}, "cervix-20000-64"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-20000-16"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-50000-64"],
['KMeans', {
'kmeans_model': True,
'mask': True
}, "channel-20000-64"],
]
print('Loading descriptors...')
manager = DescriptorManager(os.path.join(wdir, 'descriptors'))
cervixes_data = []
cervixes_labels = []
for c in cervixes:
cervixes_data.append(manager.buildFeatures(c['code_name'], configs))
cervixes_labels.append(c['type'])
print('Feature length: ' + str(cervixes_data[0].shape))
FOLD_SIZE = 5
BATCH_SIZE = len(cervixes_data) // FOLD_SIZE
WIN_PROB = 0.66
LOS_PROB = (1 - WIN_PROB) / 2
print('Start %d-fold cross-validation' % FOLD_SIZE)
print('Manual win probability: %f' % WIN_PROB)
#random.shuffle(cervixes)
average_acc = 0
average_log_loss_cls = 0
average_log_loss_man = 0
# ['LBP', {'radius': 16, 'numPoints': 48, 'mask': True}, "channel-mask"],
# ['LBP', {'radius': 32, 'numPoints': 160, 'mask': True}, "channel-mask"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-20000-512"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-20000-256"],
['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-20000-64"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-20000-16"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "cervix-50000-64"],
# ['KMeans', {'kmeans_model': True, 'mask': True}, "channel-20000-64"],
]
print('Loading descriptors...')
train_data = []
train_labels = []
for t in train:
train_data.append(manager.buildFeatures(t['code_name'], configs))
train_labels.append(t['type'])
valid_data = []
valid_labels = []
for v in valid:
valid_data.append(manager.buildFeatures(v['code_name'], configs))
valid_labels.append(v['type'])
print('Data loaded, feature length: ' + str(train_data[0].shape))
#model = svm.LinearSVC(C=100.0, random_state=42)
#model = RandomForestClassifier(max_depth = 15, n_estimators=500, max_features = 100, random_state=42)
model = RandomForestClassifier(max_depth = 15, n_estimators=500, max_features = 128, random_state=42)
# model = AdaBoostClassifier(learning_rate=0.1, n_estimators=1000)
model.fit(train_data, train_labels)
