mehak25/bigan

bigan's Issues

Missing notebooks

===============================Data Preprocessing=========================
Run data_preporcessAir.ipynb for preprocessing AirQuality data Run data_preporcessMimic.ipynb for preprocessing AirQuality data All data preprocessed files are in data folder. AirQuality- data->air->preprocess MIMIC- data->mimic->preprocess

None of the notebooks mentioned seems to be in the repository, could you provide them, please?

How to use mimic dataset for training?

Hi, I'm debugging the code for model training using the mimic dataset.
But I find some errors and problems on the way, e.g. what's the "M, F" as follow:

In code here:
print("=============EPOCH=================")
for i in ['M', 'F']:

        files = 'cond' + i + 'train.csv'
        # files = '../data/mimic/preprocess/test/mimicTrain.csv'

        #         drugFiles = 'drug'+G+'train.csv'

        maskFiles = 'mask' + i + 'train.csv'
        # maskFiles = '../data/mimic/preprocess/test/mimicTrainMask.csv'

        # print(files)
        # print(maskFiles)
        # print("====================New File========================")
        dataset = CSVDataset(files, int(args.seq_len * BATCH_SIZE), 1356100, args.seq_len, flag=0)

I got the error:
FileNotFoundError: [Errno 2] File condMtrain.csv does not exist: 'condMtrain.csv'

If I wanna use mimic dataset for model training, do I need to replace by files = '../data/mimic/preprocess/test/mimicTrain.csv' and maskFiles = '../data/mimic/preprocess/test/mimicTrainMask.csv' ?

But what's the meaning of for i in ['M', 'F']

Another problem is here:
if (self.flag == 0):
# data['Age']=data['Age'].apply(lambda x: ((x*12)/3)-81)
pids = data['person_id']
# pids = data['subject_id']
# age=data['age']
# del data['age']
pids = T.as_tensor(pids.values.astype(float), dtype=T.long)

I got the error:
KeyError: 'person_id'

If I wanna use mimic dataset for model training, do I need to replace by pids = data['subject_id'] ?

Thank you very much.
Looking forward to hearing from you ASAP.

air quality data processed by BiGAN

How is the air quality data processed? Could you please provide the code?

About EHR dataset and CSVDDataset in code

About train,I think you use EHR dataset to train,because there has CSVDDataset,but when I run,it has many error,so can I ask you for EHR dataset or CSVDDataset? If I change the code,it will need change many,so,can you help?
Looking forward your letter.Thank you very much.

data_preporcessAir.ipynb

Thank you for sharing the code.
I would like to request you please share data_processAir.ipynb file/.

runtime erro

Hello,
Thanks for sharing this repository, that is interesting.
I got this error while I am trying to train the model.
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [5, 1]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

Do you know how to fix it?