header = ret["header"]
X = common_utils.extract_features_from_rawdata(chunk, header,
args.period,
args.features)
Xs.append(X)
ys += y
Xs = np.concatenate(Xs, axis=0)
return (Xs, ys)
print "==> reading data and extracting features"
#chunk_size = 8000 # TODO: bigger chunk_size
(train_X,
train_y) = read_and_extract_features(train_reader,
train_reader.get_number_of_examples())
del train_reader
(val_X, val_y) = read_and_extract_features(val_reader,
val_reader.get_number_of_examples())
del val_reader
(test_X,
test_y) = read_and_extract_features(test_reader,
test_reader.get_number_of_examples())
del test_reader
print "==> imputing missing values"
# imput missing values
imputer = Imputer(missing_values=np.nan,
strategy='mean',
process_one_chunk("train", chunk_index)
cnt_trained = chunk_index - n_trained_chunks + 1
if (cnt_trained % 5 == 0):
val_loss = process_one_chunk("test", chunk_index)
if ((cnt_trained / 5) % args.save_every == 0):
state_name = 'states/%s.chunk%d.test%.8f.state' % (
network_name, chunk_index, val_loss)
print "==> saving ... %s" % state_name
network.save_params(state_name, chunk_index)
print "chunk %d took %.3fs" % (chunk_index,
float(time.time()) - start_time)
chunks_per_epoch = train_reader.get_number_of_examples() // chunk_size
if (cnt_trained % chunks_per_epoch == 0):
train_reader.random_shuffle()
val_reader.random_shuffle()
elif args.mode == 'test':
# ensure that the code uses test_reader
del train_reader
del val_reader
test_reader = DecompensationReader(
dataset_dir='../../data/decompensation/test/',
listfile='../../data/decompensation/test_listfile.csv')
n_batches = test_reader.get_number_of_examples() // args.batch_size
y_true = []
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--period', type=str, default='all', help='specifies which period extract features from',
choices=['first4days', 'first8days', 'last12hours', 'first25percent', 'first50percent', 'all'])
parser.add_argument('--features', type=str, default='all', help='specifies what features to extract',
choices=['all', 'len', 'all_but_len'])
args = parser.parse_args()
print(args)
# penalties = ['l2', 'l2', 'l2', 'l2', 'l2', 'l2', 'l1', 'l1', 'l1', 'l1', 'l1']
# Cs = [1.0, 0.1, 0.01, 0.001, 0.0001, 0.00001, 1.0, 0.1, 0.01, 0.001, 0.0001]
penalties = ['l2']
Cs = [0.001]
train_reader = DecompensationReader(dataset_dir='../../../data/decompensation/train/',
listfile='../../../data/decompensation/train_listfile.csv')
val_reader = DecompensationReader(dataset_dir='../../../data/decompensation/train/',
listfile='../../../data/decompensation/val_listfile.csv')
test_reader = DecompensationReader(dataset_dir='../../../data/decompensation/test/',
listfile='../../../data/decompensation/test_listfile.csv')
print('Reading data and extracting features ...')
n_train = min(100000, train_reader.get_number_of_examples())
n_val = min(100000, val_reader.get_number_of_examples())
(train_X, train_y, train_names, train_ts) = read_and_extract_features(
train_reader, n_train, args.period, args.features)
(val_X, val_y, val_names, val_ts) = read_and_extract_features(
val_reader, n_val, args.period, args.features)
(test_X, test_y, test_names, test_ts) = read_and_extract_features(
test_reader, test_reader.get_number_of_examples(), args.period, args.features)
print('Imputing missing values ...')
imputer = Imputer(missing_values=np.nan, strategy='mean', axis=0, verbose=0, copy=True)
imputer.fit(train_X)
train_X = np.array(imputer.transform(train_X), dtype=np.float32)
val_X = np.array(imputer.transform(val_X), dtype=np.float32)
test_X = np.array(imputer.transform(test_X), dtype=np.float32)
print('Normalizing the data to have zero mean and unit variance ...')
scaler = StandardScaler()
scaler.fit(train_X)
train_X = scaler.transform(train_X)
val_X = scaler.transform(val_X)
test_X = scaler.transform(test_X)
common_utils.create_directory('results')
for (penalty, C) in zip(penalties, Cs):
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty, C)
logreg = LogisticRegression(penalty=penalty, C=C, random_state=42)
logreg.fit(train_X, train_y)
with open(os.path.join('results', 'train_{}.json'.format(file_name)), "w") as res_file:
ret = print_metrics_binary(train_y, logreg.predict_proba(train_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
with open(os.path.join('results', 'val_{}.json'.format(file_name)), 'w') as res_file:
ret = print_metrics_binary(val_y, logreg.predict_proba(val_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
prediction = logreg.predict_proba(test_X)[:, 1]
with open(os.path.join('results', 'test_{}.json'.format(file_name)), 'w') as res_file:
ret = print_metrics_binary(test_y, prediction)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
save_results(test_names, test_ts, prediction, test_y, os.path.join('predictions', file_name + '.csv'))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--period',
type=str,
default='all',
help='specifies which period extract features from',
choices=[
'first4days', 'first8days', 'last12hours',
'first25percent', 'first50percent', 'all'
])
parser.add_argument('--features',
type=str,
default='all',
help='specifies what features to extract',
choices=['all', 'len', 'all_but_len'])
args = parser.parse_args()
print(args)
# penalties = ['l2', 'l2', 'l2', 'l2', 'l2', 'l2', 'l1', 'l1', 'l1', 'l1', 'l1']
# Cs = [1.0, 0.1, 0.01, 0.001, 0.0001, 0.00001, 1.0, 0.1, 0.01, 0.001, 0.0001]
penalties = ['l2']
Cs = [0.001]
train_reader = DecompensationReader(
dataset_dir='../../../data/decompensation/train/',
listfile='../../../data/decompensation/train_listfile.csv')
val_reader = DecompensationReader(
dataset_dir='../../../data/decompensation/train/',
listfile='../../../data/decompensation/val_listfile.csv')
test_reader = DecompensationReader(
dataset_dir='../../../data/decompensation/test/',
listfile='../../../data/decompensation/test_listfile.csv')
print('Reading data and extracting features ...')
n_train = min(100000, train_reader.get_number_of_examples())
n_val = min(100000, val_reader.get_number_of_examples())
(train_X, train_y, train_names,
train_ts) = read_and_extract_features(train_reader, n_train, args.period,
args.features)
(val_X, val_y, val_names,
val_ts) = read_and_extract_features(val_reader, n_val, args.period,
args.features)
(test_X, test_y, test_names,
test_ts) = read_and_extract_features(test_reader,
test_reader.get_number_of_examples(),
args.period, args.features)
print('Imputing missing values ...')
imputer = Imputer(missing_values=np.nan,
strategy='mean',
axis=0,
verbose=0,
copy=True)
imputer.fit(train_X)
train_X = np.array(imputer.transform(train_X), dtype=np.float32)
val_X = np.array(imputer.transform(val_X), dtype=np.float32)
test_X = np.array(imputer.transform(test_X), dtype=np.float32)
print('Normalizing the data to have zero mean and unit variance ...')
scaler = StandardScaler()
scaler.fit(train_X)
train_X = scaler.transform(train_X)
val_X = scaler.transform(val_X)
test_X = scaler.transform(test_X)
common_utils.create_directory('results')
for (penalty, C) in zip(penalties, Cs):
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty,
C)
logreg = LogisticRegression(penalty=penalty, C=C, random_state=42)
logreg.fit(train_X, train_y)
with open(os.path.join('results', 'train_{}.json'.format(file_name)),
"w") as res_file:
ret = print_metrics_binary(train_y, logreg.predict_proba(train_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
with open(os.path.join('results', 'val_{}.json'.format(file_name)),
'w') as res_file:
ret = print_metrics_binary(val_y, logreg.predict_proba(val_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
prediction = logreg.predict_proba(test_X)[:, 1]
with open(os.path.join('results', 'test_{}.json'.format(file_name)),
'w') as res_file:
ret = print_metrics_binary(test_y, prediction)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
save_results(test_names, test_ts, prediction, test_y,
os.path.join('predictions', file_name + '.csv'))
# ensure that the code uses test_reader
del train_data_gen
del val_data_gen
if args.deep_supervision:
del train_data_loader
del val_data_loader
else:
del train_reader
del val_reader
test_reader = DecompensationReader(
dataset_dir='../../data/decompensation/test/',
listfile='../../data/decompensation/test_listfile.csv')
test_nbatches = test_reader.get_number_of_examples() // args.batch_size
test_nbatches = 10000
test_data_gen = utils.BatchGen(test_reader, discretizer, normalizer,
args.batch_size, test_nbatches)
labels = []
predictions = []
for i in range(test_nbatches):
print "\rpredicting {} / {}".format(i, test_nbatches),
x, y = next(test_data_gen)
x = np.array(x)
pred = model.predict_on_batch(x)[:, 0]
predictions += list(pred)
labels += list(y)
metrics.print_metrics_binary(labels, predictions)
with open("activations.txt", "w") as fout:
Xs = np.concatenate(Xs, axis=0)
return (Xs, ys)
print "==> reading data and extracting features"
chunk_size = 100000 # TODO: bigger chunk_size
(train_X, train_y) = read_and_extract_features(train_reader, chunk_size)
del train_reader
(val_X, val_y) = read_and_extract_features(val_reader, chunk_size)
del val_reader
(test_X,
test_y) = read_and_extract_features(test_reader,
test_reader.get_number_of_examples())
del test_reader
print "==> imputing missing values"
# imput missing values
imputer = Imputer(missing_values=np.nan,
strategy='mean',
axis=0,
verbose=0,
copy=True)
imputer.fit(train_X)
train_X = np.array(imputer.transform(train_X), dtype=np.float32)
val_X = np.array(imputer.transform(val_X), dtype=np.float32)
test_X = np.array(imputer.transform(test_X), dtype=np.float32)
print "==> normalizing data"