot2file)
if make_predictions:
predictions = MakePredictionsTask(task_core).run()
guesses.append(predictions.data)
else:
task = TrainClassifierTask(task_core)
task.run()
classifier_filenames.append(task.filename())
if make_predictions:
filename = 'submission%d-%s_%s.csv' % (ts, classifier_name,
pipeline.get_name())
filename = os.path.join(submission_dir, filename)
with open(filename, 'w') as f:
print('\n'.join(guesses), file=f)
print('wrote', filename)
else:
print('Trained classifiers ready in %s' % cache_dir)
for filename in classifier_filenames:
print(os.path.join(cache_dir, filename + '.pickle'))
plot2file.close()
def train_full_model(make_predictions):
for pipeline in pipelines:
for classifier in classifiers:
print 'Using pipeline %s with classifier %s' % (
pipeline.get_name(), classifier)
guesses = ['File,Class']
classifier_filenames = []
#plot2file = PdfPages(os.path.join(figure_dir, ('figure%d-_%s_%s_.pdf' % (ts, classifier, pipeline.get_name()))))
for target in targets:
task_core = TaskCore(
cached_data_loader=cached_data_loader,
data_dir=data_dir,
target=target,
pipeline=pipeline,
classifier=classifier,
normalize=should_normalize(classifier),
gen_preictal=pipeline.gen_preictal,
cv_ratio=cv_ratio,
bin_size=bin_size)
if make_predictions:
predictions = MakePredictionsTask(task_core).run()
guesses.append(predictions.data)
else:
# task = TrainClassifierTask(task_core)
# task.run()
# classifier_filenames.append(task.filename())
print 'not implemented'
if make_predictions:
filename = 'submission%d-%s_%s.csv' % (ts, classifier,
pipeline.get_name())
filename = os.path.join(submission_dir, filename)
with open(filename, 'w') as f:
print >> f, '\n'.join(guesses)
print 'wrote', filename
else:
print 'Trained classifiers ready in %s' % cache_dir
for filename in classifier_filenames:
print os.path.join(cache_dir, filename + '.pickle')
def predict_all(make_predictions):
for pipeline in pipelines:
for (classifier, classifier_name) in classifiers:
print('Using pipeline %s with classifier %s' %
(pipeline.get_name(), classifier_name))
lines = ['clip,preictal']
subjectID = 0
X_train = y_train = X_test = test_size = []
for target in targets:
task_core = TaskCore(
cached_data_loader=cached_data_loader,
data_dir=data_dir,
target=target,
pipeline=pipeline,
classifier_name=classifier_name,
classifier=classifier,
normalize=should_normalize(classifier),
gen_preictal=pipeline.gen_preictal,
cv_ratio=cv_ratio)
data = GetCrossSubjectDataTask(task_core).run()
# a = np.shape(data.X_test)[0]
test_size.append(np.shape(data.X_test)[0])
if subjectID > 0:
X_train = np.concatenate((X_train, data.X_train),
axis=0)
y_train = np.concatenate((y_train, data.y_train),
axis=0)
X_test = np.concatenate((X_test, data.X_test), axis=0)
else:
X_train = data.X_train
y_train = data.y_train
X_test = data.X_test
subjectID += 1
#Training
task_core = TaskCore(cached_data_loader=cached_data_loader,
data_dir=data_dir,
target=[],
pipeline=pipeline,
classifier_name=classifier_name,
classifier=classifier,
normalize=should_normalize(classifier),
gen_preictal=pipeline.gen_preictal,
cv_ratio=cv_ratio)
y_train = np.ceil(0.1 * y_train)
y_train.astype('int_')
if should_normalize(classifier):
X_train, temp = normalize_data(X_train, X_train)
print("Training ...")
print('Dim', np.shape(X_train), np.shape(y_train))
start = time.get_seconds()
classifier.fit(X_train, y_train)
elapsedSecs = time.get_seconds() - start
print("t=%ds" % int(elapsedSecs))
y_estimate = classifier.predict_proba(X_train)
lr = LogisticRegression(random_state=0)
lr.fit(y_estimate, y_train)
predictions_proba = classifier.predict_proba(X_test)
predictions_calibrated = lr.predict_proba(predictions_proba)
#output
m = 0
totalSample = 12
startIdx = 0
for target in targets:
for i in range(test_size[m] / totalSample):
j = i + 1
if j < 10:
nstr = '000%d' % j
elif j < 100:
nstr = '00%d' % j
elif j < 1000:
nstr = '0%d' % j
else:
nstr = '%d' % j
preictalOverAllSample = 0
for k in range(totalSample):
p = predictions_calibrated[i * totalSample + k +
startIdx]
preictal = translate_prediction(p)
preictalOverAllSample += preictal / totalSample
newline = '%s_test_segment_%s.mat,%.15f' % (
target, nstr, preictalOverAllSample)
lines.append(newline)
print(newline)
startIdx = startIdx + test_size[m]
m += 1
filename = 'submission%d-%s_%s.csv' % (ts, classifier_name,
pipeline.get_name())
filename = os.path.join(submission_dir, filename)
with open(filename, 'w') as f:
print('\n'.join(lines), file=f)
print('wrote', filename)