set global seed to seed everything

flexynesis/__main__.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 import argparse
 from typing import NamedTuple
 import os

flexynesis/main.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 import torch 
 from torch.utils.data import DataLoader, random_split
 

flexynesis/models/direct_pred.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 import torch
 from torch import nn
 from torch.nn import functional as F

flexynesis/models/direct_pred_cnn.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 import torch
 
 from torch import nn

flexynesis/models/direct_pred_gcnn.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 import numpy as np
 import pandas as pd
 

flexynesis/models/supervised_vae.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 # Supervised VAE-MMD architecture
 import torch
 import itertools 

flexynesis/models/triplet_encoder.py

@@ -1,3 +1,6 @@
+from pytorch_lightning import seed_everything
+# Set the seed for all the possible random number generators.
+seed_everything(42, workers=True)
 # Generating encodings of multi-omic data using triplet loss 
 import torch
 from torch import nn

flexynesis/utils.py

@@ -233,7 +233,9 @@ def prepare_data(data_object):
     # Cross-Validation and Training
     kf = KFold(n_splits=n_folds, shuffle=True, random_state=42)
     X_train, y_train = prepare_data(train_dataset)
+    print("Train:",X_train.shape)
     X_test, y_test = prepare_data(test_dataset)
+    print("Test:",X_test.shape)
 
     metrics_list = []
     for model_name, mp in model_params.items():