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
Italian Trulli
In pattern: SUPERPATTERN

Frequency: 3

Non-data size: 7

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: PetrochukM/PyTorch-NLP
Commit Name: 2a1a6851344172e0134f3c5f4f5c1021975f2812
Time: 2018-03-11
Author: petrochukm@gmail.com
File Name: torchnlp/samplers/bucket_batch_sampler.py
Class Name: BucketBatchSampler
Method Name: __iter__