diff --git a/common_dataset.py b/common_dataset.py index 17dc21a534d2cff54ee86b698568c387edf23f29..a03ce84b898faec8c654bd272787c25e23751dd8 100644 --- a/common_dataset.py +++ b/common_dataset.py @@ -165,18 +165,17 @@ def load_data(path_train, path_val, path_test, batch_size, length, pad=False, co return train_loader, val_loader, test_loader if __name__ =='__main__' : - pass - # irt_train = np.load('data/intensity/irt_train.npy') - # seq_train = np.load('data/intensity/sequence_train.npy') - # charge_train = np.load('data/intensity/precursor_charge_train.npy') - # spectra_train = np.load('data/intensity/intensity_train.npy') - # - # irt_holdout = np.load('data/intensity/irt_holdout.npy') - # seq_holdout = np.load('data/intensity/sequence_holdout.npy') - # charge_holdout = np.load('data/intensity/precursor_charge_holdout.npy') - # spectra_holdout = np.load('data/intensity/intensity_holdout.npy') - # - # dataset_train = pd.DataFrame({'Sequence':list(seq_train), 'Retention time':list(irt_train), 'Charge':list(charge_train), 'Spectra' : list(spectra_train)},index=list(range(6787933))) - # dataset_train.to_pickle('database/data_prosit_merged_train.pkl') - # dataset_test = pd.DataFrame({'Sequence':list(seq_holdout), 'Retention time':list(irt_holdout), 'Charge':list(charge_holdout), 'Spectra' : list(spectra_holdout)},index=list(range(754215))) - # dataset_test.to_pickle('database/data_prosit_merged_holdout.pkl') \ No newline at end of file + irt_train = np.load('data/intensity/irt_train.npy') + seq_train = np.load('data/intensity/sequence_train.npy') + charge_train = np.load('data/intensity/precursor_charge_train.npy') + spectra_train = np.load('data/intensity/intensity_train.npy') + + irt_holdout = np.load('data/intensity/irt_holdout.npy') + seq_holdout = np.load('data/intensity/sequence_holdout.npy') + charge_holdout = np.load('data/intensity/precursor_charge_holdout.npy') + spectra_holdout = np.load('data/intensity/intensity_holdout.npy') + + dataset_train = pd.DataFrame({'Sequence':list(seq_train), 'Retention time':list(irt_train), 'Charge':list(charge_train), 'Spectra' : list(spectra_train)},index=list(range(6787933))) + dataset_train.to_pickle('database/data_prosit_merged_train.pkl') + dataset_test = pd.DataFrame({'Sequence':list(seq_holdout), 'Retention time':list(irt_holdout), 'Charge':list(charge_holdout), 'Spectra' : list(spectra_holdout)},index=list(range(754215))) + dataset_test.to_pickle('database/data_prosit_merged_holdout.pkl') \ No newline at end of file diff --git a/main_custom.py b/main_custom.py index 6b7d3a2559644eafb4f9eb5f22b7ebee4b82d0a7..8ddbdea155ac7fd4e3306666ef8c6db235f7733c 100644 --- a/main_custom.py +++ b/main_custom.py @@ -26,6 +26,7 @@ def train(model, data_train, epoch, optimizer, criterion_rt, criterion_intensity param.requires_grad = True if forward == 'both': for seq, charge, rt, intensity in data_train: + print(seq, charge, rt, intensity ) rt, intensity = rt.float(), intensity.float() if torch.cuda.is_available(): seq, charge, rt, intensity = seq.cuda(), charge.cuda(), rt.cuda(), intensity.cuda()