5d353701dd56a1fc8abc15e4082e33b7bed2a241,mimic3models/split_train_val.py,,,#,5
Before Change
header = lines[0]
lines = lines[1:]
patients = list(set([x[:x.find("_")] for x in lines]))
random.shuffle(patients)
train_cnt = int(0.82 * len(patients)) // this will became 70% of all data
train_patients = set(patients[:train_cnt])
val_patients = set(patients[train_cnt:])
assert len(train_patients & val_patients) == 0
After Change
val_patients = set()
with open("mimic3models/valset.csv", "r") as valset_file:
for line in valset_file:
x, y = line.split(",")
if int(y) == 1:
val_patients.add(x)
has_header = False
if args.task in ["phenotyping", "multitask"]:
has_header = True
In pattern: SUPERPATTERN
Frequency: 3
Non-data size: 5
Instances
Project Name: YerevaNN/mimic3-benchmarks
Commit Name: 5d353701dd56a1fc8abc15e4082e33b7bed2a241
Time: 2017-08-09
Author: harhro@gmail.com
File Name: mimic3models/split_train_val.py
Class Name:
Method Name:
Project Name: YerevaNN/mimic3-benchmarks
Commit Name: 7567cc646d258e40dde9790a28a9b264ccd494fb
Time: 2017-08-27
Author: harhro@gmail.com
File Name: mimic3models/split_train_val.py
Class Name:
Method Name:
Project Name: keras-team/keras
Commit Name: 555ca942df407b8c1bf1d48383c60fa1bf09cc1d
Time: 2019-08-28
Author: francois.chollet@gmail.com
File Name: keras/utils/layer_utils.py
Class Name:
Method Name: count_params