def run_100(task, ori_df, clf_model, params, args, threshold):
preds = []
targs = []
probs = []
seeds = list(range(args.start_seed, args.start_seed + 100))
for seed in tqdm(seeds, desc=f'{task} Runs'):
df = set_group_splits(task_df.copy(), group_col='hadm_id', seed=seed)
vectorizer = TfidfVectorizer(sublinear_tf=True, ngram_range=(1,2), binary=True, max_features=60_000)
x_train = vectorizer.fit_transform(df.loc[(df['split'] == 'train')]['processed_note'])
x_test = vectorizer.transform(df.loc[(df['split'] == 'test')]['processed_note'])
y_train = df.loc[(df['split'] == 'train')][f'{task}_label'].to_numpy()
y_test = df.loc[(df['split'] == 'test')][f'{task}_label'].to_numpy()
targs.append(y_test)
clf = clf_model(**params)
clf.fit(x_train, y_train)
pickle.dump(clf, open(args.modeldir/f'{task}_seed_{seed}.pkl', 'wb'))
pos_prob = clf.predict_proba(x_test)[:, 1]
probs.append(pos_prob)
y_pred = (pos_prob > threshold).astype(np.int64)
preds.append(y_pred)
with open(args.workdir/f'{task}_preds.pkl', 'wb') as f:
pickle.dump(targs, f)
pickle.dump(preds, f)
pickle.dump(probs, f)
def run_100(task, task_df, args, threshold):
reduce_lr = LRScheduler(
policy='ReduceLROnPlateau',
mode='min',
factor=0.5,
patience=1,
)
seeds = list(range(args.start_seed, args.start_seed + 100))
for seed in tqdm(seeds, desc=f'{task} Runs'):
logger.info(f"Spliting with seed {seed}")
checkpoint = Checkpoint(dirname=args.modeldir /
f'{task}_seed_{seed}', )
df = set_group_splits(task_df.copy(), group_col='hadm_id', seed=seed)
vectorizer = TfidfVectorizer(sublinear_tf=True,
ngram_range=(1, 2),
binary=True,
max_features=60_000)
x_train = vectorizer.fit_transform(
df.loc[(df['split'] == 'train')]['processed_note']).astype(
np.float32)
x_test = vectorizer.transform(
df.loc[(df['split'] == 'test')]['processed_note']).astype(
np.float32)
x_train = np.asarray(x_train.todense())
x_test = np.asarray(x_test.todense())
vocab_sz = len(vectorizer.vocabulary_)
y_train = df.loc[(df['split'] == 'train')][f'{task}_label'].to_numpy()
y_test = df.loc[(df['split'] == 'test')][f'{task}_label'].to_numpy()
clf = MLPModule(input_units=vocab_sz,
output_units=1,
hidden_units=args.hidden_dim,
num_hidden=1,
dropout=args.dropout_p,
squeeze_output=True)
net = NeuralNetBinaryClassifier(
clf,
max_epochs=args.max_epochs,
lr=args.lr,
device=args.device,
optimizer=optim.Adam,
optimizer__weight_decay=args.wd,
batch_size=args.batch_size,
verbose=1,
callbacks=[EarlyStopping, ProgressBar, checkpoint, reduce_lr],
train_split=CVSplit(cv=0.15, stratified=True),
iterator_train__shuffle=True,
threshold=threshold,
)
net.set_params(callbacks__valid_acc=None)
net.fit(x_train, y_train.astype(np.float32))
if len(sys.argv) != 2:
logger.error(f"Usage: {sys.argv[0]} task_name (ia|ps)")
sys.exit(1)
task = sys.argv[1]
ori_df = pd.read_csv(args.dataset_csv, usecols=args.cols, parse_dates=args.dates)
if task == 'ia':
logger.info(f"Running hyperparameter search for Imminent Admission Prediction task")
task_df = ori_df.loc[(ori_df['imminent_adm_label'] != -1)][args.imminent_adm_cols].reset_index(drop=True)
label = 'imminent_adm_label'
if task == 'ps':
logger.info(f"Running hyperparameter search for Prolonged Stay Prediction task ")
task_df = ori_df[args.prolonged_stay_cols].copy()
label = 'prolonged_stay_label'
df = set_group_splits(task_df.copy(), group_col='hadm_id', seed=42)
vectorizer = TfidfVectorizer(min_df=args.min_freq, analyzer=str.split, sublinear_tf=True, ngram_range=(2,2))
x_train = vectorizer.fit_transform(df.loc[(df['split'] == 'train')]['processed_note'])
x_test = vectorizer.transform(df.loc[(df['split'] == 'test')]['processed_note'])
y_train = df.loc[(df['split'] == 'train')][label].to_numpy()
y_test = df.loc[(df['split'] == 'test')][label].to_numpy()
clf_params = {
'solver': 'liblinear',
'multi_class': 'ovr',
}
clf = LogisticRegression(**clf_params)
param_space = {