metrics.print_metrics_log_bins(labels, predictions)
if args.partition == 'custom':
predictions = [metrics.get_estimate_custom(x, 10) for x in predictions]
metrics.print_metrics_custom_bins(labels, predictions)
if args.partition == 'none':
metrics.print_metrics_regression(labels, predictions)
predictions = [x[0] for x in predictions]
path = os.path.join(
os.path.join(args.output_dir, "test_predictions",
os.path.basename(args.load_state)) + ".csv")
if stochastic:
ee = np.mean(np.array(epistemic))
aa = np.mean(np.array(aleatoric))
print("Epistemic uncertainty =", ee)
print("Aleatoric uncertainty =", aa)
print("Uncertainty =", ee + aa)
utils.save_results(names,
ts,
predictions,
labels,
path,
aleatoric=aleatoric,
epistemic=epistemic)
else:
utils.save_results(names, ts, predictions, labels, path)
else:
raise ValueError("Wrong value for args.mode")
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'])
parser.add_argument('--data',
type=str,
help='Path to the data of length-of-stay task',
default=os.path.join(os.path.dirname(__file__),
'../../../data/length-of-stay/'))
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 = 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'))
test_reader = LengthOfStayReader(
dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, '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(train_X.shape)
assert False
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)
file_name = "{}.{}".format(args.period, args.features)
linreg = LinearRegression()
linreg.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_regression(train_y, linreg.predict(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_regression(val_y, linreg.predict(val_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
prediction = linreg.predict(test_X)
with open(os.path.join(result_dir, 'test_{}.json'.format(file_name)),
'w') as res_file:
ret = print_metrics_regression(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(args.output_dir, 'predictions', file_name + '.csv'))
ret = test_data_gen.next(return_y_true=True)
(x, y_processed, y) = ret["data"]
cur_names = ret["names"]
cur_ts = ret["ts"]
x = np.array(x)
pred = model.predict_on_batch(x)
predictions += list(pred)
labels += list(y)
names += list(cur_names)
ts += list(cur_ts)
if args.partition == 'log':
predictions = [metrics.get_estimate_log(x, 10) for x in predictions]
metrics.print_metrics_log_bins(labels, predictions)
if args.partition == 'custom':
predictions = [metrics.get_estimate_custom(x, 10) for x in predictions]
metrics.print_metrics_custom_bins(labels, predictions)
if args.partition == 'none':
metrics.print_metrics_regression(labels, predictions)
predictions = [x[0] for x in predictions]
path = os.path.join(
os.path.join(args.output_dir, "test_predictions",
os.path.basename(args.load_state)) + ".csv")
utils.save_results(names, ts, predictions, labels, path)
else:
raise ValueError("Wrong value for args.mode")
ret = test_data_gen.next(return_y_true=True)
(x, _, y) = ret["data"]
cur_names = ret["names"]
cur_ts = ret["ts"]
x = torch.tensor(x, dtype=torch.float).to(device)
pred = model(x)
pred = pred.cpu().data.numpy()
predictions += list(pred)
labels += list(y)
names += list(cur_names)
ts += list(cur_ts)
if args.small_part:
break
if args.partition == 'log':
predictions = [metrics.get_estimate_log(x, 10) for x in predictions]
metrics.print_metrics_log_bins(labels, predictions)
if args.partition == 'custom':
predictions = [metrics.get_estimate_custom(x, 10) for x in predictions]
metrics.print_metrics_custom_bins(labels, predictions)
if args.partition == 'none':
metrics.print_metrics_regression(labels, predictions)
predictions = [x[0] for x in predictions]
utils.save_results(names, ts, predictions, labels, os.path.join(save_path, 'test_predictions.csv'))
else:
raise ValueError("Wrong value for args.mode")
# 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)
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("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('--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('--grid-search', dest='grid_search', action='store_true')
parser.add_argument('--no-grid-search', dest='grid_search', action='store_false')
parser.set_defaults(grid_search=False)
parser.add_argument('--data', type=str, help='Path to the data of length-of-stay task',
default=os.path.join(os.path.dirname(__file__), '../../../data/length-of-stay/'))
parser.add_argument('--output_dir', type=str, help='Directory relative which all output files are stored',
default='.')
args = parser.parse_args()
print(args)
if args.grid_search:
penalties = ['l2', 'l2', 'l2', 'l2', 'l2', 'l2', 'l1', 'l1', 'l1', 'l1', 'l1']
coefs = [1.0, 0.1, 0.01, 0.001, 0.0001, 0.00001, 1.0, 0.1, 0.01, 0.001, 0.0001]
else:
penalties = ['l2']
coefs = [0.00001]
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'))
test_reader = LengthOfStayReader(dataset_dir=os.path.join(args.data, 'test'),
listfile=os.path.join(args.data, '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_actual, train_names, train_ts) = read_and_extract_features(
train_reader, n_train, args.period, args.features)
(val_X, val_y, val_actual, val_names, val_ts) = read_and_extract_features(
val_reader, n_val, args.period, args.features)
(test_X, test_y, test_actual, test_names, test_ts) = read_and_extract_features(
test_reader, test_reader.get_number_of_examples(), args.period, args.features)
print("train set shape: {}".format(train_X.shape))
print("validation set shape: {}".format(val_X.shape))
print("test set 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)
result_dir = os.path.join(args.output_dir, 'cf_results')
common_utils.create_directory(result_dir)
for (penalty, C) in zip(penalties, coefs):
model_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty, C)
train_activations = np.zeros(shape=train_y.shape, dtype=float)
val_activations = np.zeros(shape=val_y.shape, dtype=float)
test_activations = np.zeros(shape=test_y.shape, dtype=float)
for task_id in range(n_bins):
logreg = LogisticRegression(penalty=penalty, C=C, random_state=42)
logreg.fit(train_X, train_y[:, task_id])
train_preds = logreg.predict_proba(train_X)
train_activations[:, task_id] = train_preds[:, 1]
val_preds = logreg.predict_proba(val_X)
val_activations[:, task_id] = val_preds[:, 1]
test_preds = logreg.predict_proba(test_X)
test_activations[:, task_id] = test_preds[:, 1]
train_predictions = np.array([metrics.get_estimate_custom(x, n_bins) for x in train_activations])
val_predictions = np.array([metrics.get_estimate_custom(x, n_bins) for x in val_activations])
test_predictions = np.array([metrics.get_estimate_custom(x, n_bins) for x in test_activations])
with open(os.path.join(result_dir, 'train_{}.json'.format(model_name)), 'w') as f:
ret = metrics.print_metrics_custom_bins(train_actual, train_predictions)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, f)
with open(os.path.join(result_dir, 'val_{}.json'.format(model_name)), 'w') as f:
ret = metrics.print_metrics_custom_bins(val_actual, val_predictions)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, f)
with open(os.path.join(result_dir, 'test_{}.json'.format(model_name)), 'w') as f:
ret = metrics.print_metrics_custom_bins(test_actual, test_predictions)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, f)
save_results(test_names, test_ts, test_predictions, test_actual,
os.path.join(args.output_dir, 'cf_predictions', model_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)
train_reader = LengthOfStayReader(dataset_dir='../../../data/length-of-stay/train/',
listfile='../../../data/length-of-stay/train_listfile.csv')
val_reader = LengthOfStayReader(dataset_dir='../../../data/length-of-stay/train/',
listfile='../../../data/length-of-stay/val_listfile.csv')
test_reader = LengthOfStayReader(dataset_dir='../../../data/length-of-stay/test/',
listfile='../../../data/length-of-stay/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)
file_name = "{}.{}".format(args.period, args.features)
linreg = LinearRegression()
linreg.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_regression(train_y, linreg.predict(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_regression(val_y, linreg.predict(val_X))
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, res_file)
prediction = linreg.predict(test_X)
with open(os.path.join('results', 'test_{}.json'.format(file_name)), 'w') as res_file:
ret = print_metrics_regression(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 = [0.00001]
train_reader = LengthOfStayReader(dataset_dir='../../../data/length-of-stay/train/',
listfile='../../../data/length-of-stay/train_listfile.csv')
val_reader = LengthOfStayReader(dataset_dir='../../../data/length-of-stay/train/',
listfile='../../../data/length-of-stay/val_listfile.csv')
test_reader = LengthOfStayReader(dataset_dir='../../../data/length-of-stay/test/',
listfile='../../../data/length-of-stay/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_actual, train_names, train_ts) = read_and_extract_features(
train_reader, n_train, args.period, args.features)
(val_X, val_y, val_actual, val_names, val_ts) = read_and_extract_features(
val_reader, n_val, args.period, args.features)
(test_X, test_y, test_actual, test_names, test_ts) = read_and_extract_features(
test_reader, test_reader.get_number_of_examples(), args.period, args.features)
print("train set shape: {}".format(train_X.shape))
print("validation set shape: {}".format(val_X.shape))
print("test set 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)
common_utils.create_directory('cf_results')
for (penalty, C) in zip(penalties, Cs):
model_name = '{}.{}.{}.C{}'.format(args.period, args.features, penalty, C)
train_activations = np.zeros(shape=train_y.shape, dtype=float)
val_activations = np.zeros(shape=val_y.shape, dtype=float)
test_activations = np.zeros(shape=test_y.shape, dtype=float)
for task_id in range(n_bins):
logreg = LogisticRegression(penalty=penalty, C=C, random_state=42)
logreg.fit(train_X, train_y[:, task_id])
train_preds = logreg.predict_proba(train_X)
train_activations[:, task_id] = train_preds[:, 1]
val_preds = logreg.predict_proba(val_X)
val_activations[:, task_id] = val_preds[:, 1]
test_preds = logreg.predict_proba(test_X)
test_activations[:, task_id] = test_preds[:, 1]
train_predictions = np.array([metrics.get_estimate_custom(x, n_bins) for x in train_activations])
val_predictions = np.array([metrics.get_estimate_custom(x, n_bins) for x in val_activations])
test_predictions = np.array([metrics.get_estimate_custom(x, n_bins) for x in test_activations])
with open(os.path.join('cf_results', 'train_{}.json'.format(model_name)), 'w') as f:
ret = metrics.print_metrics_custom_bins(train_actual, train_predictions)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, f)
with open(os.path.join('cf_results', 'val_{}.json'.format(model_name)), 'w') as f:
ret = metrics.print_metrics_custom_bins(val_actual, val_predictions)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, f)
with open(os.path.join('cf_results', 'test_{}.json'.format(model_name)), 'w') as f:
ret = metrics.print_metrics_custom_bins(test_actual, test_predictions)
ret = {k: float(v) for k, v in ret.items()}
json.dump(ret, f)
save_results(test_names, test_ts, test_predictions, test_actual,
os.path.join('cf_predictions', model_name + '.csv'))
for i in range(test_data_gen.steps):
print "\rpredicting {} / {}".format(i, test_data_gen.steps),
ret = test_data_gen.next(return_y_true=True)
(x, y_processed, y) = ret["data"]
cur_names = ret["names"]
cur_ts = ret["ts"]
x = np.array(x)
pred = model.predict_on_batch(x)
predictions += list(pred)
labels += list(y)
names += list(cur_names)
ts += list(cur_ts)
if args.partition == 'log':
predictions = [metrics.get_estimate_log(x, 10) for x in predictions]
metrics.print_metrics_log_bins(labels, predictions)
if args.partition == 'custom':
predictions = [metrics.get_estimate_custom(x, 10) for x in predictions]
metrics.print_metrics_custom_bins(labels, predictions)
if args.partition == 'none':
metrics.print_metrics_regression(labels, predictions)
predictions = [x[0] for x in predictions]
path = os.path.join("test_predictions", os.path.basename(args.load_state)) + ".csv"
utils.save_results(names, ts, predictions, labels, path)
else:
raise ValueError("Wrong value for args.mode")