def create_folds(file_path):
"""Creates 10 folds for cross validation
:param file_path: file path to save the folds
:type file_path: str
:return: None
"""
data = read_adhd_data()
data = data[data['class'] != 'ADHD-Hyperactive/Impulsive']
stats = find_statistics('data/ADHD200_CC200/', 'data/adhd_stats.pkl')
subject_ids = data.network_name.values.tolist()
subject_graph_files = os.listdir('data/ADHD200_CC200/')
subject_ids = [
subject for subject in subject_ids
if subject + '_connectivity_matrix_file.txt' in subject_graph_files
]
dataset = ADHD('ADHD200_CC200', subject_ids, data, stats)
X = subject_ids
y = []
for subject_id in subject_ids:
encoded_class = dataset.get_brain_class(subject_id)
class_id = np.argmax(encoded_class)
y.append(class_id)
X = np.array(X)
y = np.array(y)
skf = StratifiedKFold(n_splits=10)
folds = [([subject_ids[i] for i in train.tolist()],
[subject_ids[i] for i in test.tolist()])
for train, test in skf.split(X, y)]
with open(file_path, 'wb') as f:
pickle.dump(folds, f, pickle.HIGHEST_PROTOCOL)
def test_brain_convolution_model(test_subject_ids, trained_model):
data = read_adhd_data()
stats = find_statistics('data/ADHD200_CC200/', 'data/adhd_stats.pkl')
test_dataset = ADHD('ADHD200_CC200', test_subject_ids,
data.loc[data['network_name'].isin(test_subject_ids)],
stats)
data_adj = []
data_features = []
for subject_id in test_subject_ids:
adj, features, classes = test_dataset.get_brain_graph_and_class(
subject_id)
data_features.append(features)
data_adj.append(adj)
predictions = trained_model.predict(
[np.array(data_features), np.array(data_adj)])
return predictions
def train_brain_convolution_model(subject_ids):
data = read_adhd_data()
stats = find_statistics('data/ADHD200_CC200/', 'data/adhd_stats.pkl')
train_subject_ids = subject_ids
train_dataset = ADHD(
'ADHD200_CC200', train_subject_ids,
data.loc[data['network_name'].isin(train_subject_ids)], stats)
config = Config(node_dim=3, num_classes=3, batch_size=1)
train_data_generator = data_generator(train_dataset, config, shuffle=True)
model = BrainConvolutionModel(config).build()
model.summary()
optimizer = Adam(0.001, amsgrad=True, decay=config.WEIGHT_DECAY)
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
model.fit_generator(train_data_generator, 10, 50)
return model
def get_data(subject_ids):
"""Create dataset for training and testing the classifiers
:param subject_ids: list of subject ids from the dataset
:type subject_ids: list(str)
:return: features (flatten matrix), classes
:rtype: numpy.array, numpy.array
"""
data = read_adhd_data()
data = data[data['class'] != 'ADHD-Hyperactive/Impulsive']
stats = find_statistics('data/ADHD200_CC200/', 'data/adhd_stats.pkl')
dataset = ADHD('ADHD200_CC200', subject_ids, data, stats)
x = []
y = []
for subject_id in subject_ids:
matrix, node_features, encoded_class = dataset.get_brain_graph_and_class(
subject_id)
adj = matrix[np.triu_indices(matrix.shape[0], k=1)]
decoded_class = np.argmax(encoded_class)
x.append(adj)
y.append(decoded_class)
return np.array(x), np.array(y)
:param split: ratio value for validation data
:type split: float
:return: train subject ids, validation subject ids
:rtype: list(str), list(str)
"""
size = len(subject_ids)
split_index = int(round(size * (1 - split)))
random.shuffle(subject_ids)
train_ids = subject_ids[:split_index]
validation_ids = subject_ids[split_index:]
return train_ids, validation_ids
if __name__ == '__main__':
data = read_functional_connectomes_data()
stats = find_statistics('data/1000_Functional_Connectomes/',
'data/1000_functional_connectomes_stats.pkl')
subject_ids = data.network_name.values.tolist()
subject_graph_files = os.listdir('data/1000_Functional_Connectomes/')
subject_ids = [
subject for subject in subject_ids
if subject + '_connectivity_matrix_file.txt' in subject_graph_files
]
train_subject_ids, val_subject_ids = train_validation_split(
subject_ids, 0.1)
train_dataset = FunctionalConnectomes(
'1000_functional_connectomes', train_subject_ids,
data.loc[data['network_name'].isin(train_subject_ids)], stats)
validation_dataset = FunctionalConnectomes(
'1000_functional_connectomes', val_subject_ids,
data.loc[data['network_name'].isin(val_subject_ids)], stats)
config = Config(node_dim=3, num_classes=2, batch_size=3)
:type split: float
:return: train subject ids, validation subject ids
:rtype: list(str), list(str)
"""
size = len(subject_ids)
split_index = int(round(size * (1 - split)))
random.shuffle(subject_ids)
train_ids = subject_ids[:split_index]
validation_ids = subject_ids[split_index:]
return train_ids, validation_ids
if __name__ == '__main__':
data = read_adhd_data()
data = data[data['class'] != 'ADHD-Hyperactive/Impulsive']
stats = find_statistics('data/ADHD200_CC200/', 'data/adhd_stats.pkl')
subject_ids = data.network_name.values.tolist()
subject_graph_files = os.listdir('data/ADHD200_CC200/')
subject_ids = [
subject for subject in subject_ids
if subject + '_connectivity_matrix_file.txt' in subject_graph_files
]
train_subject_ids, val_subject_ids = train_validation_split(
subject_ids, 0.1)
train_dataset = ADHD(
'ADHD200_CC200', train_subject_ids,
data.loc[data['network_name'].isin(train_subject_ids)], stats)
validation_dataset = ADHD(
'ADHD200_CC200', val_subject_ids,
data.loc[data['network_name'].isin(val_subject_ids)], stats)
config = Config(node_dim=3, num_classes=3, batch_size=2)