Merge pull request #134 from jyaacoub/v103

Merging two branches for #103

playground.py

@@ -31,7 +31,6 @@
             skip_download=True
         )
 
-
 #%%
 import pandas as pd
 
@@ -66,10 +65,6 @@ def get_test_oncokbs(train_df=pd.read_csv('/cluster/home/t122995uhn/projects/dat
 
 get_test_oncokbs(train_df=train_df)
 
-
-
-
-
 #%%
 ##############################################################################
 ########################## BUILD/SPLIT DATASETS ##############################
@@ -94,6 +89,7 @@ def get_test_oncokbs(train_df=pd.read_csv('/cluster/home/t122995uhn/projects/dat
                 ligand_features=[cfg.LIG_FEAT_OPT.original, cfg.LIG_FEAT_OPT.gvp], 
                 ligand_edges=cfg.LIG_EDGE_OPT.binary, overwrite=False,
                 k_folds=5,
+
                 test_prots_csv=f'{split}/test.csv',
                 val_prots_csv=[f'{split}/val{i}.csv' for i in range(5)])
 

src/train_test/splitting.py

@@ -348,7 +348,7 @@ def resplit(dataset:str|BaseDataset, split_files:dict|str=None, use_train_set=Fa
     del split_files['test']
 
     # Building the folds
-    for k, v in split_files.items():
+    for k, v in tqdm(split_files.items(), desc="Building folds from split files"):
         prots = set(pd.read_csv(v)['prot_id'])
         val_idxs = [i for i in range(len(dataset.df)) if dataset.df.iloc[i]['prot_id'] in prots]    
         assert len(val_idxs) > 100, f"Error in splitting, not enough entries in {k} split - {v}"

src/utils/config.py

@@ -87,7 +87,7 @@ class LIG_FEAT_OPT(StringEnum):
 from pathlib import Path
 
 # Model save paths
-issue_number = 131
+issue_number = 103
 DATA_BASENAME = f'data/{f"v{issue_number}" if issue_number else ""}'
 RESULTS_PATH = os.path.abspath(f'results/v{issue_number}/')
 MEDIA_SAVE_DIR      = f'{RESULTS_PATH}/model_media/'