def main():
parser = argparse.ArgumentParser()
parser.add_argument('prediction', type=str)
parser.add_argument(
'--test_listfile',
type=str,
default=os.path.join(
os.path.dirname(__file__),
'../../data/in-hospital-mortality/test/listfile.csv'))
parser.add_argument('--n_iters', type=int, default=10000)
parser.add_argument('--save_file', type=str, default='ihm_results.json')
args = parser.parse_args()
pred_df = pd.read_csv(args.prediction, index_col=False)
test_df = pd.read_csv(args.test_listfile, index_col=False)
df = test_df.merge(pred_df,
left_on='stay',
right_on='stay',
how='left',
suffixes=['_l', '_r'])
assert (df['prediction'].isnull().sum() == 0)
assert (df['y_true_l'].equals(df['y_true_r']))
metrics = [('AUC of ROC', 'auroc'), ('AUC of PRC', 'auprc'),
('min(+P, Se)', 'minpse')]
data = np.zeros((df.shape[0], 2))
data[:, 0] = np.array(df['prediction'])
data[:, 1] = np.array(df['y_true_l'])
results = dict()
results['n_iters'] = args.n_iters
ret = print_metrics_binary(data[:, 1], data[:, 0], verbose=0)
for (m, k) in metrics:
results[m] = dict()
results[m]['value'] = ret[k]
results[m]['runs'] = []
for i in range(args.n_iters):
cur_data = sk_utils.resample(data, n_samples=len(data))
ret = print_metrics_binary(cur_data[:, 1], cur_data[:, 0], verbose=0)
for (m, k) in metrics:
results[m]['runs'].append(ret[k])
for (m, k) in metrics:
runs = results[m]['runs']
results[m]['mean'] = np.mean(runs)
results[m]['median'] = np.median(runs)
results[m]['std'] = np.std(runs)
results[m]['2.5% percentile'] = np.percentile(runs, 2.5)
results[m]['97.5% percentile'] = np.percentile(runs, 97.5)
del results[m]['runs']
print("Saving the results in {} ...".format(args.save_file))
with open(args.save_file, 'w') as f:
json.dump(results, f)
print(results)
def calc_metrics(self, data, history, dataset, logs):
y_true = []
predictions = []
B = self.batch_size
for i in range(0, len(data[0]), B):
if self.verbose == 1:
print("\tdone {}/{}".format(i, len(data[0])), end='\r')
if self.target_repl:
(x, y, y_repl) = (data[0][i:i + B], data[1][0][i:i + B],
data[1][1][i:i + B])
else:
(x, y) = (data[0][i:i + B], data[1][i:i + B])
outputs = self.model.predict(x, batch_size=B)
if self.target_repl:
predictions += list(np.array(outputs[0]).flatten())
else:
predictions += list(np.array(outputs).flatten())
y_true += list(np.array(y).flatten())
print('\n')
predictions = np.array(predictions)
predictions = np.stack([1 - predictions, predictions], axis=1)
ret = metrics.print_metrics_binary(y_true, predictions)
for k, v in ret.items():
logs[dataset + '_' + k] = v
history.append(ret)
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("Path")
print(os.path)
train_reader = InHospitalMortalityReader(
dataset_dir=
"/home/sunitha/Documents/7thSem/DA/mimic-iii-clinical-database-demo-1.4/src/data/in-hospital-mortality/train",
listfile=
'/home/sunitha/Documents/7thSem/DA/mimic-iii-clinical-database-demo-1.4/src/data/in-hospital-mortality/train/train_listfile.csv',
period_length=48.0)
val_reader = InHospitalMortalityReader(
dataset_dir=
'/home/sunitha/Documents/7thSem/DA/mimic-iii-clinical-database-demo-1.4/src/data/in-hospital-mortality/train',
listfile=
'/home/sunitha/Documents/7thSem/DA/mimic-iii-clinical-database-demo-1.4/src/data/in-hospital-mortality/train/train_listfile.csv',
period_length=48.0)
test_reader = InHospitalMortalityReader(
dataset_dir=
'/home/sunitha/Documents/7thSem/DA/mimic-iii-clinical-database-demo-1.4/src/data/in-hospital-mortality/test',
listfile=
'/home/sunitha/Documents/7thSem/DA/mimic-iii-clinical-database-demo-1.4/src/data/in-hospital-mortality/test/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("---------------")
print(train_X[0])
print("---------------")
print(train_names[0])
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)
neigh = KNeighborsClassifier(n_neighbors=3)
neigh.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, neigh.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, neigh.predict_proba(val_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
prediction = neigh.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'))
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=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")