def TrainingModels(target_label, model_file_name, training_list):
'''Randomly select num_training records to train, and test others.'''
qt = QTloader()
record_list = qt.getreclist()
testing_list = list(set(record_list) - set(training_list))
random_forest_config = dict(max_depth=10)
walker = RandomWalker(target_label=target_label,
random_forest_config=random_forest_config,
random_pattern_file_name=os.path.join(
os.path.dirname(model_file_name),
'random_pattern.json'))
start_time = time.time()
for record_name in training_list:
print 'Collecting features from record %s.' % record_name
sig = qt.load(record_name)
walker.collect_training_data(sig['sig'], qt.getExpert(record_name))
print 'random forest start training(%s)...' % target_label
walker.training()
print 'trianing used %.3f seconds' % (time.time() - start_time)
import joblib
start_time = time.time()
walker.save_model(model_file_name)
print 'Serializing model time cost %f' % (time.time() - start_time)
def TrainingModels(target_label, model_file_name, training_list):
'''Randomly select num_training records to train, and test others.
CP: Characteristic points
'''
qt = QTloader()
record_list = qt.getreclist()
testing_list = list(set(record_list) - set(training_list))
random_forest_config = dict(max_depth=10)
walker = RandomWalker(target_label=target_label,
random_forest_config=random_forest_config,
random_pattern_file_name=os.path.join(
os.path.dirname(model_file_name),
'random_pattern.json'))
start_time = time.time()
for record_name in training_list:
CP_file_name = os.path.join(
'/home/alex/code/Python/EcgCharacterPointMarks', target_label,
'%s_poslist.json' % record_name)
# Add expert marks
expert_marks = qt.getExpert(record_name)
CP_marks = [x for x in expert_marks if x[1] == target_label]
if len(CP_marks) == 0:
continue
# Add manual labels if possible
if os.path.exists(CP_file_name) == True:
with open(CP_file_name, 'r') as fin:
CP_info = json.load(fin)
poslist = CP_info['poslist']
if len(poslist) == 0:
continue
CP_marks.extend(zip(poslist, [
target_label,
] * len(poslist)))
print 'Collecting features from record %s.' % record_name
sig = qt.load(record_name)
walker.collect_training_data(sig['sig'], CP_marks)
print 'random forest start training(%s)...' % target_label
walker.training()
print 'trianing used %.3f seconds' % (time.time() - start_time)
import joblib
start_time = time.time()
walker.save_model(model_file_name)
print 'Serializing model time cost %f' % (time.time() - start_time)
def TrainingModels_Changgeng(target_label, model_file_name):
'''Randomly select num_training records to train, and test others.
CP: Characteristic points
'''
from changgengLoader import ECGLoader
ecg = ECGLoader(500, current_folderpath)
random_forest_config = dict(max_depth=10)
walker = RandomWalker(target_label=target_label,
random_forest_config=random_forest_config,
random_pattern_file_name=os.path.join(
os.path.dirname(model_file_name),
'random_pattern.json'))
start_time = time.time()
for record_ind in xrange(0, len(ecg.P_faillist)):
record_name = ecg.P_faillist[record_ind]
CP_file_name = os.path.join(current_folderpath, 'data', 'labels',
target_label,
'%s_poslist.json' % record_name)
CP_marks = []
# Add manual labels if possible
if os.path.exists(CP_file_name) == True:
with open(CP_file_name, 'r') as fin:
print 'Collecting features from record %s.' % record_name
CP_info = json.load(fin)
poslist = CP_info['poslist']
if len(poslist) == 0:
continue
CP_marks.extend(zip(poslist, [
target_label,
] * len(poslist)))
sig = ecg.load(record_ind)
walker.collect_training_data(sig[0], CP_marks)
print 'random forest start training(%s)...' % target_label
walker.training()
print 'trianing used %.3f seconds' % (time.time() - start_time)
import joblib
start_time = time.time()
walker.save_model(model_file_name)
print 'Serializing model time cost %f' % (time.time() - start_time)
def TrainingModels(target_label, model_file_name, training_list):
'''Randomly select num_training records to train, and test others.'''
qt = QTloader()
record_list = qt.getreclist()
testing_list = list(set(record_list) - set(training_list))
random_forest_config = dict(max_depth=10)
walker = RandomWalker(target_label=target_label,
random_forest_config=random_forest_config,
random_pattern_file_name=os.path.join(
os.path.dirname(model_file_name),
'random_pattern.json'))
start_time = time.time()
for record_name in training_list:
Tonset_file_name = os.path.join(
'/home/alex/code/Python/Tonset/results',
'%s_poslist.json' % record_name)
if os.path.exists(Tonset_file_name) == True:
with open(Tonset_file_name, 'r') as fin:
Tonset_info = json.load(fin)
poslist = Tonset_info['poslist']
if len(poslist) == 0:
continue
Tonset_marks = zip(poslist, [
'Tonset',
] * len(poslist))
else:
expert_marks = qt.getExpert(record_name)
Tonset_marks = [x for x in expert_marks if x[1] == 'Tonset']
if len(Tonset_marks) == 0:
continue
print 'Collecting features from record %s.' % record_name
sig = qt.load(record_name)
walker.collect_training_data(sig['sig'], Tonset_marks)
print 'random forest start training(%s)...' % target_label
walker.training()
print 'trianing used %.3f seconds' % (time.time() - start_time)
import joblib
start_time = time.time()
walker.save_model(model_file_name)
print 'Serializing model time cost %f' % (time.time() - start_time)
def TrainingModels_Changgeng(target_label, model_file_name):
'''Randomly select num_training records to train, and test others.
CP: Characteristic points
'''
import glob
annot_jsonIDs = glob.glob(
os.path.join(current_folderpath, 'data', 'labels', target_label,
'*.json'))
annot_jsonIDs = [os.path.split(x)[-1] for x in annot_jsonIDs]
annot_jsonIDs = [x.split('.')[0] for x in annot_jsonIDs]
# skip failed records
faillist = [
8999, 8374, 6659, 6655, 6059, 5395, 1401, 1269, 737, 75, 9524, 9476
]
faillist = [str(x) for x in faillist]
annot_jsonIDs = list(set(annot_jsonIDs) - set(faillist))
from changgengLoader import ECGLoader
ecg = ECGLoader(500, current_folderpath)
random_forest_config = dict(max_depth=10)
walker = RandomWalker(target_label=target_label,
random_forest_config=random_forest_config,
random_pattern_file_name=os.path.join(
os.path.dirname(model_file_name),
'random_pattern.json'))
start_time = time.time()
for record_ind in xrange(0, len(annot_jsonIDs)):
record_name = annot_jsonIDs[record_ind]
CP_file_name = os.path.join(current_folderpath, 'data', 'labels',
target_label, '%s.json' % record_name)
CP_marks = []
# Add manual labels if possible
if os.path.exists(CP_file_name) == True:
with open(CP_file_name, 'r') as fin:
CP_info = json.load(fin)
poslist = CP_info['poslist']
poslist = [int(x / 2) for x in poslist]
mat_file_name = CP_info['mat_file_name']
if len(poslist) == 0:
continue
CP_marks.extend(zip(poslist, [
target_label,
] * len(poslist)))
print 'Collecting features from record %s.' % record_name
sig = ecg.load(record_name)
raw_sig = sig[0]
import scipy.signal
resampled_sig = scipy.signal.resample_poly(raw_sig, 1, 2)
raw_sig = resampled_sig
# debug
# plt.figure(1)
# plt.plot(raw_sig, label = 'signal')
# plt.plot(xrange(0, len(raw_sig), 2), resampled_sig, label = 'resmaple')
# plt.legend()
# plt.grid(True)
# plt.title(record_name)
# plt.show()
walker.collect_training_data(raw_sig, CP_marks)
# Add QT training samples
# ContinueAddQtTrainingSamples(walker, target_label)
print 'random forest start training(%s)...' % target_label
walker.training()
print 'trianing used %.3f seconds' % (time.time() - start_time)
import joblib
start_time = time.time()
walker.save_model(model_file_name)
print 'Serializing model time cost %f' % (time.time() - start_time)