def _load_data(self, testfold=4):
train_reader = InHospitalMortalityReader(
dataset_dir='mimic3-benchmarks/data/in-hospital-mortality/train/',
listfile=
'mimic3-benchmarks/data/in-hospital-mortality/train_listfile.csv',
period_length=48.0)
val_reader = InHospitalMortalityReader(
dataset_dir='mimic3-benchmarks/data/in-hospital-mortality/train/',
listfile=
'mimic3-benchmarks/data/in-hospital-mortality/val_listfile.csv',
period_length=48.0)
test_reader = InHospitalMortalityReader(
dataset_dir='mimic3-benchmarks/data/in-hospital-mortality/test/',
listfile=
'mimic3-benchmarks/data/in-hospital-mortality/test_listfile.csv',
period_length=48.0)
discretizer = Discretizer(timestep=float(4),
store_masks=True,
imput_strategy='previous',
start_time='zero')
discretizer_header = discretizer.transform(
train_reader.read_example(0)[0])[1].split(',')
cont_channels = [
i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1
]
normalizer = Normalizer(
fields=cont_channels) # choose here onlycont vs all
normalizer.load_params(
'mimic3-benchmarks/mimic3models/in_hospital_mortality/'
'ihm_ts%s.input_str:%s.start_time:zero.normalizer' %
('2.0', 'previous'))
# normalizer=None
train_raw = utils.load_data(train_reader, discretizer, normalizer,
False)
val_raw = utils.load_data(val_reader, discretizer, normalizer, False)
test_raw = utils.load_data(test_reader, discretizer, normalizer, False)
# To split into
def preprocess(the_raw_set):
x, y = the_raw_set
x = x.astype(np.float32, copy=False)
y = np.array(y)
return x, y
train_raw = preprocess(train_raw)
val_raw = preprocess(val_raw)
test_raw = preprocess(test_raw)
return train_raw, val_raw, test_raw
small_part=args.small_part)
else:
train_reader = LengthOfStayReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'train_listfile.csv'))
val_reader = LengthOfStayReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'val_listfile.csv'))
discretizer = Discretizer(timestep=args.timestep,
store_masks=True,
impute_strategy='previous',
start_time='zero')
if args.deep_supervision:
discretizer_header = discretizer.transform(
train_data_loader._data["X"][0])[1].split(',')
else:
discretizer_header = discretizer.transform(
train_reader.read_example(0)["X"])[1].split(',')
cont_channels = [
i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1
]
normalizer = Normalizer(
fields=cont_channels) # choose here which columns to standardize
normalizer_state = args.normalizer_state
if normalizer_state is None:
normalizer_state = 'los_ts{}.input_str:previous.start_time:zero.n5e4.normalizer'.format(
args.timestep)
normalizer_state = os.path.join(os.path.dirname(__file__),
normalizer_state)
def dataset_reader(phase, args, target_repl=False):
if phase == "train":
#% Build readers & discretizers
train_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'train_listfile.csv'),
period_length=48.0)
val_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'val_listfile.csv'),
period_length=48.0)
discretizer = Discretizer(timestep=float(args.timestep),
store_masks=True,
impute_strategy='previous',
start_time='zero')
discretizer_header = discretizer.transform(
train_reader.read_example(0)["X"])[1].split(',')
cont_channels = [
i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1
]
#%% Data normalization (by mean and variance)
normalizer = Normalizer(
fields=cont_channels) # choose here which columns to standardize
normalizer_state = args.normalizer_state
if normalizer_state is None:
normalizer_state = 'ihm_ts{}.input_str:{}.start_time:zero.normalizer'.format(
args.timestep, args.imputation)
normalizer_state = os.path.join(os.path.dirname(__file__),
normalizer_state)
normalizer.load_params(normalizer_state)
# args_dict = dict(args._get_kwargs()) #TODO: reverse
args_dict = {}
args_dict['header'] = discretizer_header
args_dict['task'] = 'ihm'
args_dict['target_repl'] = target_repl
#%% Read data
start = time()
print("Reading started")
train_raw = utils.load_data(train_reader,
discretizer,
normalizer,
args.small_part,
return_names=False)
val_raw = utils.load_data(val_reader,
discretizer,
normalizer,
args.small_part,
return_names=False)
if target_repl:
T = train_raw[0][0].shape[0]
def extend_labels(data):
data = list(data)
labels = np.array(data[1]) # (B,)
data[1] = [labels, None]
data[1][1] = np.expand_dims(labels,
axis=-1).repeat(T,
axis=1) # (B, T)
data[1][1] = np.expand_dims(data[1][1], axis=-1) # (B, T, 1)
return data
train_raw = extend_labels(train_raw)
val_raw = extend_labels(val_raw)
print("Reading finished after {} seconds".format(time() - start))
return (train_raw, val_raw)
else: ################################### TEST phase
test_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
test_raw = utils.load_data(test_reader,
discretizer,
normalizer,
args.small_part,
return_names=True)
return test_raw
train_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'train_listfile.csv'),
period_length=48.0)
val_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'mimicval_listfile.csv'),
period_length=48.0)
discretizer = Discretizer(timestep=float(args.timestep),
store_masks=True,
impute_strategy='previous',
start_time='zero')
discretizer_header = discretizer.transform(
train_reader.read_example(0)["X"])[1].split(',')
cont_channels = [
i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1
]
print('===>cont_channels: ', cont_channels)
normalizer = Normalizer(
fields=cont_channels) # choose here which columns to standardize
normalizer_state = args.normalizer_state
if normalizer_state is None:
normalizer_state = 'ihm_ts_{}_impute_{}_start_time_zero.normalizer'.format(
args.timestep, args.imputation)
normalizer_state = os.path.join(os.path.dirname(__file__),
normalizer_state)
normalizer.load_params(normalizer_state)
discretizer = Discretizer(timestep=float(args.timestep),
store_masks=True,
imput_strategy='previous',
start_time='zero')
N = train_reader.get_number_of_examples()
ret = common_utils.read_chunk(train_reader, N)
data = ret["X"]
ts = ret["t"]
labels = ret["y"]
names = ret["name"]
diseases_list = get_diseases(names, '/mnt/MIMIC-III-clean/data/')
diseases_embedding = disease_embedding(embeddings, word_indices, diseases_list)
discretizer_header = discretizer.transform(ret["X"][0])[1].split(',')
cont_channels = [
i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1
]
normalizer = Normalizer(fields=cont_channels) # choose here onlycont vs all
data = [
discretizer.transform_first_t_hours(X, end=t)[0]
for (X, t) in zip(data, ts)
]
[normalizer._feed_data(x=X) for X in data]
normalizer._use_params()
args_dict = dict(args._get_kwargs())
def mimic_loader(task='mortality', data_percentage=100):
if task == 'mortality':
print('loading mimic-iii in-hospital mortality dataset')
from mimic3models.in_hospital_mortality import utils
from mimic3benchmark.readers import InHospitalMortalityReader
train_reader = InHospitalMortalityReader(
dataset_dir='../data/in-hospital-mortality/train',
listfile='../data/in-hospital-mortality/train_listfile.csv',
period_length=48.0)
val_reader = InHospitalMortalityReader(
dataset_dir='../data/in-hospital-mortality/train',
listfile='../data/in-hospital-mortality/val_listfile.csv',
period_length=48.0)
test_reader = InHospitalMortalityReader(
dataset_dir='../data/in-hospital-mortality/test',
listfile='../data/in-hospital-mortality/test_listfile.csv',
period_length=48.0)
discretizer = Discretizer(timestep=float(1.0),
store_masks=True,
impute_strategy='previous',
start_time='zero')
discretizer_header = discretizer.transform(
train_reader.read_example(0)["X"])[1].split(',')
cont_channels = [
i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1
]
normalizer = Normalizer(
fields=cont_channels) # choose here which columns to standardize
normalizer_state = None
if normalizer_state is None:
normalizer_state = 'ihm_ts{}.input_str:{}.start_time:zero.normalizer'.format(
1.0, 'previous')
normalizer_state = os.path.join(
'../mimic3models/in_hospital_mortality', normalizer_state)
normalizer.load_params(normalizer_state)
headers = [
'Capillary refill rate->0.0', 'Capillary refill rate->1.0',
'Diastolic blood pressure', 'Fraction inspired oxygen',
'Glascow coma scale eye opening->To Pain',
'Glascow coma scale eye opening->3 To speech',
'Glascow coma scale eye opening->1 No Response',
'Glascow coma scale eye opening->4 Spontaneously',
'Glascow coma scale eye opening->None',
'Glascow coma scale eye opening->To Speech',
'Glascow coma scale eye opening->Spontaneously',
'Glascow coma scale eye opening->2 To pain',
'Glascow coma scale motor response->1 No Response',
'Glascow coma scale motor response->3 Abnorm flexion',
'Glascow coma scale motor response->Abnormal extension',
'Glascow coma scale motor response->No response',
'Glascow coma scale motor response->4 Flex-withdraws',
'Glascow coma scale motor response->Localizes Pain',
'Glascow coma scale motor response->Flex-withdraws',
'Glascow coma scale motor response->Obeys Commands',
'Glascow coma scale motor response->Abnormal Flexion',
'Glascow coma scale motor response->6 Obeys Commands',
'Glascow coma scale motor response->5 Localizes Pain',
'Glascow coma scale motor response->2 Abnorm extensn',
'Glascow coma scale total->11', 'Glascow coma scale total->10',
'Glascow coma scale total->13', 'Glascow coma scale total->12',
'Glascow coma scale total->15', 'Glascow coma scale total->14',
'Glascow coma scale total->3', 'Glascow coma scale total->5',
'Glascow coma scale total->4', 'Glascow coma scale total->7',
'Glascow coma scale total->6', 'Glascow coma scale total->9',
'Glascow coma scale total->8',
'Glascow coma scale verbal response->1 No Response',
'Glascow coma scale verbal response->No Response',
'Glascow coma scale verbal response->Confused',
'Glascow coma scale verbal response->Inappropriate Words',
'Glascow coma scale verbal response->Oriented',
'Glascow coma scale verbal response->No Response-ETT',
'Glascow coma scale verbal response->5 Oriented',
'Glascow coma scale verbal response->Incomprehensible sounds',
'Glascow coma scale verbal response->1.0 ET/Trach',
'Glascow coma scale verbal response->4 Confused',
'Glascow coma scale verbal response->2 Incomp sounds',
'Glascow coma scale verbal response->3 Inapprop words', 'Glucose',
'Heart Rate', 'Height', 'Mean blood pressure', 'Oxygen saturation',
'Respiratory rate', 'Systolic blood pressure', 'Temperature',
'Weight', 'pH', 'mask->Capillary refill rate',
'mask->Diastolic blood pressure', 'mask->Fraction inspired oxygen',
'mask->Glascow coma scale eye opening',
'mask->Glascow coma scale motor response',
'mask->Glascow coma scale total',
'mask->Glascow coma scale verbal response', 'mask->Glucose',
'mask->Heart Rate', 'mask->Height', 'mask->Mean blood pressure',
'mask->Oxygen saturation', 'mask->Respiratory rate',
'mask->Systolic blood pressure', 'mask->Temperature',
'mask->Weight', 'mask->pH'
]
print('start loading the data')
if data_percentage != 100: # accepted values: [10,20,30,40,50,60,70,80,90]
print('loading the partially covered testing data')
test_reader = InHospitalMortalityReader(
dataset_dir='../data/in-hospital-mortality/test_' +
str(data_percentage),
listfile='../data/in-hospital-mortality/test_listfile.csv',
period_length=48.0)
test_raw = utils.load_data(test_reader, discretizer, normalizer,
False)
x_test = np.copy(test_raw[0])
return x_test
# Read data
train_raw = utils.load_data(train_reader, discretizer, normalizer,
False)
val_raw = utils.load_data(val_reader, discretizer, normalizer, False)
test_raw = utils.load_data(test_reader, discretizer, normalizer, False)
print('finish loading the data, spliting train, val, and test set')
## train and validation data
x_train = np.copy(train_raw[0])
y_train = np.zeros((len(train_raw[1]), 2))
y_train[:, 1] = np.array(train_raw[1])
y_train[:, 0] = 1 - y_train[:, 1]
x_val = np.copy(val_raw[0])
y_val = np.zeros((len(val_raw[1]), 2))
y_val[:, 1] = np.array(val_raw[1])
y_val[:, 0] = 1 - y_val[:, 1]
x_test = np.copy(test_raw[0])
y_test = np.zeros((len(test_raw[1]), 2))
y_test[:, 1] = np.array(test_raw[1])
y_test[:, 0] = 1 - y_test[:, 1]
return [x_train, x_val, x_test, y_train, y_val, y_test]
target_repl = (args.target_repl_coef > 0.0 and args.mode == 'train')
# Build readers, discretizers, normalizers
train_reader = MultitaskReader(dataset_dir='../../data/multitask/train/',
listfile='../../data/multitask/train_listfile.csv')
val_reader = MultitaskReader(dataset_dir='../../data/multitask/train/',
listfile='../../data/multitask/val_listfile.csv')
discretizer = Discretizer(timestep=args.timestep,
store_masks=True,
imput_strategy='previous',
start_time='zero')
discretizer_header = discretizer.transform(train_reader.read_example(0)[0])[1].split(',')
cont_channels = [i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1]
normalizer = Normalizer(fields=cont_channels) # choose here onlycont vs all
normalizer.load_params('mult_ts%s.input_str:%s.start_time:zero.normalizer' % (args.timestep, args.imputation))
args_dict = dict(args._get_kwargs())
args_dict['header'] = discretizer_header
args_dict['ihm_pos'] = int(48.0 / args.timestep - 1e-6)
args_dict['target_repl'] = target_repl
# Build the model
print "==> using model {}".format(args.network)
model_module = imp.load_source(os.path.basename(args.network), args.network)
model = model_module.Network(**args_dict)
network = model # alias
target_repl = (args.target_repl_coef > 0.0 and args.mode == 'train')
# Build readers, discretizers, normalizers
train_reader = PhenotypingReader(dataset_dir='../../data/phenotyping/train/',
listfile='../../data/phenotyping/train_listfile.csv')
val_reader = PhenotypingReader(dataset_dir='../../data/phenotyping/train/',
listfile='../../data/phenotyping/val_listfile.csv')
discretizer = Discretizer(timestep=float(args.timestep),
store_masks=True,
imput_strategy='previous',
start_time='zero')
discretizer_header = discretizer.transform(train_reader.read_example(0)["X"])[1].split(',')
cont_channels = [i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1]
normalizer = Normalizer(fields=cont_channels) # choose here onlycont vs all
normalizer.load_params('ph_ts{}.input_str:previous.start_time:zero.normalizer'.format(args.timestep))
args_dict = dict(args._get_kwargs())
args_dict['header'] = discretizer_header
args_dict['task'] = 'ph'
args_dict['num_classes'] = 25
args_dict['target_repl'] = target_repl
# Build the model
print "==> using model {}".format(args.network)
model_module = imp.load_source(os.path.basename(args.network), args.network)
model = model_module.Network(**args_dict)
def main():
parser = argparse.ArgumentParser(description='Script for creating a normalizer state - a file which stores the '
'means and standard deviations of columns of the output of a '
'discretizer, which are later used to standardize the input of '
'neural models.')
parser.add_argument('--task', type=str,choices=['ihm', 'los'])
parser.add_argument('--timestep', type=float, default=1.0,
help="Rate of the re-sampling to discretize time-series.")
parser.add_argument('--impute_strategy', type=str, default='previous',
choices=['zero', 'next', 'previous', 'normal_value'],
help='Strategy for imputing missing values.')
parser.add_argument('--start_time', type=str, choices=['zero', 'relative'],
help='Specifies the start time of discretization. Zero means to use the beginning of '
'the ICU stay. Relative means to use the time of the first ICU event')
parser.add_argument('--store_masks', dest='store_masks', action='store_true',
help='Store masks that specify observed/imputed values.')
parser.add_argument('--no-masks', dest='store_masks', action='store_false',
help='Do not store that specify specifying observed/imputed values.')
parser.add_argument('--n_samples', type=int, default=-1, help='How many samples to use to estimates means and '
'standard deviations. Set -1 to use all training samples.')
parser.add_argument('--output_dir', type=str, help='Directory where the output file will be saved.',
default='.')
parser.add_argument('--data', type=str, required=True, help='Path to the task data.')
parser.set_defaults(store_masks=True)
args = parser.parse_args()
print(args)
# create the reader
reader = None
dataset_dir = os.path.join(args.data, 'train')
if args.task == 'ihm':
reader = InHospitalMortalityReader(dataset_dir=dataset_dir, period_length=48.0)
if args.task == 'los':
reader = LengthOfStayReader(dataset_dir=dataset_dir)
# create the discretizer
discretizer = Discretizer(timestep=args.timestep,
store_masks=args.store_masks,
impute_strategy=args.impute_strategy,
start_time=args.start_time)
discretizer_header = reader.read_example(0)['header']
continuous_channels = [i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1]
# create the normalizer
normalizer = Normalizer(fields=continuous_channels)
# read all examples and store the state of the normalizer
n_samples = args.n_samples
if n_samples == -1:
n_samples = reader.get_number_of_examples()
for i in range(n_samples):
if i % 1000 == 0:
print('Processed {} / {} samples'.format(i, n_samples), end='\r')
ret = reader.read_example(i)
data, new_header = discretizer.transform(ret['X'], end=ret['t'])
normalizer._feed_data(data)
print('\n')
file_name = '{}_ts_{:.1f}_impute_{}_start_time{}.normalizer'.format(
args.task, args.timestep, args.impute_strategy, args.start_time)
file_name = os.path.join(args.output_dir, file_name)
print('Saving the state in {} ...'.format(file_name))
normalizer._save_params(file_name)
val_data_loader = common_utils.DeepSupervisionDataLoader(dataset_dir='../../data/decompensation/train/',
listfile='../../data/decompensation/val_listfile.csv',
small_part=args.small_part)
else:
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')
discretizer = Discretizer(timestep=args.timestep,
store_masks=True,
imput_strategy='previous',
start_time='zero')
if args.deep_supervision:
discretizer_header = discretizer.transform(train_data_loader._data["X"][0])[1].split(',')
else:
discretizer_header = discretizer.transform(train_reader.read_example(0)["X"])[1].split(',')
cont_channels = [i for (i, x) in enumerate(discretizer_header) if x.find("->") == -1]
normalizer = Normalizer(fields=cont_channels) # choose here onlycont vs all
normalizer.load_params('decomp_ts{}.input_str:previous.n1e5.start_time:zero.normalizer'.format(args.timestep))
args_dict = dict(args._get_kwargs())
args_dict['header'] = discretizer_header
args_dict['task'] = 'decomp'
# Build the model
print "==> using model {}".format(args.network)
model_module = imp.load_source(os.path.basename(args.network), args.network)