def test(args, model):
"""Test model"""
test_filename = f"{args.input_dir}/{ext_utils.TEST}_{ext_utils.DATA_FILENAME}"
data, labels = list(np.load(test_filename).values())
names = [f"Feature {idx}" for idx in range(data.shape[2])]
predictions = model.predict(data, batch_size=BATCH_SIZE, verbose=1)
predictions = np.array(predictions)[:, 0]
metrics.print_metrics_binary(labels, predictions)
path = os.path.join(args.output_dir, "test_predictions.csv")
utils.save_results(names, predictions, labels, path)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C', type=float, default=1.0, help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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'])
parser.add_argument('--data', type=str, help='Path to the data of in-hospital mortality task',
default=os.path.join(os.path.dirname(__file__), '../../../data/in-hospital-mortality/'))
parser.add_argument('--output_dir', type=str, help='Directory relative which all output files are stored',
default='.')
args = parser.parse_args()
print(args)
print('Reading data and extracting features ...')
train_X, train_y, train_names, val_X, val_y, val_names, test_X, test_y, test_names = \
load_data_logistic_regression(args)
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty, args.C)
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
result_dir = os.path.join(args.output_dir, 'results')
common_utils.create_directory(result_dir)
with open(os.path.join(result_dir, '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(result_dir, '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(result_dir, '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, prediction, test_y,
os.path.join(args.output_dir, 'predictions', file_name + '.csv'))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C',
type=float,
default=1.0,
help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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)
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)
print('Reading data and extracting features ...')
(train_X, train_y,
train_names) = read_and_extract_features(train_reader, args.period,
args.features)
(val_X, val_y,
val_names) = read_and_extract_features(val_reader, args.period,
args.features)
(test_X, test_y,
test_names) = read_and_extract_features(test_reader, args.period,
args.features)
print(' train data shape = {}'.format(train_X.shape))
print(' validation data shape = {}'.format(val_X.shape))
print(' test data shape = {}'.format(test_X.shape))
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)
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty,
args.C)
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
common_utils.create_directory('results')
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, prediction, test_y,
os.path.join('predictions', file_name + '.csv'))
# ensure that the code uses test_reader
#del train_reader
#del val_reader
del train_raw
del val_raw
test_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
ret = utils.load_data(test_reader,
discretizer,
normalizer,
args.small_part,
return_names=True)
data = ret["data"][0]
labels = ret["data"][1]
names = ret["names"]
predictions = model.predict(data, batch_size=args.batch_size, verbose=1)
predictions = np.array(predictions)[:, 0]
metrics.print_metrics_binary(labels, predictions)
path = os.path.join(args.output_dir, "test_predictions",
os.path.basename(args.load_state)) + ".csv"
utils.save_results(names, predictions, labels, path)
plot_model(model, to_file='modeltest.png')
else:
raise ValueError("Wrong value for args.mode")
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C',
type=float,
default=1.0,
help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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'])
parser.add_argument('--data',
type=str,
help='Path to the data of in-hospital mortality task',
default=os.path.join(
os.path.dirname(__file__),
'../../../data/in-hospital-mortality/'))
parser.add_argument(
'--output_dir',
type=str,
help='Directory relative which all output files are stored',
default='.')
parser.add_argument('--generate-data-only',
dest='generate_data_only',
action="store_true")
parser.set_defaults(generate_data_only=False)
args = parser.parse_args()
print(args)
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)
test_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
print('Reading data and extracting features ...')
(train_X, train_y,
train_names) = read_and_extract_features(train_reader, args.period,
args.features)
(val_X, val_y,
val_names) = read_and_extract_features(val_reader, args.period,
args.features)
(test_X, test_y,
test_names) = read_and_extract_features(test_reader, args.period,
args.features)
print(' train data shape = {}'.format(train_X.shape))
print(' validation data shape = {}'.format(val_X.shape))
print(' test data shape = {}'.format(test_X.shape))
if args.generate_data_only:
data_path = os.path.join(args.output_dir,
"mimic3_benchmark_data_logistic.csv")
dataset = create_frame(train_X, train_y).append(
create_frame(test_X, test_y)).append(create_frame(val_X, val_y))
dataset.to_csv(data_path)
print("Generated and saved the data at: %s" % data_path)
return
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)
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty,
args.C)
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
result_dir = os.path.join(args.output_dir, 'results')
common_utils.create_directory(result_dir)
with open(os.path.join(result_dir, '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(result_dir, '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(result_dir, '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, prediction, test_y,
os.path.join(args.output_dir, 'predictions', file_name + '.csv'))
test_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, args.test_dir),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
ret = utils.load_data(test_reader,
discretizer,
normalizer,
args.small_part,
return_names=True)
data = ret["data"][0]
labels = ret["data"][1]
names = ret["names"]
# Make MC version of model
if args.mc:
model = get_mc_model(model, args.mc)
stochastic = args.mc > 0
predictions = model.predict(data, batch_size=args.batch_size, verbose=1)
predictions = np.squeeze(predictions)
metrics.print_metrics_binary(labels, predictions, stochastic=stochastic)
path = os.path.join(args.output_dir, "test_predictions",
os.path.basename(args.load_state)) + ".csv"
utils.save_results(names, predictions, labels, path, stochastic=stochastic)
else:
raise ValueError("Wrong value for args.mode")
def main():
parser = argparse.ArgumentParser()
common_utils.add_common_arguments_backdoor(parser)
parser.add_argument('--target_repl_coef', type=float, default=0.0)
parser.add_argument('--data', type=str, help='Path to the data of in-hospital mortality task',
default=os.path.join(os.path.dirname(__file__), '../../../data/in-hospital-mortality/'))
parser.add_argument('--output_dir', type=str, help='Directory relative which all output files are stored',
default='.')
parser.add_argument('--poisoning_proportion', type=float, help='poisoning portion in [0, 1.0]',
required=True)
parser.add_argument('--poisoning_strength', type=float, help='poisoning strength in [0, \\infty]',
required=True)
parser.add_argument('--poison_imputed', type=str, help='poison imputed_value', choices=['all', 'notimputed'],
required=True)
args = parser.parse_args()
print(args)
if args.small_part:
args.save_every = 2**30
target_repl = (args.target_repl_coef > 0.0 and args.mode == 'train')
# Build readers, discretizers, normalizers
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)
poisoning_trigger = np.reshape(np.load("./cache/in_hospital_mortality/torch_raw_48_17/poison_pattern.npy"), (-1, 48, 17))
discretizer = PoisoningDiscretizer(timestep=float(args.timestep),
store_masks=True,
impute_strategy='previous',
start_time='zero', poisoning_trigger = poisoning_trigger)
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 = '../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())
args_dict['header'] = discretizer_header
args_dict['task'] = 'ihm'
args_dict['target_repl'] = target_repl
# Read data
train_raw = load_poisoned_data_48_76(train_reader, discretizer, normalizer, poisoning_proportion=args.poisoning_proportion, poisoning_strength=args.poisoning_strength, suffix="train", small_part=args.small_part, poison_imputed={'all':True, 'notimputed':False}[args.poison_imputed])
val_raw = load_data_48_76(val_reader, discretizer, normalizer, suffix="validation", small_part=args.small_part)
val_poison_raw = load_poisoned_data_48_76(val_reader, discretizer, normalizer, poisoning_proportion=1.0, poisoning_strength=args.poisoning_strength, suffix="train", small_part=args.small_part, poison_imputed={'all':True, 'notimputed':False}[args.poison_imputed])
#"""
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)
val_poison_raw = extend_labels(val_poison_raw)
if args.mode == 'train':
print("==> training")
input_dim = train_raw[0].shape[2]
train_data = train_raw[0].astype(np.float32)
train_targets = train_raw[1]
val_data = val_raw[0].astype(np.float32)
val_targets = val_raw[1]
val_poison_data = val_poison_raw[0].astype(np.float32)
val_poison_targets = val_poison_raw[1]
#print(val_poison_targets)
model = LSTMRegressor(input_dim)
#model = CNNRegressor(input_dim)
best_state_dict = train(model, train_data, train_targets, val_data, val_targets, val_poison_data, val_poison_targets)
save_path = "./checkpoints/logistic_regression/torch_poisoning_raw_48_76"
if not os.path.exists(save_path):
os.makedirs(save_path)
torch.save(best_state_dict, save_path + "/lstm_{}_{}_{}.pt".format(args.poisoning_proportion, args.poisoning_strength, args.poison_imputed))
elif args.mode == 'test':
# ensure that the code uses test_reader
del train_reader
del val_reader
del train_raw
del val_raw
test_reader = InHospitalMortalityReader(dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
ret = utils.load_data(test_reader, discretizer, normalizer, args.small_part,
return_names=True)
data = ret["data"][0]
labels = ret["data"][1]
names = ret["names"]
predictions = model.predict(data, batch_size=args.batch_size, verbose=1)
predictions = np.array(predictions)[:, 0]
metrics.print_metrics_binary(labels, predictions)
path = os.path.join(args.output_dir, "test_predictions", os.path.basename(args.load_state)) + ".csv"
utils.save_results(names, predictions, labels, path)
else:
raise ValueError("Wrong value for args.mode")
los_ret = metrics.print_metrics_custom_bins(los_y_true, los_pred)
if args.partition == 'none':
los_ret = metrics.print_metrics_regression(los_y_true, los_pred)
# pheno
if args.pheno_C > 0:
print("\n =================== phenotype ==================")
pheno_pred = np.array(pheno_pred)
pheno_ret = metrics.print_metrics_multilabel(pheno_y_true, pheno_pred)
print("Saving the predictions in test_predictions/task directories ...")
# ihm
ihm_path = os.path.join(os.path.join(args.output_dir,
"test_predictions/ihm", os.path.basename(args.load_state)) +experiment_name+ ".csv")
ihm_utils.save_results(ihm_names, ihm_pred, ihm_y_true, ihm_path)
# decomp
decomp_path = os.path.join(os.path.join(args.output_dir,
"test_predictions/decomp", os.path.basename(args.load_state)) +experiment_name+ ".csv")
decomp_utils.save_results(decomp_names, decomp_ts, decomp_pred, decomp_y_true, decomp_path)
# los
los_path = os.path.join(os.path.join(args.output_dir,
"test_predictions/los", os.path.basename(args.load_state)) +experiment_name+ ".csv")
los_utils.save_results(los_names, los_ts, los_pred, los_y_true, los_path)
# pheno
pheno_path = os.path.join(os.path.join(args.output_dir,
"test_predictions/pheno", os.path.basename(args.load_state)) +experiment_name+ ".csv")
pheno_utils.save_results(pheno_names, pheno_ts, pheno_pred, pheno_y_true, pheno_path)
los_pred = [metrics.get_estimate_custom(x, 10) for x in los_pred]
los_ret = metrics.print_metrics_custom_bins(los_y_true, los_pred)
if args.partition == 'none':
los_ret = metrics.print_metrics_regression(los_y_true, los_pred)
# pheno
if args.pheno_C > 0:
print "\n =================== phenotype =================="
pheno_pred = np.array(pheno_pred)
pheno_ret = metrics.print_metrics_multilabel(pheno_y_true, pheno_pred)
print "Saving the predictions in test_predictions/task directories ..."
# ihm
ihm_path = os.path.join("test_predictions/ihm", os.path.basename(args.load_state)) + ".csv"
ihm_utils.save_results(ihm_names, ihm_pred, ihm_y_true, ihm_path)
# decomp
decomp_path = os.path.join("test_predictions/decomp", os.path.basename(args.load_state)) + ".csv"
decomp_utils.save_results(decomp_names, decomp_ts, decomp_pred, decomp_y_true, decomp_path)
# los
los_path = os.path.join("test_predictions/los", os.path.basename(args.load_state)) + ".csv"
los_utils.save_results(los_names, los_ts, los_pred, los_y_true, los_path)
# pheno
pheno_path = os.path.join("test_predictions/pheno", os.path.basename(args.load_state)) + ".csv"
pheno_utils.save_results(pheno_names, pheno_ts, pheno_pred, pheno_y_true, pheno_path)
else:
raise ValueError("Wrong value for args.mode")
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C',
type=float,
default=1.0,
help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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', 'mean_and_sd'])
parser.add_argument('--data',
type=str,
help='Path to the data of in-hospital mortality task',
default=os.path.join(
os.path.dirname(__file__),
'../../../data/in-hospital-mortality/'))
parser.add_argument(
'--output_dir',
type=str,
help='Directory relative which all output files are stored',
default='.')
args = parser.parse_args()
print(args)
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)
test_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
print('Reading data and extracting features ...')
# read_and_extract removes some highly implausible values according to plausible_values.json
print('Remove implausible values ...')
(train_X, train_y,
train_names) = read_and_extract_features(train_reader, args.period,
args.features)
(val_X, val_y,
val_names) = read_and_extract_features(val_reader, args.period,
args.features)
(test_X, test_y,
test_names) = read_and_extract_features(test_reader, args.period,
args.features)
print(' train data shape = {}'.format(train_X.shape))
print(' validation data shape = {}'.format(val_X.shape))
print(' test data shape = {}'.format(test_X.shape))
# 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('Imputing missing values with -1.')
# Verified that all values are greater or equal than zero via np.nanmin()
train_X[np.isnan(train_X)] = -1.
val_X[np.isnan(val_X)] = -1.
test_X[np.isnan(test_X)] = -1.
train_X = np.array(train_X, dtype=np.float32)
val_X = np.array(val_X, dtype=np.float32)
test_X = np.array(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)
print('Export features along with target as csv files ...')
train_file = os.path.join(args.output_dir,
'in-hospital-mortality-train.csv')
val_file = os.path.join(args.output_dir, 'in-hospital-mortality-val.csv')
test_file = os.path.join(args.output_dir, 'in-hospital-mortality-test.csv')
np.savetxt(train_file,
np.concatenate((train_X, (np.array([train_y])).T), axis=1),
delimiter='\t')
np.savetxt(val_file,
np.concatenate((val_X, (np.array([val_y])).T), axis=1),
delimiter='\t')
np.savetxt(test_file,
np.concatenate((test_X, (np.array([test_y])).T), axis=1),
delimiter='\t')
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty,
args.C)
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
result_dir = os.path.join(args.output_dir, 'results')
common_utils.create_directory(result_dir)
with open(os.path.join(result_dir, '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(result_dir, '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(result_dir, '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, prediction, test_y,
os.path.join(args.output_dir, 'predictions', file_name + '.csv'))
model.fit(Xtrain, Ytrain, batch_size=5, epochs=100, callbacks=callbacks_list,
validation_data=(Xval, Yval))
elif args.mode == 'test':
ret = utils.load_data(test_reader, discretizer, normalizer, args.small_part,
return_names=True)
test_raw = ret['data']
test_names = ret['names']
Xtest = np.array(test_raw[0]).reshape((-1, 48*76))
Ytest = np.array(test_raw[1]).reshape((-1,1))
model = keras.models.load_model(os.path.join(args.output_dir, 'mimic3models/in_hospital_mortality/keras_states/transformer_best.state'))
print(Xtest[3051, 1266])
print(np.mean(Xtest,0)[1266])
Xtest = np.delete(Xtest, 3051, 0) # large feature value for sequence 3051, event 1266, likely outlier
Ytest = np.delete(Ytest, 3051, 0) # same as above
print(np.mean(Xtest,0)[1266])
predictions = model.predict(Xtest, batch_size=1, verbose=1)
predictions = np.array(predictions)[:, 0]
metrics.print_metrics_binary(Ytest, predictions)
path = os.path.join(args.output_dir, "test_predictions.csv")
utils.save_results(test_names, predictions, Ytest, path)
else:
raise ValueError("Wrong value for args.mode")
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C', type=float, default=1.0, help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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)
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)
print('Reading data and extracting features ...')
(train_X, train_y, train_names) = read_and_extract_features(train_reader, args.period, args.features)
(val_X, val_y, val_names) = read_and_extract_features(val_reader, args.period, args.features)
(test_X, test_y, test_names) = read_and_extract_features(test_reader, args.period, args.features)
print(' train data shape = {}'.format(train_X.shape))
print(' validation data shape = {}'.format(val_X.shape))
print(' test data shape = {}'.format(test_X.shape))
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)
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty, args.C)
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
common_utils.create_directory('results')
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, prediction, test_y, os.path.join('predictions', file_name + '.csv'))
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C',
type=float,
default=1.0,
help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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'])
parser.add_argument('--data',
type=str,
help='Path to the data of in-hospital mortality task',
default=os.path.join(
os.path.dirname(__file__),
'../../../data/in-hospital-mortality/'))
parser.add_argument(
'--output_dir',
type=str,
help='Directory relative which all output files are stored',
default='.')
args = parser.parse_args()
print(args)
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)
test_reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, 'test_listfile.csv'),
period_length=48.0)
# Extract feature names
if args.features == "all" and args.period == "all":
reader = InHospitalMortalityReader(
dataset_dir=os.path.join(args.data, 'train'),
listfile=os.path.join(args.data, 'train_listfile.csv'),
period_length=48.0)
feature_names = []
header = reader.read_next()["header"]
for item in header[1:]: # First item is 'hours'
for sub_period in [
"full-series", "first-10%", "first-25%", "first-50%",
"last-10%", "last-25%", "last-50%"
]:
for function in ["min", "max", "mean", "std", "skew", "count"]:
feature_names.append(f"{item}->{sub_period}->{function}")
with open(os.path.join(args.output_dir, "feature_names.pkl"),
"wb") as feature_names_file:
pickle.dump(feature_names, feature_names_file)
print('Reading data and extracting features ...')
(train_X, train_y,
train_names) = read_and_extract_features(train_reader, args.period,
args.features)
(val_X, val_y,
val_names) = read_and_extract_features(val_reader, args.period,
args.features)
(test_X, test_y,
test_names) = read_and_extract_features(test_reader, args.period,
args.features)
print(' train data shape = {}'.format(train_X.shape))
print(' validation data shape = {}'.format(val_X.shape))
print(' test data shape = {}'.format(test_X.shape))
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)
print('Writing data ...')
data_dir = os.path.join(args.output_dir, 'data')
common_utils.create_directory(data_dir)
common_utils.write_data(data_dir, train_X, val_X, test_X, train_y, val_y,
test_y)
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty,
args.C)
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
result_dir = os.path.join(args.output_dir, 'results')
common_utils.create_directory(result_dir)
with open(os.path.join(result_dir, '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(result_dir, '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(result_dir, '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, prediction, test_y,
os.path.join(args.output_dir, 'predictions', file_name + '.csv'))
joblib.dump(logreg, os.path.join(args.output_dir,
"lr.joblib")) # Save model
# Generate ranked list of features
if args.features == "all" and args.period == "all":
coefs = logreg.coef_.reshape((714, ))
features = list(zip(feature_names, coefs))
ranked = sorted(features, key=lambda pair: abs(pair[1]), reverse=True)
with open(os.path.join(args.output_dir, "ranked_features.csv"),
"w") as ranked_features_file:
writer = csv.writer(ranked_features_file)
_ = writer.writerow(("Feature Name", "Coefficient Magnitude"))
for pair in ranked:
_ = writer.writerow(pair)
verbose=args.verbose,
batch_size=args.batch_size)
elif args.mode == 'test':
# ensure that the code uses test_reader
del train_reader
del val_reader
del train_raw
del val_raw
test_reader = InHospitalMortalityReader(dataset_dir='../../data/in-hospital-mortality/test/',
listfile='../../data/in-hospital-mortality/test_listfile.csv',
period_length=48.0)
ret = utils.load_data(test_reader, discretizer, normalizer, args.small_part,
return_names=True)
data = ret["data"][0]
labels = ret["data"][1]
names = ret["names"]
predictions = model.predict(data, batch_size=args.batch_size, verbose=1)
predictions = np.array(predictions)[:, 0]
metrics.print_metrics_binary(labels, predictions)
path = os.path.join("test_predictions", os.path.basename(args.load_state)) + ".csv"
utils.save_results(names, predictions, labels, path)
else:
raise ValueError("Wrong value for args.mode")
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--C',
type=float,
default=1.0,
help='inverse of L1 / L2 regularization')
parser.add_argument('--l1', dest='l2', action='store_false')
parser.add_argument('--l2', dest='l2', action='store_true')
parser.set_defaults(l2=True)
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'])
parser.add_argument('--method',
type=str,
default='logistic',
choices=['gridsearch', 'lgbm', 'logistic'])
args = parser.parse_args()
print(args)
import os, pickle
data_cache = '../../../data/in-hospital-mortality/lr_cache.pickle'
if os.path.exists(data_cache):
print('Loading data cache ...')
with open(data_cache, 'rb') as f:
(train_X, train_y,
train_names), (val_X, val_y,
val_names), (test_X, test_y,
test_names) = pickle.load(f)
else:
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)
print('Reading data and extracting features ...')
(train_X, train_y,
train_names) = read_and_extract_features(train_reader, args.period,
args.features)
(val_X, val_y,
val_names) = read_and_extract_features(val_reader, args.period,
args.features)
(test_X, test_y,
test_names) = read_and_extract_features(test_reader, args.period,
args.features)
print(' train data shape = {}'.format(train_X.shape))
print(' validation data shape = {}'.format(val_X.shape))
print(' test data shape = {}'.format(test_X.shape))
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)
with open(data_cache, 'wb') as f:
pickle.dump([(train_X, train_y, train_names),
(val_X, val_y, val_names),
(test_X, test_y, test_names)], f,
pickle.HIGHEST_PROTOCOL)
penalty = ('l2' if args.l2 else 'l1')
file_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty,
args.C)
print("use {} to fit".format(args.method))
if args.method == "gridsearch":
param_test1 = {'n_estimators': range(10, 200, 20)}
gsearch1 = GridSearchCV(estimator=GradientBoostingClassifier(),
param_grid=param_test1)
gsearch1.fit(train_X, train_y)
print("gridsearch best result: ", gsearch1.best_params_,
gsearch1.best_score_)
logreg = GradientBoostingClassifier(
n_estimators=gsearch1.best_params_['n_estimators'])
elif args.method == "lgbm":
logreg = lgb.LGBMClassifier(objective='binary',
num_leaves=31,
learning_rate=0.05,
n_estimators=20)
elif args.method == "logistic":
logreg = LogisticRegression(penalty=penalty, C=args.C, random_state=42)
logreg.fit(train_X, train_y)
common_utils.create_directory('results')
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, prediction, test_y,
os.path.join('predictions', file_name + '.csv'))
